Traffic light state generation method and device, equipment and storage medium

Abstract

The invention discloses a traffic light state generation method and device, equipment and a storage medium, and relates to the field of vehicle-mounted technology, and the method comprises the steps: obtaining vehicle driving navigation data, determining traffic light information according to the vehicle driving information in the vehicle driving navigation data, or determining the traffic light information according to the position information in the vehicle driving navigation data, and uploading the vehicle driving navigation data and the traffic light information to a cloud platform. The cloud platform receives vehicle driving navigation data and traffic light information sent by a vehicle, obtains intersection identification information and acquisition time information according to the vehicle driving navigation data, determines traffic light state data according to the traffic light information, the intersection identification information and the acquisition time information, and sends the traffic light state data to the cloud platform according to the traffic light state data and the intersection identification information. And obtaining a traffic light state result. The traffic light state is identified based on navigation and image data and uploaded to the cloud for analysis and processing to generate accurate time-sharing state information, so that the accuracy and efficiency of the traffic light state are improved.

Description

Technical Field

[0001] The present invention relates to the field of vehicle-mounted technology, and in particular to a method, device, equipment and storage medium for generating a traffic light state. Background Art

[0002] With the continuous improvement of the domestic economic level, the speed of urban development is accelerating, the information of roads and traffic participants is becoming more and more complex, and the difficulty of vehicle route planning is also increasing. At the same time, the rapid development of the intelligence of new energy vehicles enables smart cars to obtain or identify traffic light information in a timely manner through on-board equipment and optimize vehicle travel routes. The development goal of the intelligent transportation system is to make traffic light status information more accurate, realize the accurate identification and acquisition of traffic light information on all roads, and thus optimize vehicle traffic efficiency.

[0003] Currently, the market uses signal light detection devices to obtain traffic light information at the intersection in real time and send the traffic light information to a cloud server; the cloud server is connected to the signal light detection device through a wired network or a wireless network, which is used to receive and store the traffic light signal information sent by the signal light detection device and update the traffic light signal status of the entire network.

[0004] The existing method of obtaining traffic light status requires the intersection to support data upload to the cloud and the intersection to be upgraded, which leads to high costs and a long period of full coverage. In addition, when there is congestion near the intersection or vehicles are driving slowly, it is impossible to accurately obtain the duration information of the traffic light, resulting in a decrease in the accuracy of the traffic light status. Therefore, a more accurate and efficient method for generating traffic light status is urgently needed. Summary of the invention

[0005] The main purpose of this application is to provide a traffic light status generation method, device, equipment and storage medium, aiming to solve the technical problem of how to improve the accuracy and efficiency of obtaining traffic light status.

[0006] To achieve the above-mentioned purpose, the present application proposes a method for generating a traffic light state, which is applied to a vehicle and comprises:

[0007] Obtain vehicle driving navigation data;

[0008] Determine traffic light information according to the vehicle driving information in the vehicle driving navigation data;

[0009] or,

[0010] Determine traffic light information according to the position information in the vehicle driving navigation data;

[0011] The vehicle driving navigation data and the traffic light information are uploaded to the cloud platform.

[0012] In one embodiment, the step of determining traffic light information according to the position information in the vehicle driving navigation data includes:

[0013] According to the location information of the vehicle driving navigation data, the distance between the vehicle and the front intersection, the driving direction, and the intersection ID are obtained;

[0014] When the distance between the vehicle and the front intersection does not exceed a preset distance, acquiring image data;

[0015] Traffic light information is obtained according to the image data combined with the driving direction and the intersection ID through a preset perception model.

[0016] In one embodiment, the step of determining traffic light information according to the vehicle driving information in the vehicle driving navigation data includes:

[0017] Obtaining a vehicle speed and a time for maintaining the vehicle speed according to the vehicle driving information in the vehicle driving navigation data;

[0018] When the vehicle speed is less than a preset speed threshold and the time for maintaining the vehicle speed exceeds a second preset time, the traffic light information is determined to be red; otherwise, the traffic light information is determined to be green.

