system

Abstract

Provide a system. A means for acquiring an image of an intersection in real time; A means for analyzing the acquired video to detect passing vehicles and pedestrians; means for determining traffic volume based on the detection result; means for changing the traffic signal when it is determined that the traffic volume is equal to or less than a predetermined threshold; a means for checking the signal status after the change; A system including:

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional traffic lights switch between red and green at fixed intervals, regardless of whether vehicles or pedestrians are passing through, making it difficult to efficiently manage traffic flow. Furthermore, unnecessary waits at traffic lights occur, especially at night or during periods of low traffic, resulting in wasted time and fuel. The present invention addresses these issues and aims to provide a system that streamlines traffic flow. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for acquiring images of intersections in real time, a means for analyzing the acquired images to detect passing vehicles and pedestrians, and a means for determining traffic volume based on the detection results. Furthermore, the system includes a means for changing signals when it determines that traffic volume is below a predetermined threshold, and a means for confirming the signal status after the change, thereby achieving efficient signal control. This system appropriately switches signals when traffic volume is low, smoothing traffic flow and reducing unnecessary waits at traffic lights.

[0006] The "means for acquiring an image of an intersection in real time" is a device including equipment and a system for acquiring an image of an intersection in real time.

[0007] "Means for analyzing acquired video and detecting passing vehicles and pedestrians" refers to devices and programs for analyzing acquired video data and identifying and detecting vehicles and pedestrians present in the video.

[0008] The "means for determining traffic volume based on the detection results" refers to a device and algorithm for determining whether the current traffic volume is below a certain threshold based on the detection results obtained by analysis.

[0009] The "means for changing the signal when it is determined that the traffic volume is equal to or less than a predetermined threshold" refers to a device and a program for changing the state of the signal based on the result of determining the traffic volume.

[0010] The "means for checking the signal status after the change" refers to a device and a program for checking whether the signal change has been carried out correctly. [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0012] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0013] First, the terms used in the following description will be explained.

[0014] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0015] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0016] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0017] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0022] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0024] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0025] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0031] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0032] The present invention aims to efficiently control traffic lights at intersections. The system includes a server, cameras installed at intersections, and a traffic light control device.

[0033] System Overview

[0034] The server acquires video in real time from cameras installed at intersections and analyzes the video to detect passing vehicles and pedestrians. It also determines the traffic volume based on the detection results and changes the traffic lights if it determines that the traffic volume is below a predetermined threshold. After the traffic light change is made, the server checks the results and records them in a log.

[0035] Explanation of program processing

[0036] Acquiring camera footage

[0037] The server acquires video images in real time from cameras installed at intersections. The server periodically sends requests to the cameras according to a schedule and receives video data. The received video data is temporarily stored in memory.

[0038] Video Analysis

[0039] The server uses a video analysis module to analyze the captured video. The video analysis module utilizes deep learning models to identify and detect vehicles and pedestrians in the video. Information about each detected object, such as its location, direction of movement, and speed, is recorded in a list.

[0040] Traffic volume determination

[0041] The server evaluates the current traffic volume based on the detected object list. The evaluation criterion is set as a threshold, and it determines whether the traffic volume is below this threshold. For example, if there are no vehicles or pedestrians passing by, it determines that the traffic volume is below the threshold.

[0042] Traffic light changes

[0043] The server changes the traffic light when it determines that the traffic volume is below a predetermined threshold. It checks the current status of the traffic light and sends a command to the traffic light controller to switch the traffic light from red to green or from green to red as necessary.

[0044] Check and log signal status

[0045] After the signal change, the server sends a status request to the signal controller again to check whether the signal change was successful. If the change is successful, the result is recorded in a log file. The log includes the time of the signal change, the type of change (from red to green, or from green to red), and the reason for the change (traffic volume evaluation result).

[0046] Specific examples

[0047] Nighttime intersection

[0048] 1. The server acquires real-time video from a camera installed at an intersection at night.

[0049] 2. The server uses a video analysis module to detect the absence of moving vehicles or pedestrians in the video.

[0050] 3. The server evaluates the traffic volume to be zero and determines that this is below a set threshold (e.g., less than 3 vehicles).

[0051] 4. The server determines that the current traffic light state is red and that the light should be changed to green.

[0052] 5. The server sends a command to the traffic light controller to change the light to green.

[0053] 6. The server verifies that the traffic light has changed to green and logs the result.

[0054] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume, thereby optimizing traffic flow.

[0055] The processing flow will be explained below.

[0056] Step 1:

[0057] The server acquires video in real time from cameras installed at intersections. The server periodically sends requests to the cameras to receive video data. The received video data is temporarily stored in memory.

[0058] Step 2:

[0059] The server uses a video analysis module to analyze the acquired video data. The server inputs the video data into the video analysis module, which uses a deep learning model to identify vehicles and pedestrians in the video.

[0060] Step 3:

[0061] The server extracts information about each identified object, such as its location, direction of movement, and speed, and compiles this information into a list that is saved as the analysis results.

[0062] Step 4:

[0063] The server analyzes the detection result list and evaluates the current traffic volume. The server compares it with a set threshold and determines whether the traffic volume is below the threshold. For example, if there are less than three vehicles, it determines that the traffic volume is below the threshold.

[0064] Step 5:

[0065] The server obtains the current signal status from the signal controller. The server sends a status request to the signal controller to check whether the signal is currently red or green.

[0066] Step 6:

[0067] The server determines whether the traffic light needs to be changed based on the traffic volume evaluation result and the traffic light status. If the traffic volume is low and the traffic light is red, the server determines that the traffic light needs to be changed to green.

[0068] Step 7:

[0069] The server sends a signal switching command to the signal control device. The server sends a command to the signal control device to change the signal to green, and verifies that the command was sent successfully.

[0070] Step 8:

[0071] The server checks the changed signal status and sends a status request to the signal controller again to check whether the signal has been changed to green correctly.

[0072] Step 9:

[0073] The server records the result of the traffic light change in a log. If a change is confirmed, the result is written to a log file. The log records the time of the traffic light change, the type of change (red to green, green to red), and the reason for the change (traffic volume evaluation result).

[0074] Step 10:

[0075] The server starts again by acquiring camera footage after a certain time, setting a timer and repeating this process at regular intervals.

[0076] By following the above steps, the server can automatically control the traffic lights at the intersection and achieve efficient traffic light changes according to the traffic volume.

[0077] Example 1

[0078] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0079] Traffic light control at intersections is often performed at fixed timings and is sometimes unable to respond to fluctuations in traffic volume. As a result, traffic congestion and unnecessary waits at traffic lights occur, posing the problem of inefficient traffic flow. In addition, due to a lack of flexible control of traffic lights at night and during off-peak hours, it is not possible to change traffic lights according to traffic volume.

[0080] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0081] In this invention, the server includes means for acquiring images in real time from cameras at intersections, means for temporarily storing the acquired images in memory, means for analyzing the stored images to detect passing vehicles and pedestrians, means for recording the positions, movement directions, and speeds of the detected vehicles and pedestrians in a list, means for determining traffic volume based on the detection results, means for changing the traffic signal if it is determined that the traffic volume is below a predetermined threshold, means for reacquiring and confirming the signal status after the change, and means for recording the change results in a log. This enables flexible signal changes according to traffic volume, thereby optimizing traffic flow.

[0082] An "intersection camera" is a camera device that is installed at an intersection and captures images of the surrounding area in real time.

[0083] "Real-time" means that data or information is processed at the same time it is acquired.

[0084] A "server" is a computer system that processes, stores, analyzes, etc., video data acquired from cameras at intersections.

[0085] "Means for acquiring video" refers to a method or system for receiving video data from an intersection camera in real time.

[0086] "Means for temporarily storing in memory" refers to a storage device for temporarily storing received video data and a method for operating the storage device.

[0087] "Means for analyzing video" refers to methods and systems that use computer vision and deep learning technology to analyze acquired video data and extract important information.

[0088] "Means for detecting vehicles and pedestrians" refers to methods and systems that use video analysis to identify moving objects such as vehicles and pedestrians and determine their locations and attributes.

[0089] "Means for recording in a list" refers to a method or system for recording and managing information about detected vehicles and pedestrians in list form.

[0090] "Means for determining traffic volume" refers to a method or system that evaluates traffic volume based on the number of detected vehicles and pedestrians and compares it with a threshold value as a criterion.

[0091] "Means for changing a traffic signal" means a method or system for changing a traffic signal from red to green or green to red based on a traffic volume determination.

[0092] "Means for reacquiring and confirming the signal status after the change" refers to a method or system for checking the status of the signal after the change and whether the change was made correctly.

[0093] "Means for recording in a log" refers to a method or system for recording the results of signal changes and the reasons for them, and saving them for future reference.

[0094] The present invention is a system including a server, cameras installed at intersections, and a traffic light control device, for the purpose of efficiently controlling traffic lights at intersections.

[0095] System Overview

[0096] The server acquires video in real time from cameras installed at intersections and analyzes the video to detect passing vehicles and pedestrians. It also determines the traffic volume based on the detection results and changes the traffic lights if it determines that the traffic volume is below a predetermined threshold. After the traffic light change is made, the server checks the results and records them in a log.

[0097] Hardware and software used

[0098] Cameras: The cameras installed at intersections are high-resolution cameras such as the AXIS P1445-LE.

[0099] Server: Uses high-performance devices such as NVIDIA Jetson Xavier to process video analysis.

[0100] Deep learning framework: TENSORFLOW (registered trademark) and PyTorch are used for video analysis.

[0101] Video analysis module: Uses the OpenCV library and YOLOv5 to identify and detect vehicles and pedestrians.

[0102] Traffic signal control device: A SIGMA traffic signal controller is used to control and change traffic signals.

[0103] Communication protocol: Communication with the signal control device is performed using the MQTT protocol.

[0104] Log management software: We use Elastic Stack (ElasticSearch (registered trademark), Logstash, Kibana) to record and manage logs.

[0105] Specific example of system operation

[0106] Processing at intersections at night

[0107] 1. The server acquires real-time video from a camera installed at an intersection at night. The camera is an AXIS P1445-LE, and the server is an NVIDIA Jetson Xavier.

[0108] 2. The server temporarily stores the captured video in DRAM.

[0109] 3. The server uses a video analysis module (OpenCV and YOLOv5) to detect the absence of moving vehicles or pedestrians in the video.

[0110] 4. The server evaluates the traffic volume to be zero and determines that this is below a set threshold (e.g., less than 3 vehicles).

[0111] 5. The server determines that the current traffic light status is red and that the light should be changed to green.

[0112] 6. The server uses the MQTT protocol to send a command to the traffic light controller to change the light to green.

[0113] 7. The server checks again to see if the light has changed to green and logs the result in the Elastic Stack.

[0114] Prompt Sentence Examples

[0115] Based on the specific example, the prompt sentence for the generative AI model is created as follows:

[0116] "Please explain how you would implement a system that analyzes camera footage at intersections and efficiently controls traffic lights when traffic volume is low at night. Please also provide details about the hardware (e.g., NVIDIA Jetson Xavier, AXIS P1445-LE camera) and software (e.g., TensorFlow, Elastic Stack) you used."

[0117] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume, thereby optimizing traffic flow.

[0118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0119] Step 1:

[0120] Acquiring camera footage

[0121] The server acquires video in real time from a camera installed at an intersection. As input, it receives the camera's video stream URL. Specifically, the server periodically (for example, every second) sends an HTTP request to the camera and receives video data in stream format. As output, it obtains real-time video frames.

[0122] Step 2:

[0123] Temporary storage of video data

[0124] The server temporarily stores the acquired video data in memory. As input, it receives the video frames acquired in step 1. Specifically, the server allocates a buffer area in DRAM and stores the video data there sequentially. As output, it obtains the video frames stored in memory.

[0125] Step 3:

[0126] Video Analysis

[0127] The server uses a deep learning model (YOLOv5) to analyze the stored video. As input, it receives the video frames stored in memory in step 2. Specifically, the server inputs each frame into the deep learning model to detect the position, direction of movement, and speed of vehicles and pedestrians in that frame. As output, it obtains a list of detected objects.

[0128] Step 4:

[0129] Traffic volume determination

[0130] The server evaluates traffic volume based on the list of detected objects. It receives the object list obtained in step 3 as input. Specifically, the server analyzes the location information, movement direction, and speed data for each object to calculate the traffic volume. The output is a comparison result between the current traffic volume and the set threshold.

[0131] Step 5:

[0132] Traffic light changes

[0133] If the server determines that the traffic volume is below a predetermined threshold, it sends a command to the traffic light control device to change the signal. As input, it receives the judgment result from step 4. Specifically, the server uses the MQTT protocol to send a command to the traffic light control device to "change the red light to a green light." As output, a signal change command is sent.

[0134] Step 6:

[0135] Check and log signal status

[0136] The server sends a status request to the signal control device again to confirm whether the signal has been changed correctly. As input, it receives the result of the signal change command transmission and the current signal status. Specifically, the server sends a request to the signal control device asking "Please tell me the signal status" and checks the response from the device. It then records the change results as a log using Elastic Stack. As output, it obtains the signal status confirmation result and log record.

[0137] This allows the server to execute a series of processes and efficiently control traffic lights at intersections.

[0138] (Application example 1)

[0139] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0140] Conventional traffic light control systems at intersections have difficulty grasping road conditions in real time and efficiently controlling traffic lights. Furthermore, as autonomous vehicles become more widespread, there is a lack of coordination between traffic signals and autonomous driving systems, resulting in a lack of smooth traffic flow at intersections. This can prevent autonomous vehicles from fully optimizing their routes, potentially increasing the risk of traffic congestion and accidents.

[0141] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0142] In this invention, the server includes means for acquiring video of the intersection in real time, means for analyzing the acquired video to detect passing vehicles and pedestrians, means for determining traffic volume based on the detection results, means for changing the traffic signal when it is determined that the traffic volume is equal to or less than a predetermined threshold, means for confirming the signal status after the change, means for providing traffic signal information to the autonomous vehicle, and means for optimizing the route of the autonomous vehicle based on the traffic signal information. This makes it possible to improve the efficiency of traffic signal control at the intersection and optimize the route of the autonomous vehicle, thereby smoothing traffic flow and improving safety.

[0143] "Real-time" means processing and providing acquired information and data immediately without delay.

[0144] "Intersection footage" refers to video footage that captures the road conditions around the intersection, as well as the movements of passing vehicles and pedestrians.

[0145] "Means for acquiring video" refers to a system or method for acquiring video data in real time using photographic equipment such as a camera.

[0146] "Means for analyzing video" refers to algorithms and technologies that process acquired video data and recognize and identify specific objects such as vehicles and pedestrians.

[0147] "Means for detecting passing vehicles and pedestrians" refers to techniques and technologies that use video analysis to identify vehicles and pedestrians passing through an intersection and determine their presence and location.

[0148] "Means for determining traffic volume" means a method or device for assessing the degree of traffic congestion at an intersection based on the number and frequency of detected vehicles and pedestrians.

[0149] A "signal changing means" is a device or system that changes an intersection's signal lights from a current state to another state based on a traffic volume determination.

[0150] The "means for verifying the signal state" refers to a method or device for verifying whether the signal change has been made correctly after the change.

[0151] An "autonomous vehicle" is a vehicle that does not require a human driver and drives itself automatically.

[0152] "Means for providing traffic light information" means a system or method for communicating information about the traffic light status at an intersection to an automated vehicle.

[0153] "Means for optimizing travel route" refers to a method or system that supports an automated driving vehicle to select and travel the optimal route based on traffic signal information.

[0154] This invention describes the detailed configuration of a system that has been constructed to improve the efficiency of traffic signal control at intersections and strengthen cooperation with autonomous vehicles. This system grasps the intersection situation in real time and supports autonomous vehicles to pass through the intersection safely and efficiently.

[0155] Hardware and software used

[0156] The server acquires camera images in real time and analyzes them using image processing libraries such as OpenCV. It also uses deep learning models such as YOLOv4 to identify vehicles and pedestrians. Using these technologies, the server determines traffic volume at intersections and sends commands to traffic light control devices. It also provides traffic light information to the autonomous vehicle's control system, helping to optimize the vehicle's route.

[0157] Cameras are installed at appropriate locations at intersections and transmit images in real time to a server. The server periodically sends requests to the cameras and stores the captured image data in memory. The captured images are analyzed using a pre-trained deep learning model. The analysis results are recorded in list format, and the traffic volume at the intersection is evaluated based on this list.

[0158] Traffic volume is determined based on the number of detected vehicles and pedestrians. If the traffic volume falls below a predetermined threshold, the server sends a command to the traffic light control device to change the signal. After the signal change, the server checks whether the change was successful and records the result in a log.

[0159] Specific examples

[0160] For example, at night, there are fewer vehicles and pedestrians passing through intersections, so if the server analyzes the camera footage and determines that the traffic volume is below a threshold, it immediately changes the traffic lights. This information is also provided to autonomous vehicles, which then optimize their routes.

[0161] Prompt Sentence Examples

[0162] Please complete the missing parts of the source code below:

[0163] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0164] Step 1:

[0165] The server acquires video in real time from cameras installed at intersections. The input is the video stream from the camera, which the server periodically requests and acquires. The output is real-time video data. The video data is temporarily stored in memory.

[0166] Step 2:

[0167] The server uses image processing libraries such as OpenCV to analyze the captured video. The input is the real-time video data captured in step 1, and the output is the analyzed video data. Specifically, the server uses a pre-trained YOLOv4 model to identify vehicles and pedestrians, and to identify the location and type of each object.

[0168] Step 3:

[0169] The server detects passing vehicles and pedestrians based on the analyzed video data. The input is the analysis result from step 2, and the output is a list of detected objects. The server creates the list and records the location information and movement direction of each object.

[0170] Step 4:

[0171] The server determines the traffic volume based on the detected object list. The input is the object list created in step 3, and the output is the traffic volume value. The server compares it with the set threshold and evaluates whether the traffic volume is below the threshold.

[0172] Step 5:

[0173] If the server determines that the traffic volume is below a predetermined threshold, it sends a command to the signal control device to change the signal. The input is the traffic volume determination result from step 4, and the output is a command to the signal control device. The server checks the current signal status and switches the signal from red to green or from green to red as necessary.

[0174] Step 6:

[0175] The server checks the status of the signal after changing it. The input is the response from the signal control device, and the output is the confirmation result of whether the signal change was successful. If the change was successful, the server records the result in a log.

[0176] Step 7:

[0177] The server provides intersection traffic light information to the autonomous vehicle. The input is the current traffic light status and traffic volume judgment result, and the output is traffic light information to the autonomous vehicle. The server supports the autonomous vehicle in selecting the optimal route.