[0019] In one embodiment, the step of uploading the vehicle driving navigation data and the traffic light information to a cloud platform includes:

[0020] Storing the vehicle driving navigation data and the traffic light information in corresponding date folders, wherein the date folders are divided according to system dates;

[0021] When the vehicle driving navigation data meets a preset condition, the date folder is stored in the vehicle preset path and compressed to obtain a vehicle data compression package, wherein the preset condition is that the vehicle gear is in the P gear for more than a first preset time or the distance between the vehicle and the previous intersection exceeds a preset distance;

[0022] The vehicle data compression package is uploaded to the cloud platform, so that the cloud platform decompresses and calculates the vehicle data compression package to obtain the traffic light status result.

[0023] In addition, the present application also proposes a traffic light status generation method, characterized in that the method is applied to a cloud platform, and the method includes:

[0024] Receive vehicle driving navigation data and traffic light information sent by the vehicle;

[0025] Obtaining intersection identification information and collection time information according to the vehicle driving navigation data;

[0026] Determine traffic light status data according to the traffic light information, intersection identification information and collection time information;

[0027] A traffic light status result is obtained according to the traffic light status data and the intersection identification information.

[0028] In one embodiment, determining the traffic light status data according to the traffic light information, the intersection identification information and the collection time information includes:

[0029] Filter the traffic light information according to the intersection identification information to obtain data of the same driving direction;

[0030] The data of the same driving direction are sorted according to the collection time information to obtain traffic light status data, wherein the traffic light status data includes red light status data, yellow light status data, and green light traffic data;

[0031] The obtaining of a traffic light status result according to the traffic light status data and the intersection identification information includes:

[0032] Determine a driving intersection according to the intersection identification information;

[0033] The traffic light state data is calculated by weighted average to obtain the traffic light state data at the time of passing the driving intersection;

[0034] The traffic light state data at the time of passing the driving intersection is filtered using a time series smoothing strategy to obtain filtered data;

[0035] A traffic light status result is obtained according to the filtered data.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a traffic light state generating device, the traffic light state generating device comprising:

[0037] An acquisition module is used to acquire vehicle driving navigation data;

[0038] an identification module, configured to determine traffic light information based on vehicle driving information in the vehicle driving navigation data; or, to determine traffic light information based on position information in the vehicle driving navigation data;

[0039] The uploading module is used to upload the vehicle driving navigation data and the traffic light information to the cloud platform.

[0040] In addition, the present application also proposes a traffic light state generating device, the traffic light state generating device comprising:

[0041] A receiving module, used for receiving vehicle driving navigation data and traffic light information sent by the vehicle;

[0042] A parsing module, used to obtain intersection identification information and collection time information according to the vehicle driving navigation data;

[0043] The parsing module is further used to determine the traffic light status data according to the traffic light information, the intersection identification information and the collection time information;

[0044] The result module is used to obtain the traffic light status result according to the traffic light status data and the intersection identification information.

[0045] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable medium, and a computer program is stored on the medium. When the computer program is executed by a processor, the steps of the traffic light status generation method described above are implemented.

[0046] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the traffic light state generation method as described above are implemented.

[0047] This application obtains vehicle driving navigation data, determines traffic light information based on vehicle driving information in the vehicle driving navigation data, or determines traffic light information based on location information in the vehicle driving navigation data, and uploads the vehicle driving navigation data and the traffic light information to the cloud platform. The cloud platform receives the vehicle driving navigation data and traffic light information sent by the vehicle, obtains the intersection identification information and the collection time information based on the vehicle driving navigation data, determines the traffic light status data based on the traffic light information, the intersection identification information and the collection time information; and obtains the traffic light status result based on the traffic light status data and the intersection identification information. The traffic light status is identified based on navigation and image data, and uploaded to the cloud for analysis and processing to generate accurate time-sharing status information, thereby improving the accuracy and efficiency of the traffic light status, optimizing the path planning, and enhancing the driving efficiency and comfort. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0049] Figure 1 A schematic diagram of the flow chart of the first embodiment of the method for generating the state of a traffic light of the present application;

[0050] Figure 2 A flow chart of a second embodiment of the method for generating a traffic light state of the present application;

[0051] Figure 3 A schematic diagram of the module structure of a traffic light state generating device according to the first embodiment of the traffic light state generating method of the present application;

[0052] Figure 4 A schematic diagram of the module structure of a traffic light state generating device according to a second embodiment of the traffic light state generating method of the present application;

[0053] Figure 5 A schematic diagram of the device structure of the hardware operating environment involved in the traffic light state generation method in the embodiment of the present application;

[0054] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0056] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0057] The main solution of the embodiment of the present application is: obtaining vehicle driving navigation data, obtaining traffic light recognition results based on the vehicle driving navigation data, and uploading the traffic light recognition results to the cloud platform. The cloud platform receives the traffic light recognition results sent by the vehicle, obtains traffic light recognition information based on the traffic light recognition results, and obtains the traffic light status results based on the traffic light recognition information.

[0058] Based on this, the embodiment of the present application provides a method for generating a traffic light state, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for generating the status of a traffic light of the present application.

[0059] In this embodiment, the traffic light status generation method includes steps S101 to S103:

[0060] Step S101, obtaining vehicle driving navigation data.

[0061] It should be noted that obtaining vehicle driving navigation data is one of the key steps in realizing the method of generating the time-sharing state of traffic lights. This process involves the coordinated work of multiple sensors and vehicle-mounted systems to ensure the accuracy and real-time nature of the data. First, the vehicle's current position is located by the vehicle-mounted navigation system (such as GPS), and the distance and driving direction of the vehicle from the intersection ahead are determined in combination with the high-precision map (SD map). In addition, the speed information provided by the vehicle speed sensor and the image data captured by the camera are also taken into consideration. These data together constitute the comprehensive driving status of the vehicle at a specific point in time. In order to improve the data quality, preliminary data preprocessing is performed at the acquisition stage. This includes validating the validity of the timestamp to prevent data anomalies caused by system time errors; at the same time, filtering abnormal data such as speed values ​​that exceed a reasonable range to ensure that only information that meets the expected standards will be further analyzed and used. When the vehicle approaches a pre-set identification area (for example, within 60 meters from the intersection), the system will collect relevant information more intensively to more accurately determine the current state of the traffic light.

[0062] Step S102, determining traffic light information according to the vehicle driving information in the vehicle driving navigation data, or determining traffic light information according to the position information in the vehicle driving navigation data.

[0063] It should be noted that this process mainly relies on high-precision map data, real-time positioning information and the support of intelligent algorithms.

[0064] Furthermore, step S102 also includes: obtaining the distance between the vehicle and the intersection ahead, the driving direction, and the intersection ID according to the vehicle driving navigation data. First, through the location information provided by the vehicle navigation system, combined with the preset intersection ID and traffic light layout information in the SD map, it is possible to accurately determine which intersection the vehicle is about to approach, and determine the specific configuration of the intersection. Furthermore, when the distance between the vehicle and the intersection ahead does not exceed the preset distance, image data is acquired. In this embodiment, when the vehicle enters the recognition area within 60 meters of the intersection ahead, the system activates visual sensors such as cameras to collect images of the traffic lights ahead. Furthermore, according to the image data combined with the driving direction and the intersection ID, a traffic light recognition result is obtained through a preset perception model. At this time, the image data is analyzed and processed using a pre-trained deep learning model or computer vision technology to automatically identify the color state (red, yellow, green) of the current traffic light.