[0178] Step 8:

[0179] The autonomous vehicle optimizes its route based on traffic signal information provided by the server. The input is traffic signal information provided by the server, and the output is the optimized route. This allows the autonomous vehicle to travel safely and efficiently.

[0180] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0181] The present invention aims to efficiently control traffic signals at intersections, and in particular, it is a system that achieves more advanced traffic signal control by combining an emotion engine that recognizes the user's emotions. This system includes a server, cameras installed at intersections, emotion recognition sensors, and a traffic signal control device, and controls traffic signals according to the user's emotional state.

[0182] System Overview

[0183] The server acquires data from cameras and emotion recognition sensors installed at intersections, and analyzes the data to detect the number of vehicles and pedestrians passing by, as well as the user's emotions.The server evaluates the traffic volume and user emotions based on the detection results, and changes the traffic light if it determines that the traffic volume is below a predetermined threshold or if the user's emotions are in a specific state.After changing the traffic light, it checks the results and records them in a log.

[0184] Explanation of program processing

[0185] Acquiring camera footage and emotion data

[0186] The server collects real-time data from cameras and emotion recognition sensors installed at intersections. The server periodically sends requests to the cameras and sensors to receive video and emotion data. The received data is temporarily stored in memory.

[0187] Video and Emotion Analysis

[0188] The server uses a video analysis module and emotion engine to analyze the captured video data and emotion data. The video analysis module utilizes deep learning models to identify vehicles and pedestrians in the video. The emotion engine identifies emotions from the user's facial expressions and behavior. The location, direction of movement, speed, and user emotion information of each detected vehicle or pedestrian are recorded in a list.

[0189] Traffic and emotion assessment

[0190] The server evaluates the current traffic volume and the user's emotional state based on the detection result list. The evaluation criteria are set as thresholds, and it determines whether the traffic volume is below the threshold and whether the user's emotional state is in a certain state (e.g., impatience, anger).

[0191] Traffic light changes

[0192] The server changes the traffic light when it determines that the traffic volume is below a predetermined threshold or when the user's emotions are in a specific state. It checks the current state of the traffic light and sends a command to the traffic light control device to change the light from red to green or from green to red as necessary.

[0193] Check and log signal status

[0194] After the signal change, the server sends a status request to the signal controller again to confirm whether the signal change was successful. If the change is confirmed, the result is recorded in a log file. The log includes the time of the signal change, the type of change (from red to green, or from green to red), and the reason for the change (traffic volume evaluation results and user sentiment).

[0195] Specific examples

[0196] Daytime intersection

[0197] 1. The server collects real-time data from cameras and emotion recognition sensors installed at intersections during the day.

[0198] 2. The server uses a video analysis module to detect moving vehicles and pedestrians in the video, and simultaneously detects the user's emotions using an emotion engine.

[0199] 3. The server evaluates whether the traffic volume is below a set threshold or the detected user emotion is impatience.

[0200] 4. The server determines that the current traffic light state is red and that the light should be changed to green.

[0201] 5. The server sends a command to the traffic light controller to change the light to green.

[0202] 6. The server verifies that the traffic light has changed to green and logs the result.

[0203] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume and user emotions, thereby optimizing traffic flow.

[0204] The processing flow will be explained below.

[0205] Step 1:

[0206] The server collects real-time data from cameras and emotion recognition sensors installed at intersections. The server periodically sends requests to the cameras and sensors to receive video and emotion data. The received data is temporarily stored in memory.

[0207] Step 2:

[0208] The server uses a video analysis module to analyze the acquired video data. The server inputs the video data into the video analysis module and uses a deep learning model to identify vehicles and pedestrians in the video. Information such as the location, direction of movement, and speed of each identified object is extracted and compiled into a list.

[0209] Step 3:

[0210] The server uses an emotion engine to analyze the acquired emotion data. The emotion engine identifies the user's facial expressions and behavior patterns and estimates their emotional state. The detected emotion information is recorded in a list.

[0211] Step 4:

[0212] The server evaluates the current traffic volume and the user's emotional state based on the video analysis and emotion analysis results. The server compares the traffic volume with a set threshold and determines whether the traffic volume is below the threshold or whether the user's emotional state is in a specific state (e.g., impatience, anger).

[0213] Step 5:

[0214] The server obtains the current signal status from the signal controller. The server sends a status request to the signal controller to check whether the signal is currently red or green.

[0215] Step 6:

[0216] The server determines whether the traffic light needs to be changed based on the traffic volume evaluation result and the user's emotional state. If the traffic volume is below a threshold and the user's emotional state is impatient, the server determines that the traffic light needs to be changed to green.

[0217] Step 7:

[0218] The server sends a signal switching command to the signal control device. The server sends a command to the signal control device to change the signal to green, and verifies that the command was sent successfully.

[0219] Step 8:

[0220] The server checks the changed signal status and sends a status request to the signal controller again to check whether the signal has been changed to green correctly.

[0221] Step 9:

[0222] The server records the result of the traffic light change in a log. If a change is confirmed, the result is written to a log file. The log records the time of the traffic light change, the type of change (from red to green, from green to red), and the reason for the change (traffic volume evaluation result and user sentiment).

[0223] Step 10:

[0224] The server starts again after a certain time by acquiring camera footage and emotion data. A certain timer is set and this process is repeated at regular intervals.

[0225] Through the above steps, the server can automatically control the traffic lights at the intersection and achieve efficient traffic light changes according to the traffic volume and the user's emotions.

[0226] Example 2

[0227] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0228] Conventional traffic signal control systems often change signals based on a simple evaluation of traffic volume. This makes it difficult to respond to the emotional state of people at intersections or real-time situations, making it difficult to achieve optimal signal control. The present invention aims to solve this problem and realize flexible signal control that takes into account traffic volume and the emotional state of users.

[0229] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0230] In this invention, the server includes means for acquiring intersection data in real time, means for analyzing the acquired data to detect vehicles and pedestrians, means for analyzing and identifying the user's emotions, means for determining traffic volume and emotional state based on the detection results and the emotion analysis results, means for changing the traffic signal when it is determined that traffic volume is below a predetermined threshold or that the user's emotion is in a specific state, and means for confirming the signal state after the change. This enables optimal traffic signal control that takes into account not only traffic volume but also the user's emotional state.

[0231] "Means for acquiring intersection data in real time" refers to devices or systems that have the function of collecting data in real time from sensors or cameras installed at intersections.

[0232] "Means for detecting vehicles and pedestrians by analyzing acquired data" refers to devices or systems that use data analysis technology to identify vehicles and pedestrians from acquired data and identify their positions and directions of movement.

[0233] The "means for analyzing and identifying a user's emotions" refers to technology and devices that analyze the user's facial expressions and behavior to identify their emotional state.

[0234] "Means for determining traffic volume and emotional state based on detection results and emotion analysis results" refers to technology and devices that evaluate the current traffic volume at an intersection and the user's emotional state based on the detection results of vehicles and pedestrians and the user's emotion analysis results.

[0235] "Means for changing traffic signals when it is determined that traffic volume is below a predetermined threshold or the user's emotions are in a specific state" refers to technology and devices for appropriately changing traffic signals when traffic volume is below a predetermined threshold or when the user's emotions are in a specific state.

[0236] "Means for confirming the signal status after the change" refers to the technology and devices for reconfirming the status of the signal after it has been changed.

[0237] The present invention aims to efficiently control traffic signals at intersections, and is a system that achieves advanced traffic signal control by combining an emotion engine that recognizes the user's emotions. This system consists of the following components:

[0238] First, cameras and emotion recognition sensors will be installed at intersections. These devices will monitor the situation at the intersection in real time and send the data to a server. The server will then analyze the data and use it to control traffic lights.

[0239] Data acquisition from cameras and emotion recognition sensors

[0240] The server acquires data in real time from cameras and emotion recognition sensors installed at intersections. Specifically, the server periodically sends requests to the cameras and sensors to receive video data and emotion data. The received data is temporarily stored in memory. The cameras and emotion recognition sensors used here could be ordinary surveillance cameras or sensors that detect facial expressions and tone of voice.

[0241] Video and Emotion Analysis

[0242] The server uses a video analysis module and emotion engine to analyze the acquired video data and emotion data. The video analysis module uses a deep learning model such as YOLOv5. This model is used to identify vehicles and pedestrians in the video. The emotion engine uses the Emotion API from Microsoft (registered trademark) Azure (registered trademark) and identifies emotions from the user's facial expressions and behavior. The analysis results are recorded in a list.

[0243] Traffic and emotion assessment

[0244] The server evaluates the current traffic volume and the user's emotional state based on the detection result list. The evaluation criteria are set as thresholds, and it determines whether the traffic volume is below the threshold and whether the user's emotional state is in a certain state (e.g., impatience, anger).

[0245] Traffic light changes

[0246] The server changes the traffic light when it determines that the traffic volume is below a predetermined threshold or when the user's emotions are in a specific state. It sends a command to the traffic light control device to switch the traffic light from red to green or from green to red. A general traffic light control device can be used as the traffic light control device.

[0247] Check and log signal status

[0248] After the signal change, the server sends a status request to the signal controller to check whether the signal change was successful. If the change is successful, the server records the result in a log file. The log includes the time of the signal change, the type of change (from red to green, or from green to red), and the reason for the change (traffic volume evaluation results and user sentiment).

[0249] Specific examples

[0250] For example, consider an intersection during the daytime. The server acquires real-time data from cameras and emotion recognition sensors installed at the intersection during the daytime. It uses a video analysis module to detect moving vehicles and pedestrians in the video, while simultaneously detecting the user's emotions using an emotion engine. If the server determines that the traffic volume falls below a set threshold or that the detected user emotion is impatience, it sends a command to the traffic light control device to change the light to green. It then confirms that the light has changed to green and records the result in a log.

[0251] Example prompts for generative AI models

[0252] "Your task is to acquire data from cameras and emotion recognition sensors installed at intersections during the day, and design an algorithm that will optimally change traffic signals based on traffic volume and user emotions."

[0253] "Draw a flowchart of a system that analyzes the number of vehicles and pedestrians at an intersection and their emotions in real time to achieve efficient traffic light control."

[0254] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume and user emotions, thereby optimizing traffic flow.

[0255] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0256] Program processing flow

[0257] Step 1: Acquiring camera footage and emotion data

[0258] Input: Real-time data requests from cameras and emotion recognition sensors

[0259] process:

[0260] The server sends an HTTP GET request to the camera and emotion recognition sensor every 5 seconds to obtain the latest video data and emotion data. The camera sends images in JPEG format, and the emotion recognition sensor sends emotion data in JSON format to the server. These data are temporarily stored in memory.

[0261] Output: JPEG video data and JSON format emotion data

[0262] Step 2: Video and emotion analysis

[0263] Input: JPEG video data and JSON emotion data obtained in step 1

[0264] process:

[0265] The server inputs the video data into the YOLOv5 model for object detection. This model identifies vehicles and pedestrians in the video and obtains their coordinate data (x, y, w, h). At the same time, emotion data is input into an emotion engine (e.g., Microsoft Azure Emotion API) to extract emotion categories such as "joy," "anger," and "sadness." The location, direction of movement, and speed of each detected vehicle or pedestrian, as well as the user's emotion information, are recorded in a list.

[0266] Output: A list of analyzed vehicle and pedestrian locations and emotion categories

[0267] Step 3: Assess traffic and sentiment

[0268] Input: Analysis result list created in step 2

[0269] process:

[0270] The server counts the traffic volume within a certain period of time based on the vehicle and pedestrian data in the list. It also analyzes the user's emotional data and evaluates whether a specific emotional state (e.g., impatience, anger) is detected. If the traffic volume falls below a set threshold or the user's emotional state is in a specific state, the server proceeds to the next step. Specifically, the server aggregates the traffic volume every minute and compares it with a threshold (e.g., 10 vehicles or less) and the emotional state.

[0271] Output: Traffic volume and emotion evaluation results (number of passing vehicles and pedestrians, emotional state)

[0272] Step 4: Modifying the Signal

[0273] Input: Traffic volume and emotion evaluation results obtained in Step 3

[0274] process:

[0275] The server changes the traffic light when it determines that the traffic volume is below a certain threshold or that the user's emotions are in a specific state. The server sends a command to the traffic light controller to change the light from red to green or from green to red using a POST request via the REST API. The traffic light controller receives this command and changes the light.

[0276] Output: Changed signal indication

[0277] Step 5: Check and log the signal status

[0278] Input: Signal change command sent in step 4 and response from the signal controller

[0279] process:

[0280] After the signal has changed, the server again sends a GET request to the signal control device to check its status. If the signal has changed correctly, the result is recorded in a log file. The log includes the time of the signal change, the type of change (red to green, green to red), and the reason for the change (traffic volume evaluation results and user emotion). Specifically, the server sends a reconfirmation request to the signal control device after 5 seconds, recording "Change time: 14:35, Change type: red to green, Reason: Frequent occurrence of pedestrian impatience."

[0281] Output: Recorded log data

[0282] (Application example 2)

[0283] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0284] Conventional traffic signal control systems control signals based solely on traffic volume, without taking into account the emotional state of pedestrians and passengers. As a result, they are unable to respond appropriately in emergencies or when users are feeling anxious or stressed, posing challenges to optimizing traffic flow and improving safety.

[0285] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring video of the intersection in real time, means for analyzing the acquired video to detect passing vehicles and pedestrians, emotion recognition means for recognizing the emotional state of the user, means for changing the traffic light when it is determined that the traffic volume and the emotional state of the user are below a predetermined threshold, means for confirming the traffic light status after the change, and means for displaying the traffic light status after the change, including the reason for the change. This enables flexible traffic light changes according to the emotional state of the user, thereby improving traffic safety and efficiency at intersections.

[0286] "Real-time" means that images of the intersection are captured immediately on the spot and processed without delay.

[0287] "Video analysis" is the process of using acquired video data to detect and identify specific information (such as passing vehicles or pedestrians).

[0288] "Traffic volume" refers to the number or volume of vehicles and pedestrians passing through a particular traffic point.

[0289] "User's emotional state" is information that represents the emotions that the user is feeling (for example, joy, anger, impatience, sadness, etc.).

[0290] "Emotion recognition means" refers to a technology or device for determining emotions from the user's facial expressions, actions, etc., and acquiring that information.

[0291] The "means for changing a traffic light" refers to a means for sending a command to a traffic light control device to change the color of the traffic light (such as from red to green or from green to red).

[0292] "Changed signal state" refers to the state of the signal after it has changed (e.g., the signal has turned green or red).

[0293] The "means for displaying the changed signal status including the reason for the change" is a means for showing on a display device the reason why the signal has been changed and the new status of the signal.

[0294] "Log" refers to data that maintains records of system operations and results.

[0295] The system of the present invention is a real-time traffic light control system for enabling autonomous vehicles to pass through intersections efficiently and safely. The system includes a server, cameras installed at intersections, emotion recognition sensors, a traffic light control device, and smart glasses installed in the vehicle.

[0296] The server collects real-time data from cameras and emotion recognition sensors installed at intersections. The cameras use a video analysis module to detect moving vehicles and pedestrians in the video. The emotion recognition sensors analyze the user's facial expressions and movements to obtain emotional data.

[0297] The server performs calculations to determine traffic volume based on the acquired data. It uses a video analysis module and emotion engine with deep learning models to detect and record the number, location, direction, and speed of passing vehicles and pedestrians. It also analyzes the user's emotional state, and if it recognizes certain emotions such as impatience or anger, it makes a decision to respond accordingly.

[0298] If the server determines that the traffic volume and the user's emotional state are below a predetermined threshold, it sends a signal change command to the signal controller. The signal controller changes the signal in accordance with the command, including changing the signal from red to green or vice versa. The changed signal status and the reason for the change are displayed on the smart glasses in real time.

[0299] The changed signal status is recorded in a log, and details such as the reason for the change, the timing, and the type of signal are saved, optimizing traffic flow and improving safety.

[0300] Hardware and software used

[0301] 1. Camera:

[0302] It captures real-time video and uses it in the video analysis module to detect vehicles and pedestrians.

[0303] 2. Emotion Recognition Sensor:

[0304] It recognizes the user's emotional state and transmits that data to a server.

[0305] 3. Signal Control Device:

[0306] The signal is changed based on instructions from the server.

[0307] 4. Smart Glasses:

[0308] The status and reasons for signal changes are displayed in real time so that drivers and passengers can check them.

[0309] 5. Server:

[0310] A video analysis module and emotion engine are used to process the data and send commands to the traffic light controller.

[0311] Specific examples

[0312] For example, if a driver feels extremely anxious when approaching an intersection, the system will detect this emotion through emotion recognition sensors and promptly change the intersection's traffic light from red to green, allowing the vehicle to pass through the intersection smoothly, thereby improving traffic safety and traffic flow.

[0313] Prompt Sentence Examples

[0314] "If the user is impatient, please show how to instruct the intersection signal system to change the signal."

[0315] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0316] Step 1:

[0317] The server receives real-time data from cameras and emotion recognition sensors installed at intersections. The input is the camera footage and data from the emotion recognition sensors, and the output is that these data are temporarily stored in memory. Specifically, the server periodically sends requests to the cameras and sensors to receive video data and emotion data.

[0318] Step 2:

[0319] The server analyzes the acquired video data and emotion data. The input is the video data and emotion data acquired in step 1, and the output is information about detected vehicles and pedestrians, as well as the user's emotion data. The server uses a video analysis module that utilizes a deep learning model to identify vehicles and pedestrians in the video, and an emotion engine to identify emotions from the user's facial expressions and behavior. Specifically, the video analysis module calculates the position, direction of movement, and speed of vehicles and pedestrians, and the emotion engine classifies the user's emotional state.

[0320] Step 3:

[0321] The server evaluates the current traffic volume and the user's emotional state based on the detection result list. The input is the detection result from step 2, and the output is the evaluation results of the traffic volume and emotional state. Specifically, the server compares the traffic volume and the user's emotional state with a predetermined threshold and determines whether the traffic volume is below the threshold or whether the user's emotional state is in a specific state (e.g., impatience, anger).

[0322] Step 4:

[0323] If the server determines that the traffic volume is below a predetermined threshold or that the user's emotions are in a specific state, it sends a signal change command to the traffic light controller. The input is the evaluation result of step 3, and the output is the command sent to the traffic light controller. Specifically, the server checks the current traffic light status and sends an instruction to change the light from red to green, or vice versa, as necessary.

[0324] Step 5:

[0325] The server checks whether the signal change was successful. The input is the response from the signal controller, and the output is the result of the signal change. Specifically, the server sends a status request to the signal controller again to check whether the signal has been changed to the correct state.