[0065] At the same time, in order to improve recognition accuracy and robustness, the solution also considers how to effectively supplement missing information when the field of vision is obstructed. Furthermore, when the vehicle cannot obtain image data, the vehicle speed is obtained. For example, if the signal light status cannot be directly read from the image due to factors such as occlusion by the front vehicle, indirect inference is made based on the trend of vehicle speed changes. When the vehicle speed is less than the preset speed threshold and the time for maintaining the vehicle speed exceeds the second preset time, the traffic light information is determined to be red; otherwise, the traffic light information is determined to be green.

[0066] In this embodiment, when the vehicle speed is less than a preset speed threshold (such as 3m / s) and the time of maintaining this low speed state exceeds a second preset time (such as 1 second), the system will determine that the traffic light at the intersection ahead is red. This judgment is based on an assumption that if the vehicle continues to crawl at an almost stationary speed when approaching the intersection, it is likely that the red light ahead is counting down, or the red light ahead is very short. At this time, in order to indicate that the recognition result has a certain degree of uncertainty, the result confidence will be set to a preset value (such as 0.5). Such a design helps to provide a reasonable speculation when the camera is blocked or the image recognition is inaccurate. On the contrary, it will be considered as an acceleration behavior caused by the green light. In this case, the system will determine that the traffic light at the intersection ahead is green, and also set the result confidence to the same preset value (0.5). This method indirectly infers the color of the traffic light by analyzing the change pattern of the vehicle speed, which is particularly suitable for scenes where it is difficult to directly observe the traffic light, such as following behind a large truck or encountering bad weather conditions.

[0067] It should be understood that the confidence levels in both cases are relatively low, indicating that these conclusions are not absolutely reliable, but rather are high-probability guesses based on specific logical reasoning. Therefore, in actual applications, once the camera has restored its effective field of view of the traffic light and provided a high-confidence recognition result, the information provided by the visual data should be used first. At the same time, considering the complexity and variability of reality, the solution also reserves space for adjusting the preset speed threshold and time window size so that it can be optimized according to the specific conditions of different urban road environments, thereby improving the adaptability and accuracy of the overall system. In addition, as more data contributed by vehicles continue to accumulate, the cloud processing module can further correct and improve the information reported by individual vehicles through big data analysis, ultimately forming a more comprehensive and accurate global traffic light status map.

[0068] Step S103, uploading the vehicle driving navigation data and traffic light information to the cloud platform.

[0069] It should be noted that uploading the traffic light recognition results to the cloud platform is an important step in the entire traffic light time-sharing state generation method based on crowd-source data. It ensures that the information collected from a single vehicle can be centrally processed and analyzed, thereby forming a global and high-precision traffic light state map.

[0070] It should be noted that step S103 also includes: obtaining a data packet according to the traffic light recognition result, the data packet includes time, intersection ID, driving direction, traffic light status and confidence, and then storing the data packet in the preset path of the vehicle and uploading it to the cloud platform. Specifically, the data packet generated according to the traffic light recognition result is the key information carrier in the entire traffic light time-sharing state generation method based on crowd-source data. Each data packet contains five core elements: timestamp (recording the specific time of data collection), intersection ID (unique identifier in SD map, used to accurately locate the specific intersection), driving direction (the direction of the vehicle when approaching the intersection, such as straight, left turn or U-turn), traffic light status (the current recognized signal light color, i.e. red, yellow, green) and confidence (a numerical value reflecting the reliability of the recognition result). Together, this information constitutes a comprehensive description of the traffic light status at a specific moment. Once the traffic light status is successfully identified and assigned a corresponding confidence value, the system will package these data in a preset format and store them in a folder under the specified path of the vehicle. Subsequently, when specific upload conditions are met, the system will check whether there is a compressed data package to be uploaded. If it exists, the upload process is started, and the breakpoint resume mechanism is used to ensure that data transmission can be completed smoothly even when the network is unstable.