[0326] Step 6:

[0327] The server records the changed signal status and the reason for the change in a log and displays it on the smart glasses in real time. The input is the signal change result in step 5 and the evaluation result in step 3, and the output is a log file and display information on the smart glasses. Specifically, the log records the time of the signal change, the type of change, and the reason for the change, and the smart glasses display the current signal status and the reason for the change.

[0328] The above are the processing steps of the system that realizes the application example.

[0329] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0330] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0331] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0332] [Second embodiment]

[0333] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0334] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0335] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0336] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0337] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0338] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0339] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0340] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0341] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0342] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0343] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0344] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0345] The present invention aims to efficiently control traffic lights at intersections. The system includes a server, cameras installed at intersections, and a traffic light control device.

[0346] System Overview

[0347] The server acquires video in real time from cameras installed at intersections and analyzes the video to detect passing vehicles and pedestrians. It also determines the traffic volume based on the detection results and changes the traffic lights if it determines that the traffic volume is below a predetermined threshold. After the traffic light change is made, the server checks the results and records them in a log.

[0348] Explanation of program processing

[0349] Acquiring camera footage

[0350] The server acquires video images in real time from cameras installed at intersections. The server periodically sends requests to the cameras according to a schedule and receives video data. The received video data is temporarily stored in memory.

[0351] Video Analysis

[0352] The server uses a video analysis module to analyze the captured video. The video analysis module utilizes deep learning models to identify and detect vehicles and pedestrians in the video. Information about each detected object, such as its location, direction of movement, and speed, is recorded in a list.

[0353] Traffic volume determination

[0354] The server evaluates the current traffic volume based on the detected object list. The evaluation criterion is set as a threshold, and it determines whether the traffic volume is below this threshold. For example, if there are no vehicles or pedestrians passing by, it determines that the traffic volume is below the threshold.

[0355] Traffic light changes

[0356] The server changes the traffic light when it determines that the traffic volume is below a predetermined threshold. It checks the current status of the traffic light and sends a command to the traffic light controller to switch the traffic light from red to green or from green to red as necessary.

[0357] Check and log signal status

[0358] After the signal change, the server sends a status request to the signal controller again to check whether the signal change was successful. If the change is successful, the result is recorded in a log file. The log includes the time of the signal change, the type of change (from red to green, or from green to red), and the reason for the change (traffic volume evaluation result).

[0359] Specific examples

[0360] Nighttime intersection

[0361] 1. The server acquires real-time video from a camera installed at an intersection at night.

[0362] 2. The server uses a video analysis module to detect the absence of moving vehicles or pedestrians in the video.

[0363] 3. The server evaluates the traffic volume to be zero and determines that this is below a set threshold (e.g., less than 3 vehicles).

[0364] 4. The server determines that the current traffic light state is red and that the light should be changed to green.

[0365] 5. The server sends a command to the traffic light controller to change the light to green.

[0366] 6. The server verifies that the traffic light has changed to green and logs the result.

[0367] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume, thereby optimizing traffic flow.

[0368] The processing flow will be explained below.

[0369] Step 1:

[0370] The server acquires video in real time from cameras installed at intersections. The server periodically sends requests to the cameras to receive video data. The received video data is temporarily stored in memory.

[0371] Step 2:

[0372] The server uses a video analysis module to analyze the acquired video data. The server inputs the video data into the video analysis module, which uses a deep learning model to identify vehicles and pedestrians in the video.

[0373] Step 3:

[0374] The server extracts information about each identified object, such as its location, direction of movement, and speed, and compiles this information into a list that is saved as the analysis results.

[0375] Step 4:

[0376] The server analyzes the detection result list and evaluates the current traffic volume. The server compares it with a set threshold and determines whether the traffic volume is below the threshold. For example, if there are less than three vehicles, it determines that the traffic volume is below the threshold.

[0377] Step 5:

[0378] The server obtains the current signal status from the signal controller. The server sends a status request to the signal controller to check whether the signal is currently red or green.

[0379] Step 6:

[0380] The server determines whether the traffic light needs to be changed based on the traffic volume evaluation result and the traffic light status. If the traffic volume is low and the traffic light is red, the server determines that the traffic light needs to be changed to green.

[0381] Step 7:

[0382] The server sends a signal switching command to the signal control device. The server sends a command to the signal control device to change the signal to green, and verifies that the command was sent successfully.

[0383] Step 8:

[0384] The server checks the changed signal status and sends a status request to the signal controller again to check whether the signal has been changed to green correctly.

[0385] Step 9:

[0386] The server records the result of the traffic light change in a log. If a change is confirmed, the result is written to a log file. The log records the time of the traffic light change, the type of change (red to green, green to red), and the reason for the change (traffic volume evaluation result).

[0387] Step 10:

[0388] The server starts again by acquiring camera footage after a certain time, setting a timer and repeating this process at regular intervals.

[0389] By following the above steps, the server can automatically control the traffic lights at the intersection and achieve efficient traffic light changes according to the traffic volume.

[0390] Example 1

[0391] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0392] Traffic light control at intersections is often performed at fixed timings and is sometimes unable to respond to fluctuations in traffic volume. As a result, traffic congestion and unnecessary waits at traffic lights occur, posing the problem of inefficient traffic flow. In addition, due to a lack of flexible control of traffic lights at night and during off-peak hours, it is not possible to change traffic lights according to traffic volume.

[0393] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0394] In this invention, the server includes means for acquiring images in real time from cameras at intersections, means for temporarily storing the acquired images in memory, means for analyzing the stored images to detect passing vehicles and pedestrians, means for recording the positions, movement directions, and speeds of the detected vehicles and pedestrians in a list, means for determining traffic volume based on the detection results, means for changing the traffic signal if it is determined that the traffic volume is below a predetermined threshold, means for reacquiring and confirming the signal status after the change, and means for recording the change results in a log. This enables flexible signal changes according to traffic volume, thereby optimizing traffic flow.

[0395] An "intersection camera" is a camera device that is installed at an intersection and captures images of the surrounding area in real time.

[0396] "Real-time" means that data or information is processed at the same time it is acquired.

[0397] A "server" is a computer system that processes, stores, analyzes, etc., video data acquired from cameras at intersections.

[0398] "Means for acquiring video" refers to a method or system for receiving video data from an intersection camera in real time.

[0399] "Means for temporarily storing in memory" refers to a storage device for temporarily storing received video data and a method for operating the storage device.

[0400] "Means for analyzing video" refers to methods and systems that use computer vision and deep learning technology to analyze acquired video data and extract important information.

[0401] "Means for detecting vehicles and pedestrians" refers to methods and systems that use video analysis to identify moving objects such as vehicles and pedestrians and determine their locations and attributes.

[0402] "Means for recording in a list" refers to a method or system for recording and managing information about detected vehicles and pedestrians in list form.

[0403] "Means for determining traffic volume" refers to a method or system that evaluates traffic volume based on the number of detected vehicles and pedestrians and compares it with a threshold value as a criterion.

[0404] "Means for changing a traffic signal" means a method or system for changing a traffic signal from red to green or green to red based on a traffic volume determination.

[0405] "Means for reacquiring and confirming the signal status after the change" refers to a method or system for checking the status of the signal after the change and whether the change was made correctly.

[0406] "Means for recording in a log" refers to a method or system for recording the results of signal changes and the reasons for them, and saving them for future reference.

[0407] The present invention is a system including a server, cameras installed at intersections, and a traffic light control device, for the purpose of efficiently controlling traffic lights at intersections.

[0408] System Overview

[0409] The server acquires video in real time from cameras installed at intersections and analyzes the video to detect passing vehicles and pedestrians. It also determines the traffic volume based on the detection results and changes the traffic lights if it determines that the traffic volume is below a predetermined threshold. After the traffic light change is made, the server checks the results and records them in a log.

[0410] Hardware and software used

[0411] Cameras: The cameras installed at intersections are high-resolution cameras such as the AXIS P1445-LE.

[0412] Server: Uses high-performance devices such as NVIDIA Jetson Xavier to process video analysis.

[0413] Deep learning framework: TensorFlow and PyTorch are used for video analysis.

[0414] Video analysis module: Uses the OpenCV library and YOLOv5 to identify and detect vehicles and pedestrians.

[0415] Traffic signal control device: A SIGMA traffic signal controller is used to control and change traffic signals.

[0416] Communication protocol: Communication with the signal control device is performed using the MQTT protocol.

[0417] Log management software: Use the Elastic Stack (Elasticsearch, Logstash, Kibana) to record and manage logs.

[0418] Specific example of system operation

[0419] Processing at intersections at night

[0420] 1. The server acquires real-time video from a camera installed at an intersection at night. The camera is an AXIS P1445-LE, and the server is an NVIDIA Jetson Xavier.

[0421] 2. The server temporarily stores the captured video in DRAM.

[0422] 3. The server uses a video analysis module (OpenCV and YOLOv5) to detect the absence of moving vehicles or pedestrians in the video.

[0423] 4. The server evaluates the traffic volume to be zero and determines that this is below a set threshold (e.g., less than 3 vehicles).

[0424] 5. The server determines that the current traffic light status is red and that the light should be changed to green.

[0425] 6. The server uses the MQTT protocol to send a command to the traffic light controller to change the light to green.

[0426] 7. The server checks again to see if the light has changed to green and logs the result in the Elastic Stack.

[0427] Prompt Sentence Examples

[0428] Based on the specific example, the prompt sentence for the generative AI model is created as follows:

[0429] "Please explain how you would implement a system that analyzes camera footage at intersections and efficiently controls traffic lights when traffic volume is low at night. Please also provide details about the hardware (e.g., NVIDIA Jetson Xavier, AXIS P1445-LE camera) and software (e.g., TensorFlow, Elastic Stack) you used."

[0430] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume, thereby optimizing traffic flow.

[0431] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0432] Step 1:

[0433] Acquiring camera footage

[0434] The server acquires video in real time from a camera installed at an intersection. As input, it receives the camera's video stream URL. Specifically, the server periodically (for example, every second) sends an HTTP request to the camera and receives video data in stream format. As output, it obtains real-time video frames.

[0435] Step 2:

[0436] Temporary storage of video data

[0437] The server temporarily stores the acquired video data in memory. As input, it receives the video frames acquired in step 1. Specifically, the server allocates a buffer area in DRAM and stores the video data there sequentially. As output, it obtains the video frames stored in memory.

[0438] Step 3:

[0439] Video Analysis

[0440] The server uses a deep learning model (YOLOv5) to analyze the stored video. As input, it receives the video frames stored in memory in step 2. Specifically, the server inputs each frame into the deep learning model to detect the position, direction of movement, and speed of vehicles and pedestrians in that frame. As output, it obtains a list of detected objects.

[0441] Step 4:

[0442] Traffic volume determination

[0443] The server evaluates traffic volume based on the list of detected objects. It receives the object list obtained in step 3 as input. Specifically, the server analyzes the location information, movement direction, and speed data for each object to calculate the traffic volume. The output is a comparison result between the current traffic volume and the set threshold.

[0444] Step 5:

[0445] Traffic light changes

[0446] If the server determines that the traffic volume is below a predetermined threshold, it sends a command to the traffic light control device to change the signal. As input, it receives the judgment result from step 4. Specifically, the server uses the MQTT protocol to send a command to the traffic light control device to "change the red light to a green light." As output, a signal change command is sent.

[0447] Step 6:

[0448] Check and log signal status

[0449] The server sends a status request to the signal control device again to confirm whether the signal has been changed correctly. As input, it receives the result of the signal change command transmission and the current signal status. Specifically, the server sends a request to the signal control device asking "Please tell me the signal status" and checks the response from the device. It then records the change results as a log using Elastic Stack. As output, it obtains the signal status confirmation result and log record.

[0450] This allows the server to execute a series of processes and efficiently control traffic lights at intersections.

[0451] (Application example 1)

[0452] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0453] Conventional traffic light control systems at intersections have difficulty grasping road conditions in real time and efficiently controlling traffic lights. Furthermore, as autonomous vehicles become more widespread, there is a lack of coordination between traffic signals and autonomous driving systems, resulting in a lack of smooth traffic flow at intersections. This can prevent autonomous vehicles from fully optimizing their routes, potentially increasing the risk of traffic congestion and accidents.

[0454] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0455] In this invention, the server includes means for acquiring video of the intersection in real time, means for analyzing the acquired video to detect passing vehicles and pedestrians, means for determining traffic volume based on the detection results, means for changing the traffic signal when it is determined that the traffic volume is equal to or less than a predetermined threshold, means for confirming the signal status after the change, means for providing traffic signal information to the autonomous vehicle, and means for optimizing the route of the autonomous vehicle based on the traffic signal information. This makes it possible to improve the efficiency of traffic signal control at the intersection and optimize the route of the autonomous vehicle, thereby smoothing traffic flow and improving safety.

[0456] "Real-time" means processing and providing acquired information and data immediately without delay.

[0457] "Intersection footage" refers to video footage that captures the road conditions around the intersection, as well as the movements of passing vehicles and pedestrians.

[0458] "Means for acquiring video" refers to a system or method for acquiring video data in real time using photographic equipment such as a camera.

[0459] "Means for analyzing video" refers to algorithms and technologies that process acquired video data and recognize and identify specific objects such as vehicles and pedestrians.

[0460] "Means for detecting passing vehicles and pedestrians" refers to techniques and technologies that use video analysis to identify vehicles and pedestrians passing through an intersection and determine their presence and location.

[0461] "Means for determining traffic volume" means a method or device for assessing the degree of traffic congestion at an intersection based on the number and frequency of detected vehicles and pedestrians.

[0462] A "signal changing means" is a device or system that changes an intersection's signal lights from a current state to another state based on a traffic volume determination.

[0463] The "means for verifying the signal state" refers to a method or device for verifying whether the signal change has been made correctly after the change.

[0464] An "autonomous vehicle" is a vehicle that does not require a human driver and drives itself automatically.

[0465] "Means for providing traffic light information" means a system or method for communicating information about the traffic light status at an intersection to an automated vehicle.

[0466] "Means for optimizing travel route" refers to a method or system that supports an automated driving vehicle to select and travel the optimal route based on traffic signal information.

[0467] This invention describes the detailed configuration of a system that has been constructed to improve the efficiency of traffic signal control at intersections and strengthen cooperation with autonomous vehicles. This system grasps the intersection situation in real time and supports autonomous vehicles to pass through the intersection safely and efficiently.

[0468] Hardware and software used

[0469] The server acquires camera images in real time and analyzes them using image processing libraries such as OpenCV. It also uses deep learning models such as YOLOv4 to identify vehicles and pedestrians. Using these technologies, the server determines traffic volume at intersections and sends commands to traffic light control devices. It also provides traffic light information to the autonomous vehicle's control system, helping to optimize the vehicle's route.

[0470] Cameras are installed at appropriate locations at intersections and transmit images in real time to a server. The server periodically sends requests to the cameras and stores the captured image data in memory. The captured images are analyzed using a pre-trained deep learning model. The analysis results are recorded in list format, and the traffic volume at the intersection is evaluated based on this list.

[0471] Traffic volume is determined based on the number of detected vehicles and pedestrians. If the traffic volume falls below a predetermined threshold, the server sends a command to the traffic light control device to change the signal. After the signal change, the server checks whether the change was successful and records the result in a log.

[0472] Specific examples

[0473] For example, at night, there are fewer vehicles and pedestrians passing through intersections, so if the server analyzes the camera footage and determines that the traffic volume is below a threshold, it immediately changes the traffic lights. This information is also provided to autonomous vehicles, which then optimize their routes.

[0474] Prompt Sentence Examples

[0475] Please complete the missing parts of the source code below:

[0476] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0477] Step 1:

[0478] The server acquires video in real time from cameras installed at intersections. The input is the video stream from the camera, which the server periodically requests and acquires. The output is real-time video data. The video data is temporarily stored in memory.

[0479] Step 2:

[0480] The server uses image processing libraries such as OpenCV to analyze the captured video. The input is the real-time video data captured in step 1, and the output is the analyzed video data. Specifically, the server uses a pre-trained YOLOv4 model to identify vehicles and pedestrians, and to identify the location and type of each object.

[0481] Step 3:

[0482] The server detects passing vehicles and pedestrians based on the analyzed video data. The input is the analysis result from step 2, and the output is a list of detected objects. The server creates the list and records the location information and movement direction of each object.

[0483] Step 4:

[0484] The server determines the traffic volume based on the detected object list. The input is the object list created in step 3, and the output is the traffic volume value. The server compares it with the set threshold and evaluates whether the traffic volume is below the threshold.

[0485] Step 5:

[0486] If the server determines that the traffic volume is below a predetermined threshold, it sends a command to the signal control device to change the signal. The input is the traffic volume determination result from step 4, and the output is a command to the signal control device. The server checks the current signal status and switches the signal from red to green or from green to red as necessary.

[0487] Step 6:

[0488] The server checks the status of the signal after changing it. The input is the response from the signal control device, and the output is the confirmation result of whether the signal change was successful. If the change was successful, the server records the result in a log.

[0489] Step 7:

[0490] The server provides intersection traffic light information to the autonomous vehicle. The input is the current traffic light status and traffic volume judgment result, and the output is traffic light information to the autonomous vehicle. The server supports the autonomous vehicle in selecting the optimal route.

[0491] Step 8:

[0492] The autonomous vehicle optimizes its route based on traffic signal information provided by the server. The input is traffic signal information provided by the server, and the output is the optimized route. This allows the autonomous vehicle to travel safely and efficiently.

[0493] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0494] The present invention aims to efficiently control traffic signals at intersections, and in particular, it is a system that achieves more advanced traffic signal control by combining an emotion engine that recognizes the user's emotions. This system includes a server, cameras installed at intersections, emotion recognition sensors, and a traffic signal control device, and controls traffic signals according to the user's emotional state.

[0495] System Overview

[0496] The server acquires data from cameras and emotion recognition sensors installed at intersections, and analyzes the data to detect the number of vehicles and pedestrians passing by, as well as the user's emotions.The server evaluates the traffic volume and user emotions based on the detection results, and changes the traffic light if it determines that the traffic volume is below a predetermined threshold or if the user's emotions are in a specific state.After changing the traffic light, it checks the results and records them in a log.

[0497] Explanation of program processing

[0498] Acquiring camera footage and emotion data

[0499] The server collects real-time data from cameras and emotion recognition sensors installed at intersections. The server periodically sends requests to the cameras and sensors to receive video and emotion data. The received data is temporarily stored in memory.

[0500] Video and Emotion Analysis

[0501] The server uses a video analysis module and emotion engine to analyze the captured video data and emotion data. The video analysis module utilizes deep learning models to identify vehicles and pedestrians in the video. The emotion engine identifies emotions from the user's facial expressions and behavior. The location, direction of movement, speed, and user emotion information of each detected vehicle or pedestrian are recorded in a list.

[0502] Traffic and emotion assessment

[0503] The server evaluates the current traffic volume and the user's emotional state based on the detection result list. The evaluation criteria are set as thresholds, and it determines whether the traffic volume is below the threshold and whether the user's emotional state is in a certain state (e.g., impatience, anger).

[0504] Traffic light changes

[0505] The server changes the traffic light when it determines that the traffic volume is below a predetermined threshold or when the user's emotions are in a specific state. It checks the current state of the traffic light and sends a command to the traffic light control device to change the light from red to green or from green to red as necessary.

[0506] Check and log signal status

[0507] After the signal change, the server sends a status request to the signal controller again to confirm whether the signal change was successful. If the change is confirmed, the result is recorded in a log file. The log includes the time of the signal change, the type of change (from red to green, or from green to red), and the reason for the change (traffic volume evaluation results and user sentiment).

[0508] Specific examples

[0509] Daytime intersection

[0510] 1. The server collects real-time data from cameras and emotion recognition sensors installed at intersections during the day.

[0511] 2. The server uses a video analysis module to detect moving vehicles and pedestrians in the video, and simultaneously detects the user's emotions using an emotion engine.

[0512] 3. The server evaluates whether the traffic volume is below a set threshold or the detected user emotion is impatience.

[0513] 4. The server determines that the current traffic light state is red and that the light should be changed to green.

[0514] 5. The server sends a command to the traffic light controller to change the light to green.

[0515] 6. The server verifies that the traffic light has changed to green and logs the result.

[0516] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume and user emotions, thereby optimizing traffic flow.

[0517] The processing flow will be explained below.

[0518] Step 1:

[0519] The server collects real-time data from cameras and emotion recognition sensors installed at intersections. The server periodically sends requests to the cameras and sensors to receive video and emotion data. The received data is temporarily stored in memory.

[0520] Step 2:

[0521] The server uses a video analysis module to analyze the acquired video data. The server inputs the video data into the video analysis module and uses a deep learning model to identify vehicles and pedestrians in the video. Information such as the location, direction of movement, and speed of each identified object is extracted and compiled into a list.

[0522] Step 3:

[0523] The server uses an emotion engine to analyze the acquired emotion data. The emotion engine identifies the user's facial expressions and behavior patterns and estimates their emotional state. The detected emotion information is recorded in a list.

[0524] Step 4:

[0525] The server evaluates the current traffic volume and the user's emotional state based on the video analysis and emotion analysis results. The server compares the traffic volume with a set threshold and determines whether the traffic volume is below the threshold or whether the user's emotional state is in a specific state (e.g., impatience, anger).

[0526] Step 5:

[0527] The server obtains the current signal status from the signal controller. The server sends a status request to the signal controller to check whether the signal is currently red or green.

[0528] Step 6:

[0529] The server determines whether the traffic light needs to be changed based on the traffic volume evaluation result and the user's emotional state. If the traffic volume is below a threshold and the user's emotional state is impatient, the server determines that the traffic light needs to be changed to green.

[0530] Step 7:

[0531] The server sends a signal switching command to the signal control device. The server sends a command to the signal control device to change the signal to green, and verifies that the command was sent successfully.

[0532] Step 8:

[0533] The server checks the changed signal status and sends a status request to the signal controller again to check whether the signal has been changed to green correctly.

[0534] Step 9:

[0535] The server records the result of the traffic light change in a log. If a change is confirmed, the result is written to a log file. The log records the time of the traffic light change, the type of change (from red to green, from green to red), and the reason for the change (traffic volume evaluation result and user sentiment).

[0536] Step 10:

[0537] The server starts again after a certain time by acquiring camera footage and emotion data. A certain timer is set and this process is repeated at regular intervals.

[0538] Through the above steps, the server can automatically control the traffic lights at the intersection and achieve efficient traffic light changes according to the traffic volume and the user's emotions.

[0539] Example 2

[0540] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0541] Conventional traffic signal control systems often change signals based on a simple evaluation of traffic volume. This makes it difficult to respond to the emotional state of people at intersections or real-time situations, making it difficult to achieve optimal signal control. The present invention aims to solve this problem and realize flexible signal control that takes into account traffic volume and the emotional state of users.

[0542] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0543] In this invention, the server includes means for acquiring intersection data in real time, means for analyzing the acquired data to detect vehicles and pedestrians, means for analyzing and identifying the user's emotions, means for determining traffic volume and emotional state based on the detection results and the emotion analysis results, means for changing the traffic signal when it is determined that traffic volume is below a predetermined threshold or that the user's emotion is in a specific state, and means for confirming the signal state after the change. This enables optimal traffic signal control that takes into account not only traffic volume but also the user's emotional state.

[0544] "Means for acquiring intersection data in real time" refers to devices or systems that have the function of collecting data in real time from sensors or cameras installed at intersections.

[0545] "Means for detecting vehicles and pedestrians by analyzing acquired data" refers to devices or systems that use data analysis technology to identify vehicles and pedestrians from acquired data and identify their positions and directions of movement.

[0546] The "means for analyzing and identifying a user's emotions" refers to technology and devices that analyze the user's facial expressions and behavior to identify their emotional state.

[0547] "Means for determining traffic volume and emotional state based on detection results and emotion analysis results" refers to technology and devices that evaluate the current traffic volume at an intersection and the user's emotional state based on the detection results of vehicles and pedestrians and the user's emotion analysis results.

[0548] "Means for changing traffic signals when it is determined that traffic volume is below a predetermined threshold or the user's emotions are in a specific state" refers to technology and devices for appropriately changing traffic signals when traffic volume is below a predetermined threshold or when the user's emotions are in a specific state.

[0549] "Means for confirming the signal status after the change" refers to the technology and devices for reconfirming the status of the signal after it has been changed.

[0550] The present invention aims to efficiently control traffic signals at intersections, and is a system that achieves advanced traffic signal control by combining an emotion engine that recognizes the user's emotions. This system consists of the following components:

[0551] First, cameras and emotion recognition sensors will be installed at intersections. These devices will monitor the situation at the intersection in real time and send the data to a server. The server will then analyze the data and use it to control traffic lights.

[0552] Data acquisition from cameras and emotion recognition sensors

[0553] The server acquires data in real time from cameras and emotion recognition sensors installed at intersections. Specifically, the server periodically sends requests to the cameras and sensors to receive video data and emotion data. The received data is temporarily stored in memory. The cameras and emotion recognition sensors used here could be ordinary surveillance cameras or sensors that detect facial expressions and tone of voice.

[0554] Video and Emotion Analysis

[0555] The server uses a video analysis module and emotion engine to analyze the acquired video data and emotion data. The video analysis module uses a deep learning model such as YOLOv5. This model is used to identify vehicles and pedestrians in the video. The emotion engine uses Microsoft Azure's Emotion API, among others, to identify emotions from the user's facial expressions and behavior. The analysis results are recorded in a list.

[0556] Traffic and emotion assessment

[0557] The server evaluates the current traffic volume and the user's emotional state based on the detection result list. The evaluation criteria are set as thresholds, and it determines whether the traffic volume is below the threshold and whether the user's emotional state is in a certain state (e.g., impatience, anger).

[0558] Traffic light changes

[0559] The server changes the traffic light when it determines that the traffic volume is below a predetermined threshold or when the user's emotions are in a specific state. It sends a command to the traffic light control device to switch the traffic light from red to green or from green to red. A general traffic light control device can be used as the traffic light control device.

[0560] Check and log signal status

[0561] After the signal change, the server sends a status request to the signal controller to check whether the signal change was successful. If the change is successful, the server records the result in a log file. The log includes the time of the signal change, the type of change (from red to green, or from green to red), and the reason for the change (traffic volume evaluation results and user sentiment).

[0562] Specific examples

[0563] For example, consider an intersection during the daytime. The server acquires real-time data from cameras and emotion recognition sensors installed at the intersection during the daytime. It uses a video analysis module to detect moving vehicles and pedestrians in the video, while simultaneously detecting the user's emotions using an emotion engine. If the server determines that the traffic volume falls below a set threshold or that the detected user emotion is impatience, it sends a command to the traffic light control device to change the light to green. It then confirms that the light has changed to green and records the result in a log.

[0564] Example prompts for generative AI models

[0565] "Your task is to acquire data from cameras and emotion recognition sensors installed at intersections during the day, and design an algorithm that will optimally change traffic signals based on traffic volume and user emotions."

[0566] "Draw a flowchart of a system that analyzes the number of vehicles and pedestrians at an intersection and their emotions in real time to achieve efficient traffic light control."

[0567] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume and user emotions, thereby optimizing traffic flow.

[0568] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0569] Program processing flow

[0570] Step 1: Acquiring camera footage and emotion data

[0571] Input: Real-time data requests from cameras and emotion recognition sensors

[0572] process:

[0573] The server sends an HTTP GET request to the camera and emotion recognition sensor every 5 seconds to obtain the latest video data and emotion data. The camera sends images in JPEG format, and the emotion recognition sensor sends emotion data in JSON format to the server. These data are temporarily stored in memory.

[0574] Output: JPEG video data and JSON format emotion data

[0575] Step 2: Video and emotion analysis

[0576] Input: JPEG video data and JSON emotion data obtained in step 1

[0577] process:

[0578] The server inputs the video data into the YOLOv5 model for object detection. This model identifies vehicles and pedestrians in the video and obtains their coordinate data (x, y, w, h). At the same time, emotion data is input into an emotion engine (e.g., Microsoft Azure Emotion API) to extract emotion categories such as "joy," "anger," and "sadness." The location, direction of movement, and speed of each detected vehicle or pedestrian, as well as the user's emotion information, are recorded in a list.

[0579] Output: A list of analyzed vehicle and pedestrian locations and emotion categories

[0580] Step 3: Assess traffic and sentiment

[0581] Input: Analysis result list created in step 2

[0582] process:

[0583] The server counts the traffic volume within a certain period of time based on the vehicle and pedestrian data in the list. It also analyzes the user's emotional data and evaluates whether a specific emotional state (e.g., impatience, anger) is detected. If the traffic volume falls below a set threshold or the user's emotional state is in a specific state, the server proceeds to the next step. Specifically, the server aggregates the traffic volume every minute and compares it with a threshold (e.g., 10 vehicles or less) and the emotional state.

[0584] Output: Traffic volume and emotion evaluation results (number of passing vehicles and pedestrians, emotional state)

[0585] Step 4: Modifying the Signal

[0586] Input: Traffic volume and emotion evaluation results obtained in Step 3

[0587] process:

[0588] The server changes the traffic light when it determines that the traffic volume is below a certain threshold or that the user's emotions are in a specific state. The server sends a command to the traffic light controller to change the light from red to green or from green to red using a POST request via the REST API. The traffic light controller receives this command and changes the light.

[0589] Output: Changed signal indication

[0590] Step 5: Check and log the signal status

[0591] Input: Signal change command sent in step 4 and response from the signal controller

[0592] process:

[0593] After the signal has changed, the server again sends a GET request to the signal control device to check its status. If the signal has changed correctly, the result is recorded in a log file. The log includes the time of the signal change, the type of change (red to green, green to red), and the reason for the change (traffic volume evaluation results and user emotion). Specifically, the server sends a reconfirmation request to the signal control device after 5 seconds, recording "Change time: 14:35, Change type: red to green, Reason: Frequent occurrence of pedestrian impatience."

[0594] Output: Recorded log data

[0595] (Application example 2)

[0596] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0597] Conventional traffic signal control systems control signals based solely on traffic volume, without taking into account the emotional state of pedestrians and passengers. As a result, they are unable to respond appropriately in emergencies or when users are feeling anxious or stressed, posing challenges to optimizing traffic flow and improving safety.

[0598] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring video of the intersection in real time, means for analyzing the acquired video to detect passing vehicles and pedestrians, emotion recognition means for recognizing the emotional state of the user, means for changing the traffic light when it is determined that the traffic volume and the emotional state of the user are below a predetermined threshold, means for confirming the traffic light status after the change, and means for displaying the traffic light status after the change, including the reason for the change. This enables flexible traffic light changes according to the emotional state of the user, thereby improving traffic safety and efficiency at intersections.

[0599] "Real-time" means that images of the intersection are captured immediately on the spot and processed without delay.

[0600] "Video analysis" is the process of using acquired video data to detect and identify specific information (such as passing vehicles or pedestrians).

[0601] "Traffic volume" refers to the number or volume of vehicles and pedestrians passing through a particular traffic point.

[0602] "User's emotional state" is information that represents the emotions that the user is feeling (for example, joy, anger, impatience, sadness, etc.).

[0603] "Emotion recognition means" refers to a technology or device for determining emotions from the user's facial expressions, actions, etc., and acquiring that information.

[0604] The "means for changing a traffic light" refers to a means for sending a command to a traffic light control device to change the color of the traffic light (such as from red to green or from green to red).

[0605] "Changed signal state" refers to the state of the signal after it has changed (e.g., the signal has turned green or red).

[0606] The "means for displaying the changed signal status including the reason for the change" is a means for showing on a display device the reason why the signal has been changed and the new status of the signal.

[0607] "Log" refers to data that maintains records of system operations and results.

[0608] The system of the present invention is a real-time traffic light control system for enabling autonomous vehicles to pass through intersections efficiently and safely. The system includes a server, cameras installed at intersections, emotion recognition sensors, a traffic light control device, and smart glasses installed in the vehicle.

[0609] The server collects real-time data from cameras and emotion recognition sensors installed at intersections. The cameras use a video analysis module to detect moving vehicles and pedestrians in the video. The emotion recognition sensors analyze the user's facial expressions and movements to obtain emotional data.

[0610] The server performs calculations to determine traffic volume based on the acquired data. It uses a video analysis module and emotion engine with deep learning models to detect and record the number, location, direction, and speed of passing vehicles and pedestrians. It also analyzes the user's emotional state, and if it recognizes certain emotions such as impatience or anger, it makes a decision to respond accordingly.

[0611] If the server determines that the traffic volume and the user's emotional state are below a predetermined threshold, it sends a signal change command to the signal controller. The signal controller changes the signal in accordance with the command, including changing the signal from red to green or vice versa. The changed signal status and the reason for the change are displayed on the smart glasses in real time.

[0612] The changed signal status is recorded in a log, and details such as the reason for the change, the timing, and the type of signal are saved, optimizing traffic flow and improving safety.

[0613] Hardware and software used

[0614] 1. Camera:

[0615] It captures real-time video and uses it in the video analysis module to detect vehicles and pedestrians.

[0616] 2. Emotion Recognition Sensor:

[0617] It recognizes the user's emotional state and transmits that data to a server.

[0618] 3. Signal Control Device:

[0619] The signal is changed based on instructions from the server.

[0620] 4. Smart Glasses:

[0621] The status and reasons for signal changes are displayed in real time so that drivers and passengers can check them.

[0622] 5. Server:

[0623] A video analysis module and emotion engine are used to process the data and send commands to the traffic light controller.

[0624] Specific examples

[0625] For example, if a driver feels extremely anxious when approaching an intersection, the system will detect this emotion through emotion recognition sensors and promptly change the intersection's traffic light from red to green, allowing the vehicle to pass through the intersection smoothly, thereby improving traffic safety and traffic flow.

[0626] Prompt Sentence Examples

[0627] "If the user is impatient, please show how to instruct the intersection signal system to change the signal."

[0628] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0629] Step 1:

[0630] The server receives real-time data from cameras and emotion recognition sensors installed at intersections. The input is the camera footage and data from the emotion recognition sensors, and the output is that these data are temporarily stored in memory. Specifically, the server periodically sends requests to the cameras and sensors to receive video data and emotion data.

[0631] Step 2:

[0632] The server analyzes the acquired video data and emotion data. The input is the video data and emotion data acquired in step 1, and the output is information about detected vehicles and pedestrians, as well as the user's emotion data. The server uses a video analysis module that utilizes a deep learning model to identify vehicles and pedestrians in the video, and an emotion engine to identify emotions from the user's facial expressions and behavior. Specifically, the video analysis module calculates the position, direction of movement, and speed of vehicles and pedestrians, and the emotion engine classifies the user's emotional state.

[0633] Step 3:

[0634] The server evaluates the current traffic volume and the user's emotional state based on the detection result list. The input is the detection result from step 2, and the output is the evaluation results of the traffic volume and emotional state. Specifically, the server compares the traffic volume and the user's emotional state with a predetermined threshold and determines whether the traffic volume is below the threshold or whether the user's emotional state is in a specific state (e.g., impatience, anger).

[0635] Step 4:

[0636] If the server determines that the traffic volume is below a predetermined threshold or that the user's emotions are in a specific state, it sends a signal change command to the traffic light controller. The input is the evaluation result of step 3, and the output is the command sent to the traffic light controller. Specifically, the server checks the current traffic light status and sends an instruction to change the light from red to green, or vice versa, as necessary.

[0637] Step 5:

[0638] The server checks whether the signal change was successful. The input is the response from the signal controller, and the output is the result of the signal change. Specifically, the server sends a status request to the signal controller again to check whether the signal has been changed to the correct state.

[0639] Step 6:

[0640] The server records the changed signal status and the reason for the change in a log and displays it on the smart glasses in real time. The input is the signal change result in step 5 and the evaluation result in step 3, and the output is a log file and display information on the smart glasses. Specifically, the log records the time of the signal change, the type of change, and the reason for the change, and the smart glasses display the current signal status and the reason for the change.

[0641] The above are the processing steps of the system that realizes the application example.

[0642] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0643] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0644] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0645] [Third embodiment]

[0646] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0647] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0648] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0649] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0650] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0651] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0652] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0653] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0654] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0655] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0656] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0657] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0658] The present invention aims to efficiently control traffic lights at intersections. The system includes a server, cameras installed at intersections, and a traffic light control device.

[0659] System Overview

[0660] The server acquires video in real time from cameras installed at intersections and analyzes the video to detect passing vehicles and pedestrians. It also determines the traffic volume based on the detection results and changes the traffic lights if it determines that the traffic volume is below a predetermined threshold. After the traffic light change is made, the server checks the results and records them in a log.

[0661] Explanation of program processing

[0662] Acquiring camera footage

[0663] The server acquires video images in real time from cameras installed at intersections. The server periodically sends requests to the cameras according to a schedule and receives video data. The received video data is temporarily stored in memory.

[0664] Video Analysis

[0665] The server uses a video analysis module to analyze the captured video. The video analysis module utilizes deep learning models to identify and detect vehicles and pedestrians in the video. Information about each detected object, such as its location, direction of movement, and speed, is recorded in a list.

[0666] Traffic volume determination

[0667] The server evaluates the current traffic volume based on the detected object list. The evaluation criterion is set as a threshold, and it determines whether the traffic volume is below this threshold. For example, if there are no vehicles or pedestrians passing by, it determines that the traffic volume is below the threshold.