[0071] Furthermore, step S103 also includes: storing the vehicle navigation data and traffic light information in the corresponding date folder, and the date folder is divided according to the system date. Specifically, once the traffic light status is successfully identified and assigned a corresponding confidence value, the system will package these data in a preset format and store them in the TrafficLight folder under the specified path on the vehicle side. For ease of management and subsequent processing, the data packets will be further organized into a subdirectory structure based on date and week. For example, daily data will be archived in a file with a naming rule of year, month, day and hour; when the file size reaches a certain threshold (such as 6,000 data packets), a new file will be automatically created to continue storing new data.

[0072] Furthermore, when the vehicle driving navigation data meets the preset conditions, the date folder is stored in the vehicle preset path and compressed to obtain a vehicle data compression package. The preset conditions are that the vehicle gear is in P gear for more than a first preset time or the distance of the vehicle from the previous intersection exceeds a preset distance. Specifically, when the vehicle driving navigation data meets a specific preset condition, the system automatically compresses the traffic light recognition result stored in the date folder and generates a vehicle data compression package. These preset conditions include two situations: one is that the vehicle gear is switched to P gear (parking gear) and the duration exceeds the first preset time (for example, 1 minute), which usually means that the vehicle has stopped and the driver may temporarily leave the vehicle or prepare to park for a long time; the other is that the distance between the vehicle and the last recorded intersection exceeds the preset distance threshold (such as 5 kilometers), which indicates that the vehicle has moved away from the previous detection area and entered a new section. When these two situations are met, the vehicle system will trigger a check mechanism to first confirm whether there is a data folder for the day. If it exists, all traffic light recognition data in the folder (that is, data packets containing information such as timestamp, intersection ID, driving direction, traffic light status and confidence) are packaged into a compressed file. This not only reduces the bandwidth and time required for uploading, but also facilitates decompression and processing after receiving in the cloud. At the same time, in order to ensure the security and integrity of the data, encryption and checksum functions can be added during the compression process to ensure that even if problems such as packet loss occur during network transmission, they can be discovered and remedial measures can be taken in a timely manner. After the compression is completed, the system will immediately start the upload process and send the compressed package to the cloud platform for further analysis and utilization.

[0073] Furthermore, the compressed vehicle data package is uploaded to the cloud platform so that the cloud platform can decompress and calculate the compressed vehicle data package to obtain the traffic light status result. First, the system checks whether there is a compressed data package to be uploaded; if so, the compressed package is sent to the cloud platform through the network connection. On the cloud platform, the received compressed vehicle data package is decompressed and stored in the specified path and classified by date. Next, the cloud platform processing software performs a series of complex calculations and analyses on these raw data.

[0074] This embodiment provides a method for generating a traffic light status, which obtains vehicle driving navigation data, determines traffic light information according to vehicle driving information in the vehicle driving navigation data, or determines traffic light information according to location information in the vehicle driving navigation data, and uploads the vehicle driving navigation data and the traffic light information to a cloud platform. The cloud platform receives the vehicle driving navigation data and traffic light information sent by the vehicle, obtains intersection identification information and collection time information according to the vehicle driving navigation data, determines traffic light status data according to traffic light information, intersection identification information and collection time information; and obtains traffic light status results according to traffic light status data and intersection identification information. The traffic light status is identified based on navigation and image data, and uploaded to the cloud for analysis and processing to generate accurate time-sharing status information, thereby improving the accuracy and efficiency of traffic light status, optimizing path planning, and enhancing driving efficiency and comfort.

[0075] Based on the above, the embodiment of the present application also provides a method for generating a traffic light state, referring to Figure 2 , Figure 2 This is a flow chart of a second embodiment of the method for generating a traffic light status of the present application.

[0076] In this embodiment, the traffic light status generation method includes steps S201 to S204:

[0077] Step S201, receiving vehicle driving navigation data and traffic light information sent by a vehicle.