[0668] Traffic light changes

[0669] The server changes the traffic light when it determines that the traffic volume is below a predetermined threshold. It checks the current status of the traffic light and sends a command to the traffic light controller to switch the traffic light from red to green or from green to red as necessary.

[0670] Check and log signal status

[0671] After the signal change, the server sends a status request to the signal controller again to check whether the signal change was successful. If the change is successful, the result is recorded in a log file. The log includes the time of the signal change, the type of change (from red to green, or from green to red), and the reason for the change (traffic volume evaluation result).

[0672] Specific examples

[0673] Nighttime intersection

[0674] 1. The server acquires real-time video from a camera installed at an intersection at night.

[0675] 2. The server uses a video analysis module to detect the absence of moving vehicles or pedestrians in the video.

[0676] 3. The server evaluates the traffic volume to be zero and determines that this is below a set threshold (e.g., less than 3 vehicles).

[0677] 4. The server determines that the current traffic light state is red and that the light should be changed to green.

[0678] 5. The server sends a command to the traffic light controller to change the light to green.

[0679] 6. The server verifies that the traffic light has changed to green and logs the result.

[0680] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume, thereby optimizing traffic flow.

[0681] The processing flow will be explained below.

[0682] Step 1:

[0683] The server acquires video in real time from cameras installed at intersections. The server periodically sends requests to the cameras to receive video data. The received video data is temporarily stored in memory.

[0684] Step 2:

[0685] The server uses a video analysis module to analyze the acquired video data. The server inputs the video data into the video analysis module, which uses a deep learning model to identify vehicles and pedestrians in the video.

[0686] Step 3:

[0687] The server extracts information about each identified object, such as its location, direction of movement, and speed, and compiles this information into a list that is saved as the analysis results.

[0688] Step 4:

[0689] The server analyzes the detection result list and evaluates the current traffic volume. The server compares it with a set threshold and determines whether the traffic volume is below the threshold. For example, if there are less than three vehicles, it determines that the traffic volume is below the threshold.

[0690] Step 5:

[0691] The server obtains the current signal status from the signal controller. The server sends a status request to the signal controller to check whether the signal is currently red or green.

[0692] Step 6:

[0693] The server determines whether the traffic light needs to be changed based on the traffic volume evaluation result and the traffic light status. If the traffic volume is low and the traffic light is red, the server determines that the traffic light needs to be changed to green.

[0694] Step 7:

[0695] The server sends a signal switching command to the signal control device. The server sends a command to the signal control device to change the signal to green, and verifies that the command was sent successfully.

[0696] Step 8:

[0697] The server checks the changed signal status and sends a status request to the signal controller again to check whether the signal has been changed to green correctly.

[0698] Step 9:

[0699] The server records the result of the traffic light change in a log. If a change is confirmed, the result is written to a log file. The log records the time of the traffic light change, the type of change (red to green, green to red), and the reason for the change (traffic volume evaluation result).

[0700] Step 10:

[0701] The server starts again by acquiring camera footage after a certain time, setting a timer and repeating this process at regular intervals.

[0702] By following the above steps, the server can automatically control the traffic lights at the intersection and achieve efficient traffic light changes according to the traffic volume.

[0703] Example 1

[0704] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0705] Traffic light control at intersections is often performed at fixed timings and is sometimes unable to respond to fluctuations in traffic volume. As a result, traffic congestion and unnecessary waits at traffic lights occur, posing the problem of inefficient traffic flow. In addition, due to a lack of flexible control of traffic lights at night and during off-peak hours, it is not possible to change traffic lights according to traffic volume.

[0706] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0707] In this invention, the server includes means for acquiring images in real time from cameras at intersections, means for temporarily storing the acquired images in memory, means for analyzing the stored images to detect passing vehicles and pedestrians, means for recording the positions, movement directions, and speeds of the detected vehicles and pedestrians in a list, means for determining traffic volume based on the detection results, means for changing the traffic signal if it is determined that the traffic volume is below a predetermined threshold, means for reacquiring and confirming the signal status after the change, and means for recording the change results in a log. This enables flexible signal changes according to traffic volume, thereby optimizing traffic flow.

[0708] An "intersection camera" is a camera device that is installed at an intersection and captures images of the surrounding area in real time.

[0709] "Real-time" means that data or information is processed at the same time it is acquired.

[0710] A "server" is a computer system that processes, stores, analyzes, etc., video data acquired from cameras at intersections.

[0711] "Means for acquiring video" refers to a method or system for receiving video data from an intersection camera in real time.

[0712] "Means for temporarily storing in memory" refers to a storage device for temporarily storing received video data and a method for operating the storage device.

[0713] "Means for analyzing video" refers to methods and systems that use computer vision and deep learning technology to analyze acquired video data and extract important information.

[0714] "Means for detecting vehicles and pedestrians" refers to methods and systems that use video analysis to identify moving objects such as vehicles and pedestrians and determine their locations and attributes.

[0715] "Means for recording in a list" refers to a method or system for recording and managing information about detected vehicles and pedestrians in list form.

[0716] "Means for determining traffic volume" refers to a method or system that evaluates traffic volume based on the number of detected vehicles and pedestrians and compares it with a threshold value as a criterion.

[0717] "Means for changing a traffic signal" means a method or system for changing a traffic signal from red to green or green to red based on a traffic volume determination.

[0718] "Means for reacquiring and confirming the signal status after the change" refers to a method or system for checking the status of the signal after the change and whether the change was made correctly.

[0719] "Means for recording in a log" refers to a method or system for recording the results of signal changes and the reasons for them, and saving them for future reference.

[0720] The present invention is a system including a server, cameras installed at intersections, and a traffic light control device, for the purpose of efficiently controlling traffic lights at intersections.

[0721] System Overview

[0722] The server acquires video in real time from cameras installed at intersections and analyzes the video to detect passing vehicles and pedestrians. It also determines the traffic volume based on the detection results and changes the traffic lights if it determines that the traffic volume is below a predetermined threshold. After the traffic light change is made, the server checks the results and records them in a log.

[0723] Hardware and software used

[0724] Cameras: The cameras installed at intersections are high-resolution cameras such as the AXIS P1445-LE.

[0725] Server: Uses high-performance devices such as NVIDIA Jetson Xavier to process video analysis.

[0726] Deep learning framework: TensorFlow and PyTorch are used for video analysis.

[0727] Video analysis module: Uses the OpenCV library and YOLOv5 to identify and detect vehicles and pedestrians.

[0728] Traffic signal control device: A SIGMA traffic signal controller is used to control and change traffic signals.

[0729] Communication protocol: Communication with the signal control device is performed using the MQTT protocol.

[0730] Log management software: Use the Elastic Stack (Elasticsearch, Logstash, Kibana) to record and manage logs.

[0731] Specific example of system operation

[0732] Processing at intersections at night

[0733] 1. The server acquires real-time video from a camera installed at an intersection at night. The camera is an AXIS P1445-LE, and the server is an NVIDIA Jetson Xavier.

[0734] 2. The server temporarily stores the captured video in DRAM.

[0735] 3. The server uses a video analysis module (OpenCV and YOLOv5) to detect the absence of moving vehicles or pedestrians in the video.

[0736] 4. The server evaluates the traffic volume to be zero and determines that this is below a set threshold (e.g., less than 3 vehicles).

[0737] 5. The server determines that the current traffic light status is red and that the light should be changed to green.

[0738] 6. The server uses the MQTT protocol to send a command to the traffic light controller to change the light to green.

[0739] 7. The server checks again to see if the light has changed to green and logs the result in the Elastic Stack.

[0740] Prompt Sentence Examples

[0741] Based on the specific example, the prompt sentence for the generative AI model is created as follows:

[0742] "Please explain how you would implement a system that analyzes camera footage at intersections and efficiently controls traffic lights when traffic volume is low at night. Please also provide details about the hardware (e.g., NVIDIA Jetson Xavier, AXIS P1445-LE camera) and software (e.g., TensorFlow, Elastic Stack) you used."

[0743] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume, thereby optimizing traffic flow.

[0744] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0745] Step 1:

[0746] Acquiring camera footage

[0747] The server acquires video in real time from a camera installed at an intersection. As input, it receives the camera's video stream URL. Specifically, the server periodically (for example, every second) sends an HTTP request to the camera and receives video data in stream format. As output, it obtains real-time video frames.

[0748] Step 2:

[0749] Temporary storage of video data

[0750] The server temporarily stores the acquired video data in memory. As input, it receives the video frames acquired in step 1. Specifically, the server allocates a buffer area in DRAM and stores the video data there sequentially. As output, it obtains the video frames stored in memory.

[0751] Step 3:

[0752] Video Analysis

[0753] The server uses a deep learning model (YOLOv5) to analyze the stored video. As input, it receives the video frames stored in memory in step 2. Specifically, the server inputs each frame into the deep learning model to detect the position, direction of movement, and speed of vehicles and pedestrians in that frame. As output, it obtains a list of detected objects.

[0754] Step 4:

[0755] Traffic volume determination

[0756] The server evaluates traffic volume based on the list of detected objects. It receives the object list obtained in step 3 as input. Specifically, the server analyzes the location information, movement direction, and speed data for each object to calculate the traffic volume. The output is a comparison result between the current traffic volume and the set threshold.

[0757] Step 5:

[0758] Traffic light changes

[0759] If the server determines that the traffic volume is below a predetermined threshold, it sends a command to the traffic light control device to change the signal. As input, it receives the judgment result from step 4. Specifically, the server uses the MQTT protocol to send a command to the traffic light control device to "change the red light to a green light." As output, a signal change command is sent.

[0760] Step 6:

[0761] Check and log signal status

[0762] The server sends a status request to the signal control device again to confirm whether the signal has been changed correctly. As input, it receives the result of the signal change command transmission and the current signal status. Specifically, the server sends a request to the signal control device asking "Please tell me the signal status" and checks the response from the device. It then records the change results as a log using Elastic Stack. As output, it obtains the signal status confirmation result and log record.

[0763] This allows the server to execute a series of processes and efficiently control traffic lights at intersections.

[0764] (Application example 1)

[0765] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0766] Conventional traffic light control systems at intersections have difficulty grasping road conditions in real time and efficiently controlling traffic lights. Furthermore, as autonomous vehicles become more widespread, there is a lack of coordination between traffic signals and autonomous driving systems, resulting in a lack of smooth traffic flow at intersections. This can prevent autonomous vehicles from fully optimizing their routes, potentially increasing the risk of traffic congestion and accidents.

[0767] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0768] In this invention, the server includes means for acquiring video of the intersection in real time, means for analyzing the acquired video to detect passing vehicles and pedestrians, means for determining traffic volume based on the detection results, means for changing the traffic signal when it is determined that the traffic volume is equal to or less than a predetermined threshold, means for confirming the signal status after the change, means for providing traffic signal information to the autonomous vehicle, and means for optimizing the route of the autonomous vehicle based on the traffic signal information. This makes it possible to improve the efficiency of traffic signal control at the intersection and optimize the route of the autonomous vehicle, thereby smoothing traffic flow and improving safety.

[0769] "Real-time" means processing and providing acquired information and data immediately without delay.

[0770] "Intersection footage" refers to video footage that captures the road conditions around the intersection, as well as the movements of passing vehicles and pedestrians.

[0771] "Means for acquiring video" refers to a system or method for acquiring video data in real time using photographic equipment such as a camera.

[0772] "Means for analyzing video" refers to algorithms and technologies that process acquired video data and recognize and identify specific objects such as vehicles and pedestrians.

[0773] "Means for detecting passing vehicles and pedestrians" refers to techniques and technologies that use video analysis to identify vehicles and pedestrians passing through an intersection and determine their presence and location.

[0774] "Means for determining traffic volume" means a method or device for assessing the degree of traffic congestion at an intersection based on the number and frequency of detected vehicles and pedestrians.

[0775] A "signal changing means" is a device or system that changes an intersection's signal lights from a current state to another state based on a traffic volume determination.

[0776] The "means for verifying the signal state" refers to a method or device for verifying whether the signal change has been made correctly after the change.

[0777] An "autonomous vehicle" is a vehicle that does not require a human driver and drives itself automatically.

[0778] "Means for providing traffic light information" means a system or method for communicating information about the traffic light status at an intersection to an automated vehicle.

[0779] "Means for optimizing travel route" refers to a method or system that supports an automated driving vehicle to select and travel the optimal route based on traffic signal information.

[0780] This invention describes the detailed configuration of a system that has been constructed to improve the efficiency of traffic signal control at intersections and strengthen cooperation with autonomous vehicles. This system grasps the intersection situation in real time and supports autonomous vehicles to pass through the intersection safely and efficiently.

[0781] Hardware and software used

[0782] The server acquires camera images in real time and analyzes them using image processing libraries such as OpenCV. It also uses deep learning models such as YOLOv4 to identify vehicles and pedestrians. Using these technologies, the server determines traffic volume at intersections and sends commands to traffic light control devices. It also provides traffic light information to the autonomous vehicle's control system, helping to optimize the vehicle's route.

[0783] Cameras are installed at appropriate locations at intersections and transmit images in real time to a server. The server periodically sends requests to the cameras and stores the captured image data in memory. The captured images are analyzed using a pre-trained deep learning model. The analysis results are recorded in list format, and the traffic volume at the intersection is evaluated based on this list.

[0784] Traffic volume is determined based on the number of detected vehicles and pedestrians. If the traffic volume falls below a predetermined threshold, the server sends a command to the traffic light control device to change the signal. After the signal change, the server checks whether the change was successful and records the result in a log.

[0785] Specific examples

[0786] For example, at night, there are fewer vehicles and pedestrians passing through intersections, so if the server analyzes the camera footage and determines that the traffic volume is below a threshold, it immediately changes the traffic lights. This information is also provided to autonomous vehicles, which then optimize their routes.

[0787] Prompt Sentence Examples

[0788] Please complete the missing parts of the source code below:

[0789] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0790] Step 1:

[0791] The server acquires video in real time from cameras installed at intersections. The input is the video stream from the camera, which the server periodically requests and acquires. The output is real-time video data. The video data is temporarily stored in memory.

[0792] Step 2:

[0793] The server uses image processing libraries such as OpenCV to analyze the captured video. The input is the real-time video data captured in step 1, and the output is the analyzed video data. Specifically, the server uses a pre-trained YOLOv4 model to identify vehicles and pedestrians, and to identify the location and type of each object.

[0794] Step 3:

[0795] The server detects passing vehicles and pedestrians based on the analyzed video data. The input is the analysis result from step 2, and the output is a list of detected objects. The server creates the list and records the location information and movement direction of each object.

[0796] Step 4:

[0797] The server determines the traffic volume based on the detected object list. The input is the object list created in step 3, and the output is the traffic volume value. The server compares it with the set threshold and evaluates whether the traffic volume is below the threshold.

[0798] Step 5:

[0799] If the server determines that the traffic volume is below a predetermined threshold, it sends a command to the signal control device to change the signal. The input is the traffic volume determination result from step 4, and the output is a command to the signal control device. The server checks the current signal status and switches the signal from red to green or from green to red as necessary.

[0800] Step 6:

[0801] The server checks the status of the signal after changing it. The input is the response from the signal control device, and the output is the confirmation result of whether the signal change was successful. If the change was successful, the server records the result in a log.

[0802] Step 7:

[0803] The server provides intersection traffic light information to the autonomous vehicle. The input is the current traffic light status and traffic volume judgment result, and the output is traffic light information to the autonomous vehicle. The server supports the autonomous vehicle in selecting the optimal route.

[0804] Step 8:

[0805] The autonomous vehicle optimizes its route based on traffic signal information provided by the server. The input is traffic signal information provided by the server, and the output is the optimized route. This allows the autonomous vehicle to travel safely and efficiently.

[0806] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0807] The present invention aims to efficiently control traffic signals at intersections, and in particular, it is a system that achieves more advanced traffic signal control by combining an emotion engine that recognizes the user's emotions. This system includes a server, cameras installed at intersections, emotion recognition sensors, and a traffic signal control device, and controls traffic signals according to the user's emotional state.

[0808] System Overview

[0809] The server acquires data from cameras and emotion recognition sensors installed at intersections, and analyzes the data to detect the number of vehicles and pedestrians passing by, as well as the user's emotions.The server evaluates the traffic volume and user emotions based on the detection results, and changes the traffic light if it determines that the traffic volume is below a predetermined threshold or if the user's emotions are in a specific state.After changing the traffic light, it checks the results and records them in a log.

[0810] Explanation of program processing

[0811] Acquiring camera footage and emotion data

[0812] The server collects real-time data from cameras and emotion recognition sensors installed at intersections. The server periodically sends requests to the cameras and sensors to receive video and emotion data. The received data is temporarily stored in memory.

[0813] Video and Emotion Analysis

[0814] The server uses a video analysis module and emotion engine to analyze the captured video data and emotion data. The video analysis module utilizes deep learning models to identify vehicles and pedestrians in the video. The emotion engine identifies emotions from the user's facial expressions and behavior. The location, direction of movement, speed, and user emotion information of each detected vehicle or pedestrian are recorded in a list.

[0815] Traffic and emotion assessment

[0816] The server evaluates the current traffic volume and the user's emotional state based on the detection result list. The evaluation criteria are set as thresholds, and it determines whether the traffic volume is below the threshold and whether the user's emotional state is in a certain state (e.g., impatience, anger).

[0817] Traffic light changes

[0818] The server changes the traffic light when it determines that the traffic volume is below a predetermined threshold or when the user's emotions are in a specific state. It checks the current state of the traffic light and sends a command to the traffic light control device to change the light from red to green or from green to red as necessary.

[0819] Check and log signal status

[0820] After the signal change, the server sends a status request to the signal controller again to confirm whether the signal change was successful. If the change is confirmed, the result is recorded in a log file. The log includes the time of the signal change, the type of change (from red to green, or from green to red), and the reason for the change (traffic volume evaluation results and user sentiment).

[0821] Specific examples

[0822] Daytime intersection

[0823] 1. The server collects real-time data from cameras and emotion recognition sensors installed at intersections during the day.

[0824] 2. The server uses a video analysis module to detect moving vehicles and pedestrians in the video, and simultaneously detects the user's emotions using an emotion engine.

[0825] 3. The server evaluates whether the traffic volume is below a set threshold or the detected user emotion is impatience.

[0826] 4. The server determines that the current traffic light state is red and that the light should be changed to green.

[0827] 5. The server sends a command to the traffic light controller to change the light to green.

[0828] 6. The server verifies that the traffic light has changed to green and logs the result.

[0829] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume and user emotions, thereby optimizing traffic flow.

[0830] The processing flow will be explained below.

[0831] Step 1:

[0832] The server collects real-time data from cameras and emotion recognition sensors installed at intersections. The server periodically sends requests to the cameras and sensors to receive video and emotion data. The received data is temporarily stored in memory.

[0833] Step 2:

[0834] The server uses a video analysis module to analyze the acquired video data. The server inputs the video data into the video analysis module and uses a deep learning model to identify vehicles and pedestrians in the video. Information such as the location, direction of movement, and speed of each identified object is extracted and compiled into a list.

[0835] Step 3:

[0836] The server uses an emotion engine to analyze the acquired emotion data. The emotion engine identifies the user's facial expressions and behavior patterns and estimates their emotional state. The detected emotion information is recorded in a list.

[0837] Step 4:

[0838] The server evaluates the current traffic volume and the user's emotional state based on the video analysis and emotion analysis results. The server compares the traffic volume with a set threshold and determines whether the traffic volume is below the threshold or whether the user's emotional state is in a specific state (e.g., impatience, anger).

[0839] Step 5:

[0840] The server obtains the current signal status from the signal controller. The server sends a status request to the signal controller to check whether the signal is currently red or green.

[0841] Step 6:

[0842] The server determines whether the traffic light needs to be changed based on the traffic volume evaluation result and the user's emotional state. If the traffic volume is below a threshold and the user's emotional state is impatient, the server determines that the traffic light needs to be changed to green.

[0843] Step 7:

[0844] The server sends a signal switching command to the signal control device. The server sends a command to the signal control device to change the signal to green, and verifies that the command was sent successfully.

[0845] Step 8:

[0846] The server checks the changed signal status and sends a status request to the signal controller again to check whether the signal has been changed to green correctly.

[0847] Step 9:

[0848] The server records the result of the traffic light change in a log. If a change is confirmed, the result is written to a log file. The log records the time of the traffic light change, the type of change (from red to green, from green to red), and the reason for the change (traffic volume evaluation result and user sentiment).

[0849] Step 10:

[0850] The server starts again after a certain time by acquiring camera footage and emotion data. A certain timer is set and this process is repeated at regular intervals.

[0851] Through the above steps, the server can automatically control the traffic lights at the intersection and achieve efficient traffic light changes according to the traffic volume and the user's emotions.

[0852] Example 2

[0853] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0854] Conventional traffic signal control systems often change signals based on a simple evaluation of traffic volume. This makes it difficult to respond to the emotional state of people at intersections or real-time situations, making it difficult to achieve optimal signal control. The present invention aims to solve this problem and realize flexible signal control that takes into account traffic volume and the emotional state of users.

[0855] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0856] In this invention, the server includes means for acquiring intersection data in real time, means for analyzing the acquired data to detect vehicles and pedestrians, means for analyzing and identifying the user's emotions, means for determining traffic volume and emotional state based on the detection results and the emotion analysis results, means for changing the traffic signal when it is determined that traffic volume is below a predetermined threshold or that the user's emotion is in a specific state, and means for confirming the signal state after the change. This enables optimal traffic signal control that takes into account not only traffic volume but also the user's emotional state.

[0857] "Means for acquiring intersection data in real time" refers to devices or systems that have the function of collecting data in real time from sensors or cameras installed at intersections.

[0858] "Means for detecting vehicles and pedestrians by analyzing acquired data" refers to devices or systems that use data analysis technology to identify vehicles and pedestrians from acquired data and identify their positions and directions of movement.

[0859] The "means for analyzing and identifying a user's emotions" refers to technology and devices that analyze the user's facial expressions and behavior to identify their emotional state.

[0860] "Means for determining traffic volume and emotional state based on detection results and emotion analysis results" refers to technology and devices that evaluate the current traffic volume at an intersection and the user's emotional state based on the detection results of vehicles and pedestrians and the user's emotion analysis results.

[0861] "Means for changing traffic signals when it is determined that traffic volume is below a predetermined threshold or the user's emotions are in a specific state" refers to technology and devices for appropriately changing traffic signals when traffic volume is below a predetermined threshold or when the user's emotions are in a specific state.

[0862] "Means for confirming the signal status after the change" refers to the technology and devices for reconfirming the status of the signal after it has been changed.

[0863] The present invention aims to efficiently control traffic signals at intersections, and is a system that achieves advanced traffic signal control by combining an emotion engine that recognizes the user's emotions. This system consists of the following components:

[0864] First, cameras and emotion recognition sensors will be installed at intersections. These devices will monitor the situation at the intersection in real time and send the data to a server. The server will then analyze the data and use it to control traffic lights.

[0865] Data acquisition from cameras and emotion recognition sensors

[0866] The server acquires data in real time from cameras and emotion recognition sensors installed at intersections. Specifically, the server periodically sends requests to the cameras and sensors to receive video data and emotion data. The received data is temporarily stored in memory. The cameras and emotion recognition sensors used here could be ordinary surveillance cameras or sensors that detect facial expressions and tone of voice.

[0867] Video and Emotion Analysis

[0868] The server uses a video analysis module and emotion engine to analyze the acquired video data and emotion data. The video analysis module uses a deep learning model such as YOLOv5. This model is used to identify vehicles and pedestrians in the video. The emotion engine uses Microsoft Azure's Emotion API, among others, to identify emotions from the user's facial expressions and behavior. The analysis results are recorded in a list.

[0869] Traffic and emotion assessment

[0870] The server evaluates the current traffic volume and the user's emotional state based on the detection result list. The evaluation criteria are set as thresholds, and it determines whether the traffic volume is below the threshold and whether the user's emotional state is in a certain state (e.g., impatience, anger).

[0871] Traffic light changes

[0872] The server changes the traffic light when it determines that the traffic volume is below a predetermined threshold or when the user's emotions are in a specific state. It sends a command to the traffic light control device to switch the traffic light from red to green or from green to red. A general traffic light control device can be used as the traffic light control device.

[0873] Check and log signal status

[0874] After the signal change, the server sends a status request to the signal controller to check whether the signal change was successful. If the change is successful, the server records the result in a log file. The log includes the time of the signal change, the type of change (from red to green, or from green to red), and the reason for the change (traffic volume evaluation results and user sentiment).

[0875] Specific examples

[0876] For example, consider an intersection during the daytime. The server acquires real-time data from cameras and emotion recognition sensors installed at the intersection during the daytime. It uses a video analysis module to detect moving vehicles and pedestrians in the video, while simultaneously detecting the user's emotions using an emotion engine. If the server determines that the traffic volume falls below a set threshold or that the detected user emotion is impatience, it sends a command to the traffic light control device to change the light to green. It then confirms that the light has changed to green and records the result in a log.

[0877] Example prompts for generative AI models

[0878] "Your task is to acquire data from cameras and emotion recognition sensors installed at intersections during the day, and design an algorithm that will optimally change traffic signals based on traffic volume and user emotions."

[0879] "Draw a flowchart of a system that analyzes the number of vehicles and pedestrians at an intersection and their emotions in real time to achieve efficient traffic light control."

[0880] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume and user emotions, thereby optimizing traffic flow.

[0881] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0882] Program processing flow

[0883] Step 1: Acquiring camera footage and emotion data

[0884] Input: Real-time data requests from cameras and emotion recognition sensors

[0885] process:

[0886] The server sends an HTTP GET request to the camera and emotion recognition sensor every 5 seconds to obtain the latest video data and emotion data. The camera sends images in JPEG format, and the emotion recognition sensor sends emotion data in JSON format to the server. These data are temporarily stored in memory.

[0887] Output: JPEG video data and JSON format emotion data

[0888] Step 2: Video and emotion analysis

[0889] Input: JPEG video data and JSON emotion data obtained in step 1

[0890] process:

[0891] The server inputs the video data into the YOLOv5 model for object detection. This model identifies vehicles and pedestrians in the video and obtains their coordinate data (x, y, w, h). At the same time, emotion data is input into an emotion engine (e.g., Microsoft Azure Emotion API) to extract emotion categories such as "joy," "anger," and "sadness." The location, direction of movement, and speed of each detected vehicle or pedestrian, as well as the user's emotion information, are recorded in a list.

[0892] Output: A list of analyzed vehicle and pedestrian locations and emotion categories

[0893] Step 3: Assess traffic and sentiment

[0894] Input: Analysis result list created in step 2

[0895] process:

[0896] The server counts the traffic volume within a certain period of time based on the vehicle and pedestrian data in the list. It also analyzes the user's emotional data and evaluates whether a specific emotional state (e.g., impatience, anger) is detected. If the traffic volume falls below a set threshold or the user's emotional state is in a specific state, the server proceeds to the next step. Specifically, the server aggregates the traffic volume every minute and compares it with a threshold (e.g., 10 vehicles or less) and the emotional state.

[0897] Output: Traffic volume and emotion evaluation results (number of passing vehicles and pedestrians, emotional state)

[0898] Step 4: Modifying the Signal

[0899] Input: Traffic volume and emotion evaluation results obtained in Step 3

[0900] process:

[0901] The server changes the traffic light when it determines that the traffic volume is below a certain threshold or that the user's emotions are in a specific state. The server sends a command to the traffic light controller to change the light from red to green or from green to red using a POST request via the REST API. The traffic light controller receives this command and changes the light.

[0902] Output: Changed signal indication

[0903] Step 5: Check and log the signal status

[0904] Input: Signal change command sent in step 4 and response from the signal controller

[0905] process:

[0906] After the signal has changed, the server again sends a GET request to the signal control device to check its status. If the signal has changed correctly, the result is recorded in a log file. The log includes the time of the signal change, the type of change (red to green, green to red), and the reason for the change (traffic volume evaluation results and user emotion). Specifically, the server sends a reconfirmation request to the signal control device after 5 seconds, recording "Change time: 14:35, Change type: red to green, Reason: Frequent occurrence of pedestrian impatience."

[0907] Output: Recorded log data

[0908] (Application example 2)

[0909] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0910] Conventional traffic signal control systems control signals based solely on traffic volume, without taking into account the emotional state of pedestrians and passengers. As a result, they are unable to respond appropriately in emergencies or when users are feeling anxious or stressed, posing challenges to optimizing traffic flow and improving safety.

[0911] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring video of the intersection in real time, means for analyzing the acquired video to detect passing vehicles and pedestrians, emotion recognition means for recognizing the emotional state of the user, means for changing the traffic light when it is determined that the traffic volume and the emotional state of the user are below a predetermined threshold, means for confirming the traffic light status after the change, and means for displaying the traffic light status after the change, including the reason for the change. This enables flexible traffic light changes according to the emotional state of the user, thereby improving traffic safety and efficiency at intersections.

[0912] "Real-time" means that images of the intersection are captured immediately on the spot and processed without delay.

[0913] "Video analysis" is the process of using acquired video data to detect and identify specific information (such as passing vehicles or pedestrians).

[0914] "Traffic volume" refers to the number or volume of vehicles and pedestrians passing through a particular traffic point.

[0915] "User's emotional state" is information that represents the emotions that the user is feeling (for example, joy, anger, impatience, sadness, etc.).

[0916] "Emotion recognition means" refers to a technology or device for determining emotions from the user's facial expressions, actions, etc., and acquiring that information.

[0917] The "means for changing a traffic light" refers to a means for sending a command to a traffic light control device to change the color of the traffic light (such as from red to green or from green to red).

[0918] "Changed signal state" refers to the state of the signal after it has changed (e.g., the signal has turned green or red).

[0919] The "means for displaying the changed signal status including the reason for the change" is a means for showing on a display device the reason why the signal has been changed and the new status of the signal.

[0920] "Log" refers to data that maintains records of system operations and results.

[0921] The system of the present invention is a real-time traffic light control system for enabling autonomous vehicles to pass through intersections efficiently and safely. The system includes a server, cameras installed at intersections, emotion recognition sensors, a traffic light control device, and smart glasses installed in the vehicle.

[0922] The server collects real-time data from cameras and emotion recognition sensors installed at intersections. The cameras use a video analysis module to detect moving vehicles and pedestrians in the video. The emotion recognition sensors analyze the user's facial expressions and movements to obtain emotional data.

[0923] The server performs calculations to determine traffic volume based on the acquired data. It uses a video analysis module and emotion engine with deep learning models to detect and record the number, location, direction, and speed of passing vehicles and pedestrians. It also analyzes the user's emotional state, and if it recognizes certain emotions such as impatience or anger, it makes a decision to respond accordingly.

[0924] If the server determines that the traffic volume and the user's emotional state are below a predetermined threshold, it sends a signal change command to the signal controller. The signal controller changes the signal in accordance with the command, including changing the signal from red to green or vice versa. The changed signal status and the reason for the change are displayed on the smart glasses in real time.

[0925] The changed signal status is recorded in a log, and details such as the reason for the change, the timing, and the type of signal are saved, optimizing traffic flow and improving safety.

[0926] Hardware and software used

[0927] 1. Camera:

[0928] It captures real-time video and uses it in the video analysis module to detect vehicles and pedestrians.

[0929] 2. Emotion Recognition Sensor:

[0930] It recognizes the user's emotional state and transmits that data to a server.

[0931] 3. Signal Control Device:

[0932] The signal is changed based on instructions from the server.

[0933] 4. Smart Glasses:

[0934] The status and reasons for signal changes are displayed in real time so that drivers and passengers can check them.

[0935] 5. Server:

[0936] A video analysis module and emotion engine are used to process the data and send commands to the traffic light controller.

[0937] Specific examples

[0938] For example, if a driver feels extremely anxious when approaching an intersection, the system will detect this emotion through emotion recognition sensors and promptly change the intersection's traffic light from red to green, allowing the vehicle to pass through the intersection smoothly, thereby improving traffic safety and traffic flow.

[0939] Prompt Sentence Examples

[0940] "If the user is impatient, please show how to instruct the intersection signal system to change the signal."

[0941] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0942] Step 1:

[0943] The server receives real-time data from cameras and emotion recognition sensors installed at intersections. The input is the camera footage and data from the emotion recognition sensors, and the output is that these data are temporarily stored in memory. Specifically, the server periodically sends requests to the cameras and sensors to receive video data and emotion data.

[0944] Step 2:

[0945] The server analyzes the acquired video data and emotion data. The input is the video data and emotion data acquired in step 1, and the output is information about detected vehicles and pedestrians, as well as the user's emotion data. The server uses a video analysis module that utilizes a deep learning model to identify vehicles and pedestrians in the video, and an emotion engine to identify emotions from the user's facial expressions and behavior. Specifically, the video analysis module calculates the position, direction of movement, and speed of vehicles and pedestrians, and the emotion engine classifies the user's emotional state.

[0946] Step 3:

[0947] The server evaluates the current traffic volume and the user's emotional state based on the detection result list. The input is the detection result from step 2, and the output is the evaluation results of the traffic volume and emotional state. Specifically, the server compares the traffic volume and the user's emotional state with a predetermined threshold and determines whether the traffic volume is below the threshold or whether the user's emotional state is in a specific state (e.g., impatience, anger).

[0948] Step 4:

[0949] If the server determines that the traffic volume is below a predetermined threshold or that the user's emotions are in a specific state, it sends a signal change command to the traffic light controller. The input is the evaluation result of step 3, and the output is the command sent to the traffic light controller. Specifically, the server checks the current traffic light status and sends an instruction to change the light from red to green, or vice versa, as necessary.

[0950] Step 5:

[0951] The server checks whether the signal change was successful. The input is the response from the signal controller, and the output is the result of the signal change. Specifically, the server sends a status request to the signal controller again to check whether the signal has been changed to the correct state.

[0952] Step 6:

[0953] The server records the changed signal status and the reason for the change in a log and displays it on the smart glasses in real time. The input is the signal change result in step 5 and the evaluation result in step 3, and the output is a log file and display information on the smart glasses. Specifically, the log records the time of the signal change, the type of change, and the reason for the change, and the smart glasses display the current signal status and the reason for the change.

[0954] The above are the processing steps of the system that realizes the application example.

[0955] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0956] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0957] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0958] [Fourth embodiment]

[0959] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0960] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0961] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0962] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0963] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0964] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0965] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0966] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0967] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0968] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0969] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0970] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0971] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0972] The present invention aims to efficiently control traffic lights at intersections. The system includes a server, cameras installed at intersections, and a traffic light control device.

[0973] System Overview

[0974] The server acquires video in real time from cameras installed at intersections and analyzes the video to detect passing vehicles and pedestrians. It also determines the traffic volume based on the detection results and changes the traffic lights if it determines that the traffic volume is below a predetermined threshold. After the traffic light change is made, the server checks the results and records them in a log.

[0975] Explanation of program processing

[0976] Acquiring camera footage

[0977] The server acquires video images in real time from cameras installed at intersections. The server periodically sends requests to the cameras according to a schedule and receives video data. The received video data is temporarily stored in memory.

[0978] Video Analysis

[0979] The server uses a video analysis module to analyze the captured video. The video analysis module utilizes deep learning models to identify and detect vehicles and pedestrians in the video. Information about each detected object, such as its location, direction of movement, and speed, is recorded in a list.

[0980] Traffic volume determination

[0981] The server evaluates the current traffic volume based on the detected object list. The evaluation criterion is set as a threshold, and it determines whether the traffic volume is below this threshold. For example, if there are no vehicles or pedestrians passing by, it determines that the traffic volume is below the threshold.

[0982] Traffic light changes

[0983] The server changes the traffic light when it determines that the traffic volume is below a predetermined threshold. It checks the current status of the traffic light and sends a command to the traffic light controller to switch the traffic light from red to green or from green to red as necessary.

[0984] Check and log signal status

[0985] After the signal change, the server sends a status request to the signal controller again to check whether the signal change was successful. If the change is successful, the result is recorded in a log file. The log includes the time of the signal change, the type of change (from red to green, or from green to red), and the reason for the change (traffic volume evaluation result).

[0986] Specific examples

[0987] Nighttime intersection

[0988] 1. The server acquires real-time video from a camera installed at an intersection at night.

[0989] 2. The server uses a video analysis module to detect the absence of moving vehicles or pedestrians in the video.

[0990] 3. The server evaluates the traffic volume to be zero and determines that this is below a set threshold (e.g., less than 3 vehicles).

[0991] 4. The server determines that the current traffic light state is red and that the light should be changed to green.

[0992] 5. The server sends a command to the traffic light controller to change the light to green.

[0993] 6. The server verifies that the traffic light has changed to green and logs the result.

[0994] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume, thereby optimizing traffic flow.

[0995] The processing flow will be explained below.

[0996] Step 1:

[0997] The server acquires video in real time from cameras installed at intersections. The server periodically sends requests to the cameras to receive video data. The received video data is temporarily stored in memory.

[0998] Step 2:

[0999] The server uses a video analysis module to analyze the acquired video data. The server inputs the video data into the video analysis module, which uses a deep learning model to identify vehicles and pedestrians in the video.