[0078] It should be noted that when the vehicle meets the preset conditions (for example, the gear is in P gear for more than 1 minute or the distance to the previous intersection is more than 5 kilometers) and uploads a compressed package of traffic identification results, the cloud platform receives the data packet and then decompresses and calculates it.

[0079] Step S202, obtaining intersection identification information and collection time information according to the vehicle driving navigation data.

[0080] It is important to understand that the process by which the cloud platform generates traffic light identification information based on the traffic light identification results uploaded by the vehicle involves multiple key steps to ensure the accuracy and practicality of the data. First, the cloud will decompress the received data compression package and classify and store the decompressed data in date and time order. Subsequently, the system will parse the raw data and extract key information from each data packet, including timestamp, intersection ID, driving direction, traffic light status, and confidence level. In order to ensure data quality, the cloud will also verify the validity of this information and eliminate abnormal or erroneous data points.

[0081] Step S203, determining traffic light status data according to traffic light information, intersection sign information and collection time information.

[0082] It should be noted that based on the traffic light identification information, the cloud platform goes through a series of data processing and analysis steps to ultimately generate accurate traffic light status results.

[0083] Furthermore, step S203 also includes: filtering the traffic light information according to the intersection identification information to obtain data of the same driving direction. The cloud platform extracts the intersection ID and driving direction information of each data point from the received traffic light identification results. This information is crucial for subsequent data processing because the status of traffic lights in different driving directions may be different. Next, the system will classify the data according to the intersection ID and further filter out the data with the same driving direction. For example, for a specific intersection, the system will process the data of straight, left turn and U-turn directions separately. This can avoid the data of different directions from being mixed together, resulting in inaccurate analysis results. After filtering out the data of the same driving direction, the system will sort the data in chronological order. In this way, a continuous time series can be constructed to facilitate subsequent statistical analysis and state calculation. Through this orderly arrangement, the system can more accurately capture the changing trend of the traffic light state, thereby generating more reliable traffic light state information.

[0084] Furthermore, the data of the same driving direction are sorted according to the collection time information to obtain traffic light status data, which includes red light status data, yellow light status data, and green light traffic data. Specifically, the cloud platform will classify and store the received traffic light identification information according to the intersection ID and time sequence. Next, the system will summarize and process these data. Specifically, for each specific intersection ID, the cloud software will filter out data with a unified driving direction (such as straight, left turn or U-turn) and sort them in chronological order. This ensures that when analyzing traffic flow in a certain direction, the data set used is consistent and orderly. After completing the data screening and sorting, the system will count the red light status data, yellow light status data, and green light status data respectively. Each status data contains the color of the traffic light in the corresponding time period and the corresponding confidence information.

[0085] Step S204, obtaining a traffic light status result according to the traffic light status data and the intersection identification information.

[0086] Furthermore, step S203 also includes: determining the driving intersection according to the intersection identification information, calculating the traffic light status data by weighted average, and obtaining the traffic light status data at the time of passing the driving intersection. Specifically, in the summarized traffic light identification information, each data point contains a timestamp, intersection ID, driving direction, and traffic light status (red, yellow, green) and its confidence. In order to obtain the traffic light status data at the current moment, the system will perform a weighted average calculation on the status reported by different vehicles according to these confidence values. Specifically, for each specific time point, the cloud software will collect the traffic light status and corresponding confidence reported by all relevant vehicles at the same time. The confidence reflects the reliability of the recognition result, and the result with high confidence will be given a greater weight. For example, if a vehicle reports a traffic light status of red with a confidence of 0.8, and another vehicle reports green with a confidence of 0.6, then the red status will be given a higher weight. The specific formula is:

[0087] S=c red *w red *v red +c yellow *w yellow *v yellow +c green *w green *v green

[0088]

[0089] Among them, c represents the confidence, w represents the weight of each state, n represents the number of current state data at the current moment, and n 总 Indicates the number of all data at the current moment, v red , v yellow , v green Indicates red, yellow, and green light data.