[1000] Step 3:

[1001] The server extracts information about each identified object, such as its location, direction of movement, and speed, and compiles this information into a list that is saved as the analysis results.

[1002] Step 4:

[1003] The server analyzes the detection result list and evaluates the current traffic volume. The server compares it with a set threshold and determines whether the traffic volume is below the threshold. For example, if there are less than three vehicles, it determines that the traffic volume is below the threshold.

[1004] Step 5:

[1005] The server obtains the current signal status from the signal controller. The server sends a status request to the signal controller to check whether the signal is currently red or green.

[1006] Step 6:

[1007] The server determines whether the traffic light needs to be changed based on the traffic volume evaluation result and the traffic light status. If the traffic volume is low and the traffic light is red, the server determines that the traffic light needs to be changed to green.

[1008] Step 7:

[1009] The server sends a signal switching command to the signal control device. The server sends a command to the signal control device to change the signal to green, and verifies that the command was sent successfully.

[1010] Step 8:

[1011] The server checks the changed signal status and sends a status request to the signal controller again to check whether the signal has been changed to green correctly.

[1012] Step 9:

[1013] The server records the result of the traffic light change in a log. If a change is confirmed, the result is written to a log file. The log records the time of the traffic light change, the type of change (red to green, green to red), and the reason for the change (traffic volume evaluation result).

[1014] Step 10:

[1015] The server starts again by acquiring camera footage after a certain time, setting a timer and repeating this process at regular intervals.

[1016] By following the above steps, the server can automatically control the traffic lights at the intersection and achieve efficient traffic light changes according to the traffic volume.

[1017] Example 1

[1018] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1019] Traffic light control at intersections is often performed at fixed timings and is sometimes unable to respond to fluctuations in traffic volume. As a result, traffic congestion and unnecessary waits at traffic lights occur, posing the problem of inefficient traffic flow. In addition, due to a lack of flexible control of traffic lights at night and during off-peak hours, it is not possible to change traffic lights according to traffic volume.

[1020] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1021] In this invention, the server includes means for acquiring images in real time from cameras at intersections, means for temporarily storing the acquired images in memory, means for analyzing the stored images to detect passing vehicles and pedestrians, means for recording the positions, movement directions, and speeds of the detected vehicles and pedestrians in a list, means for determining traffic volume based on the detection results, means for changing the traffic signal if it is determined that the traffic volume is below a predetermined threshold, means for reacquiring and confirming the signal status after the change, and means for recording the change results in a log. This enables flexible signal changes according to traffic volume, thereby optimizing traffic flow.

[1022] An "intersection camera" is a camera device that is installed at an intersection and captures images of the surrounding area in real time.

[1023] "Real-time" means that data or information is processed at the same time it is acquired.

[1024] A "server" is a computer system that processes, stores, analyzes, etc., video data acquired from cameras at intersections.

[1025] "Means for acquiring video" refers to a method or system for receiving video data from an intersection camera in real time.

[1026] "Means for temporarily storing in memory" refers to a storage device for temporarily storing received video data and a method for operating the storage device.

[1027] "Means for analyzing video" refers to methods and systems that use computer vision and deep learning technology to analyze acquired video data and extract important information.

[1028] "Means for detecting vehicles and pedestrians" refers to methods and systems that use video analysis to identify moving objects such as vehicles and pedestrians and determine their locations and attributes.

[1029] "Means for recording in a list" refers to a method or system for recording and managing information about detected vehicles and pedestrians in list form.

[1030] "Means for determining traffic volume" refers to a method or system that evaluates traffic volume based on the number of detected vehicles and pedestrians and compares it with a threshold value as a criterion.

[1031] "Means for changing a traffic signal" means a method or system for changing a traffic signal from red to green or green to red based on a traffic volume determination.

[1032] "Means for reacquiring and confirming the signal status after the change" refers to a method or system for checking the status of the signal after the change and whether the change was made correctly.

[1033] "Means for recording in a log" refers to a method or system for recording the results of signal changes and the reasons for them, and saving them for future reference.

[1034] The present invention is a system including a server, cameras installed at intersections, and a traffic light control device, for the purpose of efficiently controlling traffic lights at intersections.

[1035] System Overview

[1036] The server acquires video in real time from cameras installed at intersections and analyzes the video to detect passing vehicles and pedestrians. It also determines the traffic volume based on the detection results and changes the traffic lights if it determines that the traffic volume is below a predetermined threshold. After the traffic light change is made, the server checks the results and records them in a log.

[1037] Hardware and software used

[1038] Cameras: The cameras installed at intersections are high-resolution cameras such as the AXIS P1445-LE.

[1039] Server: Uses high-performance devices such as NVIDIA Jetson Xavier to process video analysis.

[1040] Deep learning framework: TensorFlow and PyTorch are used for video analysis.

[1041] Video analysis module: Uses the OpenCV library and YOLOv5 to identify and detect vehicles and pedestrians.

[1042] Traffic signal control device: A SIGMA traffic signal controller is used to control and change traffic signals.

[1043] Communication protocol: Communication with the signal control device is performed using the MQTT protocol.

[1044] Log management software: Use the Elastic Stack (Elasticsearch, Logstash, Kibana) to record and manage logs.

[1045] Specific example of system operation

[1046] Processing at intersections at night

[1047] 1. The server acquires real-time video from a camera installed at an intersection at night. The camera is an AXIS P1445-LE, and the server is an NVIDIA Jetson Xavier.

[1048] 2. The server temporarily stores the captured video in DRAM.

[1049] 3. The server uses a video analysis module (OpenCV and YOLOv5) to detect the absence of moving vehicles or pedestrians in the video.

[1050] 4. The server evaluates the traffic volume to be zero and determines that this is below a set threshold (e.g., less than 3 vehicles).

[1051] 5. The server determines that the current traffic light status is red and that the light should be changed to green.

[1052] 6. The server uses the MQTT protocol to send a command to the traffic light controller to change the light to green.

[1053] 7. The server checks again to see if the light has changed to green and logs the result in the Elastic Stack.

[1054] Prompt Sentence Examples

[1055] Based on the specific example, the prompt sentence for the generative AI model is created as follows:

[1056] "Please explain how you would implement a system that analyzes camera footage at intersections and efficiently controls traffic lights when traffic volume is low at night. Please also provide details about the hardware (e.g., NVIDIA Jetson Xavier, AXIS P1445-LE camera) and software (e.g., TensorFlow, Elastic Stack) you used."

[1057] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume, thereby optimizing traffic flow.

[1058] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1059] Step 1:

[1060] Acquiring camera footage

[1061] The server acquires video in real time from a camera installed at an intersection. As input, it receives the camera's video stream URL. Specifically, the server periodically (for example, every second) sends an HTTP request to the camera and receives video data in stream format. As output, it obtains real-time video frames.

[1062] Step 2:

[1063] Temporary storage of video data

[1064] The server temporarily stores the acquired video data in memory. As input, it receives the video frames acquired in step 1. Specifically, the server allocates a buffer area in DRAM and stores the video data there sequentially. As output, it obtains the video frames stored in memory.

[1065] Step 3:

[1066] Video Analysis

[1067] The server uses a deep learning model (YOLOv5) to analyze the stored video. As input, it receives the video frames stored in memory in step 2. Specifically, the server inputs each frame into the deep learning model to detect the position, direction of movement, and speed of vehicles and pedestrians in that frame. As output, it obtains a list of detected objects.

[1068] Step 4:

[1069] Traffic volume determination

[1070] The server evaluates traffic volume based on the list of detected objects. It receives the object list obtained in step 3 as input. Specifically, the server analyzes the location information, movement direction, and speed data for each object to calculate the traffic volume. The output is a comparison result between the current traffic volume and the set threshold.

[1071] Step 5:

[1072] Traffic light changes

[1073] If the server determines that the traffic volume is below a predetermined threshold, it sends a command to the traffic light control device to change the signal. As input, it receives the judgment result from step 4. Specifically, the server uses the MQTT protocol to send a command to the traffic light control device to "change the red light to a green light." As output, a signal change command is sent.

[1074] Step 6:

[1075] Check and log signal status

[1076] The server sends a status request to the signal control device again to confirm whether the signal has been changed correctly. As input, it receives the result of the signal change command transmission and the current signal status. Specifically, the server sends a request to the signal control device asking "Please tell me the signal status" and checks the response from the device. It then records the change results as a log using Elastic Stack. As output, it obtains the signal status confirmation result and log record.

[1077] This allows the server to execute a series of processes and efficiently control traffic lights at intersections.

[1078] (Application example 1)

[1079] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1080] Conventional traffic light control systems at intersections have difficulty grasping road conditions in real time and efficiently controlling traffic lights. Furthermore, as autonomous vehicles become more widespread, there is a lack of coordination between traffic signals and autonomous driving systems, resulting in a lack of smooth traffic flow at intersections. This can prevent autonomous vehicles from fully optimizing their routes, potentially increasing the risk of traffic congestion and accidents.

[1081] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1082] In this invention, the server includes means for acquiring video of the intersection in real time, means for analyzing the acquired video to detect passing vehicles and pedestrians, means for determining traffic volume based on the detection results, means for changing the traffic signal when it is determined that the traffic volume is equal to or less than a predetermined threshold, means for confirming the signal status after the change, means for providing traffic signal information to the autonomous vehicle, and means for optimizing the route of the autonomous vehicle based on the traffic signal information. This makes it possible to improve the efficiency of traffic signal control at the intersection and optimize the route of the autonomous vehicle, thereby smoothing traffic flow and improving safety.

[1083] "Real-time" means processing and providing acquired information and data immediately without delay.

[1084] "Intersection footage" refers to video footage that captures the road conditions around the intersection, as well as the movements of passing vehicles and pedestrians.

[1085] "Means for acquiring video" refers to a system or method for acquiring video data in real time using photographic equipment such as a camera.

[1086] "Means for analyzing video" refers to algorithms and technologies that process acquired video data and recognize and identify specific objects such as vehicles and pedestrians.

[1087] "Means for detecting passing vehicles and pedestrians" refers to techniques and technologies that use video analysis to identify vehicles and pedestrians passing through an intersection and determine their presence and location.

[1088] "Means for determining traffic volume" means a method or device for assessing the degree of traffic congestion at an intersection based on the number and frequency of detected vehicles and pedestrians.

[1089] A "signal changing means" is a device or system that changes an intersection's signal lights from a current state to another state based on a traffic volume determination.

[1090] The "means for verifying the signal state" refers to a method or device for verifying whether the signal change has been made correctly after the change.

[1091] An "autonomous vehicle" is a vehicle that does not require a human driver and drives itself automatically.

[1092] "Means for providing traffic light information" means a system or method for communicating information about the traffic light status at an intersection to an automated vehicle.

[1093] "Means for optimizing travel route" refers to a method or system that supports an automated driving vehicle to select and travel the optimal route based on traffic signal information.

[1094] This invention describes the detailed configuration of a system that has been constructed to improve the efficiency of traffic signal control at intersections and strengthen cooperation with autonomous vehicles. This system grasps the intersection situation in real time and supports autonomous vehicles to pass through the intersection safely and efficiently.

[1095] Hardware and software used

[1096] The server acquires camera images in real time and analyzes them using image processing libraries such as OpenCV. It also uses deep learning models such as YOLOv4 to identify vehicles and pedestrians. Using these technologies, the server determines traffic volume at intersections and sends commands to traffic light control devices. It also provides traffic light information to the autonomous vehicle's control system, helping to optimize the vehicle's route.

[1097] Cameras are installed at appropriate locations at intersections and transmit images in real time to a server. The server periodically sends requests to the cameras and stores the captured image data in memory. The captured images are analyzed using a pre-trained deep learning model. The analysis results are recorded in list format, and the traffic volume at the intersection is evaluated based on this list.

[1098] Traffic volume is determined based on the number of detected vehicles and pedestrians. If the traffic volume falls below a predetermined threshold, the server sends a command to the traffic light control device to change the signal. After the signal change, the server checks whether the change was successful and records the result in a log.

[1099] Specific examples

[1100] For example, at night, there are fewer vehicles and pedestrians passing through intersections, so if the server analyzes the camera footage and determines that the traffic volume is below a threshold, it immediately changes the traffic lights. This information is also provided to autonomous vehicles, which then optimize their routes.

[1101] Prompt Sentence Examples

[1102] Please complete the missing parts of the source code below:

[1103] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1104] Step 1:

[1105] The server acquires video in real time from cameras installed at intersections. The input is the video stream from the camera, which the server periodically requests and acquires. The output is real-time video data. The video data is temporarily stored in memory.

[1106] Step 2:

[1107] The server uses image processing libraries such as OpenCV to analyze the captured video. The input is the real-time video data captured in step 1, and the output is the analyzed video data. Specifically, the server uses a pre-trained YOLOv4 model to identify vehicles and pedestrians, and to identify the location and type of each object.

[1108] Step 3:

[1109] The server detects passing vehicles and pedestrians based on the analyzed video data. The input is the analysis result from step 2, and the output is a list of detected objects. The server creates the list and records the location information and movement direction of each object.

[1110] Step 4:

[1111] The server determines the traffic volume based on the detected object list. The input is the object list created in step 3, and the output is the traffic volume value. The server compares it with the set threshold and evaluates whether the traffic volume is below the threshold.

[1112] Step 5:

[1113] If the server determines that the traffic volume is below a predetermined threshold, it sends a command to the signal control device to change the signal. The input is the traffic volume determination result from step 4, and the output is a command to the signal control device. The server checks the current signal status and switches the signal from red to green or from green to red as necessary.

[1114] Step 6:

[1115] The server checks the status of the signal after changing it. The input is the response from the signal control device, and the output is the confirmation result of whether the signal change was successful. If the change was successful, the server records the result in a log.

[1116] Step 7:

[1117] The server provides intersection traffic light information to the autonomous vehicle. The input is the current traffic light status and traffic volume judgment result, and the output is traffic light information to the autonomous vehicle. The server supports the autonomous vehicle in selecting the optimal route.

[1118] Step 8:

[1119] The autonomous vehicle optimizes its route based on traffic signal information provided by the server. The input is traffic signal information provided by the server, and the output is the optimized route. This allows the autonomous vehicle to travel safely and efficiently.

[1120] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1121] The present invention aims to efficiently control traffic signals at intersections, and in particular, it is a system that achieves more advanced traffic signal control by combining an emotion engine that recognizes the user's emotions. This system includes a server, cameras installed at intersections, emotion recognition sensors, and a traffic signal control device, and controls traffic signals according to the user's emotional state.

[1122] System Overview

[1123] The server acquires data from cameras and emotion recognition sensors installed at intersections, and analyzes the data to detect the number of vehicles and pedestrians passing by, as well as the user's emotions.The server evaluates the traffic volume and user emotions based on the detection results, and changes the traffic light if it determines that the traffic volume is below a predetermined threshold or if the user's emotions are in a specific state.After changing the traffic light, it checks the results and records them in a log.

[1124] Explanation of program processing

[1125] Acquiring camera footage and emotion data

[1126] The server collects real-time data from cameras and emotion recognition sensors installed at intersections. The server periodically sends requests to the cameras and sensors to receive video and emotion data. The received data is temporarily stored in memory.

[1127] Video and Emotion Analysis

[1128] The server uses a video analysis module and emotion engine to analyze the captured video data and emotion data. The video analysis module utilizes deep learning models to identify vehicles and pedestrians in the video. The emotion engine identifies emotions from the user's facial expressions and behavior. The location, direction of movement, speed, and user emotion information of each detected vehicle or pedestrian are recorded in a list.

[1129] Traffic and emotion assessment

[1130] The server evaluates the current traffic volume and the user's emotional state based on the detection result list. The evaluation criteria are set as thresholds, and it determines whether the traffic volume is below the threshold and whether the user's emotional state is in a certain state (e.g., impatience, anger).

[1131] Traffic light changes

[1132] The server changes the traffic light when it determines that the traffic volume is below a predetermined threshold or when the user's emotions are in a specific state. It checks the current state of the traffic light and sends a command to the traffic light control device to change the light from red to green or from green to red as necessary.

[1133] Check and log signal status

[1134] After the signal change, the server sends a status request to the signal controller again to confirm whether the signal change was successful. If the change is confirmed, the result is recorded in a log file. The log includes the time of the signal change, the type of change (from red to green, or from green to red), and the reason for the change (traffic volume evaluation results and user sentiment).

[1135] Specific examples

[1136] Daytime intersection

[1137] 1. The server collects real-time data from cameras and emotion recognition sensors installed at intersections during the day.

[1138] 2. The server uses a video analysis module to detect moving vehicles and pedestrians in the video, and simultaneously detects the user's emotions using an emotion engine.

[1139] 3. The server evaluates whether the traffic volume is below a set threshold or the detected user emotion is impatience.

[1140] 4. The server determines that the current traffic light state is red and that the light should be changed to green.

[1141] 5. The server sends a command to the traffic light controller to change the light to green.

[1142] 6. The server verifies that the traffic light has changed to green and logs the result.

[1143] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume and user emotions, thereby optimizing traffic flow.

[1144] The processing flow will be explained below.

[1145] Step 1:

[1146] The server collects real-time data from cameras and emotion recognition sensors installed at intersections. The server periodically sends requests to the cameras and sensors to receive video and emotion data. The received data is temporarily stored in memory.

[1147] Step 2:

[1148] The server uses a video analysis module to analyze the acquired video data. The server inputs the video data into the video analysis module and uses a deep learning model to identify vehicles and pedestrians in the video. Information such as the location, direction of movement, and speed of each identified object is extracted and compiled into a list.

[1149] Step 3:

[1150] The server uses an emotion engine to analyze the acquired emotion data. The emotion engine identifies the user's facial expressions and behavior patterns and estimates their emotional state. The detected emotion information is recorded in a list.

[1151] Step 4:

[1152] The server evaluates the current traffic volume and the user's emotional state based on the video analysis and emotion analysis results. The server compares the traffic volume with a set threshold and determines whether the traffic volume is below the threshold or whether the user's emotional state is in a specific state (e.g., impatience, anger).

[1153] Step 5:

[1154] The server obtains the current signal status from the signal controller. The server sends a status request to the signal controller to check whether the signal is currently red or green.

[1155] Step 6:

[1156] The server determines whether the traffic light needs to be changed based on the traffic volume evaluation result and the user's emotional state. If the traffic volume is below a threshold and the user's emotional state is impatient, the server determines that the traffic light needs to be changed to green.

[1157] Step 7:

[1158] The server sends a signal switching command to the signal control device. The server sends a command to the signal control device to change the signal to green, and verifies that the command was sent successfully.

[1159] Step 8:

[1160] The server checks the changed signal status and sends a status request to the signal controller again to check whether the signal has been changed to green correctly.

[1161] Step 9:

[1162] The server records the result of the traffic light change in a log. If a change is confirmed, the result is written to a log file. The log records the time of the traffic light change, the type of change (from red to green, from green to red), and the reason for the change (traffic volume evaluation result and user sentiment).

[1163] Step 10:

[1164] The server starts again after a certain time by acquiring camera footage and emotion data. A certain timer is set and this process is repeated at regular intervals.

[1165] Through the above steps, the server can automatically control the traffic lights at the intersection and achieve efficient traffic light changes according to the traffic volume and the user's emotions.

[1166] Example 2

[1167] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1168] Conventional traffic signal control systems often change signals based on a simple evaluation of traffic volume. This makes it difficult to respond to the emotional state of people at intersections or real-time situations, making it difficult to achieve optimal signal control. The present invention aims to solve this problem and realize flexible signal control that takes into account traffic volume and the emotional state of users.

[1169] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1170] In this invention, the server includes means for acquiring intersection data in real time, means for analyzing the acquired data to detect vehicles and pedestrians, means for analyzing and identifying the user's emotions, means for determining traffic volume and emotional state based on the detection results and the emotion analysis results, means for changing the traffic signal when it is determined that traffic volume is below a predetermined threshold or that the user's emotion is in a specific state, and means for confirming the signal state after the change. This enables optimal traffic signal control that takes into account not only traffic volume but also the user's emotional state.

[1171] "Means for acquiring intersection data in real time" refers to devices or systems that have the function of collecting data in real time from sensors or cameras installed at intersections.

[1172] "Means for detecting vehicles and pedestrians by analyzing acquired data" refers to devices or systems that use data analysis technology to identify vehicles and pedestrians from acquired data and identify their positions and directions of movement.

[1173] The "means for analyzing and identifying a user's emotions" refers to technology and devices that analyze the user's facial expressions and behavior to identify their emotional state.

[1174] "Means for determining traffic volume and emotional state based on detection results and emotion analysis results" refers to technology and devices that evaluate the current traffic volume at an intersection and the user's emotional state based on the detection results of vehicles and pedestrians and the user's emotion analysis results.

[1175] "Means for changing traffic signals when it is determined that traffic volume is below a predetermined threshold or the user's emotions are in a specific state" refers to technology and devices for appropriately changing traffic signals when traffic volume is below a predetermined threshold or when the user's emotions are in a specific state.

[1176] "Means for confirming the signal status after the change" refers to the technology and devices for reconfirming the status of the signal after it has been changed.

[1177] The present invention aims to efficiently control traffic signals at intersections, and is a system that achieves advanced traffic signal control by combining an emotion engine that recognizes the user's emotions. This system consists of the following components:

[1178] First, cameras and emotion recognition sensors will be installed at intersections. These devices will monitor the situation at the intersection in real time and send the data to a server. The server will then analyze the data and use it to control traffic lights.

[1179] Data acquisition from cameras and emotion recognition sensors

[1180] The server acquires data in real time from cameras and emotion recognition sensors installed at intersections. Specifically, the server periodically sends requests to the cameras and sensors to receive video data and emotion data. The received data is temporarily stored in memory. The cameras and emotion recognition sensors used here could be ordinary surveillance cameras or sensors that detect facial expressions and tone of voice.

[1181] Video and Emotion Analysis

[1182] The server uses a video analysis module and emotion engine to analyze the acquired video data and emotion data. The video analysis module uses a deep learning model such as YOLOv5. This model is used to identify vehicles and pedestrians in the video. The emotion engine uses Microsoft Azure's Emotion API, among others, to identify emotions from the user's facial expressions and behavior. The analysis results are recorded in a list.

[1183] Traffic and emotion assessment

[1184] The server evaluates the current traffic volume and the user's emotional state based on the detection result list. The evaluation criteria are set as thresholds, and it determines whether the traffic volume is below the threshold and whether the user's emotional state is in a certain state (e.g., impatience, anger).

[1185] Traffic light changes

[1186] The server changes the traffic light when it determines that the traffic volume is below a predetermined threshold or when the user's emotions are in a specific state. It sends a command to the traffic light control device to switch the traffic light from red to green or from green to red. A general traffic light control device can be used as the traffic light control device.

[1187] Check and log signal status

[1188] After the signal change, the server sends a status request to the signal controller to check whether the signal change was successful. If the change is successful, the server records the result in a log file. The log includes the time of the signal change, the type of change (from red to green, or from green to red), and the reason for the change (traffic volume evaluation results and user sentiment).

[1189] Specific examples

[1190] For example, consider an intersection during the daytime. The server acquires real-time data from cameras and emotion recognition sensors installed at the intersection during the daytime. It uses a video analysis module to detect moving vehicles and pedestrians in the video, while simultaneously detecting the user's emotions using an emotion engine. If the server determines that the traffic volume falls below a set threshold or that the detected user emotion is impatience, it sends a command to the traffic light control device to change the light to green. It then confirms that the light has changed to green and records the result in a log.

[1191] Example prompts for generative AI models

[1192] "Your task is to acquire data from cameras and emotion recognition sensors installed at intersections during the day, and design an algorithm that will optimally change traffic signals based on traffic volume and user emotions."

[1193] "Draw a flowchart of a system that analyzes the number of vehicles and pedestrians at an intersection and their emotions in real time to achieve efficient traffic light control."

[1194] In this way, the present invention automates traffic signal control at intersections and enables flexible signal changes according to traffic volume and user emotions, thereby optimizing traffic flow.

[1195] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1196] Program processing flow

[1197] Step 1: Acquiring camera footage and emotion data

[1198] Input: Real-time data requests from cameras and emotion recognition sensors

[1199] process:

[1200] The server sends an HTTP GET request to the camera and emotion recognition sensor every 5 seconds to obtain the latest video data and emotion data. The camera sends images in JPEG format, and the emotion recognition sensor sends emotion data in JSON format to the server. These data are temporarily stored in memory.

[1201] Output: JPEG video data and JSON format emotion data

[1202] Step 2: Video and emotion analysis

[1203] Input: JPEG video data and JSON emotion data obtained in step 1

[1204] process:

[1205] The server inputs the video data into the YOLOv5 model for object detection. This model identifies vehicles and pedestrians in the video and obtains their coordinate data (x, y, w, h). At the same time, emotion data is input into an emotion engine (e.g., Microsoft Azure Emotion API) to extract emotion categories such as "joy," "anger," and "sadness." The location, direction of movement, and speed of each detected vehicle or pedestrian, as well as the user's emotion information, are recorded in a list.

[1206] Output: A list of analyzed vehicle and pedestrian locations and emotion categories

[1207] Step 3: Assess traffic and sentiment

[1208] Input: Analysis result list created in step 2

[1209] process:

[1210] The server counts the traffic volume within a certain period of time based on the vehicle and pedestrian data in the list. It also analyzes the user's emotional data and evaluates whether a specific emotional state (e.g., impatience, anger) is detected. If the traffic volume falls below a set threshold or the user's emotional state is in a specific state, the server proceeds to the next step. Specifically, the server aggregates the traffic volume every minute and compares it with a threshold (e.g., 10 vehicles or less) and the emotional state.

[1211] Output: Traffic volume and emotion evaluation results (number of passing vehicles and pedestrians, emotional state)

[1212] Step 4: Modifying the Signal

[1213] Input: Traffic volume and emotion evaluation results obtained in Step 3

[1214] process:

[1215] The server changes the traffic light when it determines that the traffic volume is below a certain threshold or that the user's emotions are in a specific state. The server sends a command to the traffic light controller to change the light from red to green or from green to red using a POST request via the REST API. The traffic light controller receives this command and changes the light.

[1216] Output: Changed signal indication

[1217] Step 5: Check and log the signal status

[1218] Input: Signal change command sent in step 4 and response from the signal controller

[1219] process:

[1220] After the signal has changed, the server again sends a GET request to the signal control device to check its status. If the signal has changed correctly, the result is recorded in a log file. The log includes the time of the signal change, the type of change (red to green, green to red), and the reason for the change (traffic volume evaluation results and user emotion). Specifically, the server sends a reconfirmation request to the signal control device after 5 seconds, recording "Change time: 14:35, Change type: red to green, Reason: Frequent occurrence of pedestrian impatience."

[1221] Output: Recorded log data

[1222] (Application example 2)

[1223] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1224] Conventional traffic signal control systems control signals based solely on traffic volume, without taking into account the emotional state of pedestrians and passengers. As a result, they are unable to respond appropriately in emergencies or when users are feeling anxious or stressed, posing challenges to optimizing traffic flow and improving safety.

[1225] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring video of the intersection in real time, means for analyzing the acquired video to detect passing vehicles and pedestrians, emotion recognition means for recognizing the emotional state of the user, means for changing the traffic light when it is determined that the traffic volume and the emotional state of the user are below a predetermined threshold, means for confirming the traffic light status after the change, and means for displaying the traffic light status after the change, including the reason for the change. This enables flexible traffic light changes according to the emotional state of the user, thereby improving traffic safety and efficiency at intersections.

[1226] "Real-time" means that images of the intersection are captured immediately on the spot and processed without delay.

[1227] "Video analysis" is the process of using acquired video data to detect and identify specific information (such as passing vehicles or pedestrians).

[1228] "Traffic volume" refers to the number or volume of vehicles and pedestrians passing through a particular traffic point.

[1229] "User's emotional state" is information that represents the emotions that the user is feeling (for example, joy, anger, impatience, sadness, etc.).

[1230] "Emotion recognition means" refers to a technology or device for determining emotions from the user's facial expressions, actions, etc., and acquiring that information.

[1231] The "means for changing a traffic light" refers to a means for sending a command to a traffic light control device to change the color of the traffic light (such as from red to green or from green to red).

[1232] "Changed signal state" refers to the state of the signal after it has changed (e.g., the signal has turned green or red).

[1233] The "means for displaying the changed signal status including the reason for the change" is a means for showing on a display device the reason why the signal has been changed and the new status of the signal.

[1234] "Log" refers to data that maintains records of system operations and results.

[1235] The system of the present invention is a real-time traffic light control system for enabling autonomous vehicles to pass through intersections efficiently and safely. The system includes a server, cameras installed at intersections, emotion recognition sensors, a traffic light control device, and smart glasses installed in the vehicle.

[1236] The server collects real-time data from cameras and emotion recognition sensors installed at intersections. The cameras use a video analysis module to detect moving vehicles and pedestrians in the video. The emotion recognition sensors analyze the user's facial expressions and movements to obtain emotional data.

[1237] The server performs calculations to determine traffic volume based on the acquired data. It uses a video analysis module and emotion engine with deep learning models to detect and record the number, location, direction, and speed of passing vehicles and pedestrians. It also analyzes the user's emotional state, and if it recognizes certain emotions such as impatience or anger, it makes a decision to respond accordingly.

[1238] If the server determines that the traffic volume and the user's emotional state are below a predetermined threshold, it sends a signal change command to the signal controller. The signal controller changes the signal in accordance with the command, including changing the signal from red to green or vice versa. The changed signal status and the reason for the change are displayed on the smart glasses in real time.

[1239] The changed signal status is recorded in a log, and details such as the reason for the change, the timing, and the type of signal are saved, optimizing traffic flow and improving safety.

[1240] Hardware and software used

[1241] 1. Camera:

[1242] It captures real-time video and uses it in the video analysis module to detect vehicles and pedestrians.

[1243] 2. Emotion Recognition Sensor:

[1244] It recognizes the user's emotional state and transmits that data to a server.

[1245] 3. Signal Control Device:

[1246] The signal is changed based on instructions from the server.

[1247] 4. Smart Glasses:

[1248] The status and reasons for signal changes are displayed in real time so that drivers and passengers can check them.

[1249] 5. Server:

[1250] A video analysis module and emotion engine are used to process the data and send commands to the traffic light controller.

[1251] Specific examples

[1252] For example, if a driver feels extremely anxious when approaching an intersection, the system will detect this emotion through emotion recognition sensors and promptly change the intersection's traffic light from red to green, allowing the vehicle to pass through the intersection smoothly, thereby improving traffic safety and traffic flow.

[1253] Prompt Sentence Examples

[1254] "If the user is impatient, please show how to instruct the intersection signal system to change the signal."

[1255] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1256] Step 1:

[1257] The server receives real-time data from cameras and emotion recognition sensors installed at intersections. The input is the camera footage and data from the emotion recognition sensors, and the output is that these data are temporarily stored in memory. Specifically, the server periodically sends requests to the cameras and sensors to receive video data and emotion data.

[1258] Step 2:

[1259] The server analyzes the acquired video data and emotion data. The input is the video data and emotion data acquired in step 1, and the output is information about detected vehicles and pedestrians, as well as the user's emotion data. The server uses a video analysis module that utilizes a deep learning model to identify vehicles and pedestrians in the video, and an emotion engine to identify emotions from the user's facial expressions and behavior. Specifically, the video analysis module calculates the position, direction of movement, and speed of vehicles and pedestrians, and the emotion engine classifies the user's emotional state.

[1260] Step 3:

[1261] The server evaluates the current traffic volume and the user's emotional state based on the detection result list. The input is the detection result from step 2, and the output is the evaluation results of the traffic volume and emotional state. Specifically, the server compares the traffic volume and the user's emotional state with a predetermined threshold and determines whether the traffic volume is below the threshold or whether the user's emotional state is in a specific state (e.g., impatience, anger).

[1262] Step 4:

[1263] If the server determines that the traffic volume is below a predetermined threshold or that the user's emotions are in a specific state, it sends a signal change command to the traffic light controller. The input is the evaluation result of step 3, and the output is the command sent to the traffic light controller. Specifically, the server checks the current traffic light status and sends an instruction to change the light from red to green, or vice versa, as necessary.

[1264] Step 5:

[1265] The server checks whether the signal change was successful. The input is the response from the signal controller, and the output is the result of the signal change. Specifically, the server sends a status request to the signal controller again to check whether the signal has been changed to the correct state.

[1266] Step 6:

[1267] The server records the changed signal status and the reason for the change in a log and displays it on the smart glasses in real time. The input is the signal change result in step 5 and the evaluation result in step 3, and the output is a log file and display information on the smart glasses. Specifically, the log records the time of the signal change, the type of change, and the reason for the change, and the smart glasses display the current signal status and the reason for the change.

[1268] The above are the processing steps of the system that realizes the application example.

[1269] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1270] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1271] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1272] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1273] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1274] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1275] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1276] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1277] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1278] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1279] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1280] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1281] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1282] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1283] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1284] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1285] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1286] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1287] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1288] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1289] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1290] The following is further disclosed regarding the above embodiment.

[1291] (Claim 1)

[1292] A means for acquiring images of the intersection in real time;

[1293] A means for analyzing the acquired video to detect passing vehicles and pedestrians;

[1294] means for determining traffic volume based on the detection result;

[1295] means for changing the traffic signal when it is determined that the traffic volume is equal to or less than a predetermined threshold;

[1296] a means for checking the signal status after the change;

[1297] A system including:

[1298] (Claim 2)

[1299] 10. The system of claim 1, further comprising means for obtaining a current state of the signal.

[1300] (Claim 3)

[1301] 10. The system of claim 1, further comprising: means for logging the changed signal state.

[1302] "Example 1"

[1303] (Claim 1)

[1304] A means of acquiring real-time images from cameras at intersections;

[1305] A means for temporarily storing the acquired video in memory;

[1306] A means for analyzing the stored video to detect passing vehicles and pedestrians;

[1307] a means for recording the location, direction of movement, and speed of detected vehicles and pedestrians in a list;

[1308] means for determining traffic volume based on the detection result;

[1309] means for changing the traffic signal when it is determined that the traffic volume is equal to or less than a predetermined threshold;

[1310] A means for reacquiring and checking the signal state after the change;

[1311] a means of logging the results of the changes;

[1312] A system including:

[1313] (Claim 2)

[1314] 10. The system of claim 1, further comprising means for obtaining a current state of the signal.

[1315] (Claim 3)

[1316] 10. The system of claim 1, further comprising: means for logging the changed signal state.

[1317] "Application Example 1"

[1318] (Claim 1)

[1319] A means for acquiring images of the intersection in real time;

[1320] A means for analyzing the acquired video to detect passing vehicles and pedestrians;

[1321] means for determining traffic volume based on the detection result;

[1322] means for changing the traffic signal when it is determined that the traffic volume is equal to or less than a predetermined threshold;

[1323] a means for checking the signal status after the change;

[1324] means for providing signal information to an automated vehicle;

[1325] a means for optimizing a route for the automated vehicle based on the traffic light information;

[1326] A system including:

[1327] (Claim 2)

[1328] 10. The system of claim 1, further comprising means for obtaining a current state of the signal.

[1329] (Claim 3)

[1330] 10. The system of claim 1, further comprising: means for logging the changed signal state.

[1331] "Example 2: Combining Emotion Engines"

[1332] (Claim 1)

[1333] A means of obtaining intersection data in real time;

[1334] A means for analyzing the acquired data to detect vehicles and pedestrians;

[1335] means for analyzing and identifying user emotions;

[1336] means for determining traffic volume and emotional state based on the detection results and emotion analysis results;

[1337] means for changing a traffic signal when it is determined that the traffic volume is equal to or less than a predetermined threshold or that the user's emotion is in a specific state;

[1338] a means for checking the signal status after the change;

[1339] A system including:

[1340] (Claim 2)

[1341] 10. The system of claim 1, further comprising means for obtaining a current state of the signal.

[1342] (Claim 3)

[1343] 10. The system of claim 1, further comprising means for logging the changed signal state and the reason for the change.

[1344] "Application example 2 when combining emotion engines"

[1345] (Claim 1)

[1346] A means for acquiring images of the intersection in real time;

[1347] A means for analyzing the acquired video to detect passing vehicles and pedestrians;

[1348] means for determining traffic volume based on the detection result;

[1349] emotion recognition means for recognizing an emotional state of a user;

[1350] means for changing the traffic signal when it is determined that the traffic volume and the emotional state of the user are below a predetermined threshold;

[1351] a means for checking the signal status after the change;

[1352] means for displaying the changed signal status including the reason for the change;

[1353] A system including:

[1354] (Claim 2)

[1355] 10. The system of claim 1, further comprising means for obtaining a current state of the signal.

[1356] (Claim 3)

[1357] 10. The system of claim 1, further comprising: means for logging the changed signal state. [Explanation of symbols]

[1358] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring images of the intersection in real time; A means for analyzing the acquired video to detect passing vehicles and pedestrians; means for determining traffic volume based on the detection result; means for changing the traffic signal when it is determined that the traffic volume is equal to or less than a predetermined threshold; a means for checking the signal status after the change; A system including:

2. 10. The system of claim 1, further comprising means for obtaining a current state of the signal.

3. 10. The system of claim 1, further comprising means for logging changed signal conditions.

Images