[0090] Furthermore, the traffic light status data at the time of passing the intersection is filtered using a time series smoothing strategy to obtain the filtered data; based on the filtered data, the traffic light status result is obtained. In order to further improve the accuracy, the cloud will also apply the sliding window technology to smooth the data to eliminate the fluctuations caused by individual abnormal data. Through this filtering operation, the impact of burr data can be reduced, making the change of traffic light status smoother and more natural. In addition, the cloud will combine historical data with current real-time data, and use machine learning algorithms to continuously optimize the model to improve the accuracy of the prediction. Finally, the traffic light status results after the above processing will be updated to the database to form a comprehensive and real-time updated traffic light status map. This map can not only provide accurate information support for the intelligent traffic management system, but also help the driving assistance system to better plan the route and improve the overall traffic efficiency and safety. Finally, based on the traffic light status map, the final traffic light status result is obtained.

[0091] This embodiment receives vehicle driving navigation data and traffic light information sent by the vehicle, obtains intersection identification information and collection time information according to the vehicle driving navigation data, determines traffic light status data according to the traffic light information, intersection identification information and collection time information, and obtains traffic light status results according to the traffic light status data and the intersection identification information. By receiving the vehicle traffic light recognition result, processing and generating recognition information, and calculating the status result, the accuracy of the traffic light status is improved.

[0092] Based on the first embodiment of the present application, the present application also provides a traffic light state generating device, which is applied to vehicles, please refer to Figure 3 , the device comprises:

[0093] The acquisition module 10 is used to acquire vehicle driving navigation data.

[0094] Identification module 20, for determining traffic light information based on vehicle driving information in vehicle driving navigation data; or, determining traffic light information based on location information in vehicle driving navigation data.

[0095] The uploading module 30 is used to upload the vehicle driving navigation data and traffic light information to the cloud platform.

[0096] The traffic light state generation device provided by the present application adopts the traffic light state generation method in the above embodiment, which can solve the technical problem of how to improve the accuracy and efficiency of obtaining the traffic light state. Compared with the prior art, the beneficial effects of the traffic light state generation device provided by the present application are the same as the beneficial effects of the traffic light state generation method provided by the above embodiment, and other technical features in the traffic light state generation device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0097] In one embodiment, the recognition module 20 is also used to obtain the distance between the vehicle and the intersection ahead, the driving direction, and the intersection ID based on the position information of the vehicle's driving navigation data; when the distance between the vehicle and the intersection ahead does not exceed a preset distance, obtain image data; and obtain traffic light information based on the image data combined with the driving direction and the intersection ID through a preset perception model.

[0098] In one embodiment, the identification module 20 is also used to obtain the vehicle speed and the time to maintain the vehicle speed based on the vehicle driving information in the vehicle driving navigation data; if the vehicle continues to crawl at an almost stationary speed when approaching an intersection, it is likely that the red light ahead is counting down, or the red light ahead is for a very short time.

[0099] In one embodiment, the upload module 30 is also used to store the vehicle driving navigation data and traffic light information in corresponding date folders, and the date folders are divided according to the system date; when the vehicle driving navigation data meets the preset conditions, the date folders are stored in the vehicle preset path and compressed to obtain a vehicle data compression package, and the preset conditions are that the vehicle gear is in P gear for more than a first preset time or the distance between the vehicle and the previous intersection exceeds a preset distance; the vehicle data compression package is uploaded to the cloud platform, so that the cloud platform decompresses and calculates the vehicle data compression package to obtain the traffic light status result.

[0100] Based on the second embodiment of the present application, the present application also provides a traffic light status generating device, which is applied to the cloud platform. Please refer to Figure 4 , the device comprises:

[0101] The receiving module 40 is used to receive vehicle driving navigation data and traffic light information sent by the vehicle.

[0102] The analysis module 50 is used to obtain the intersection identification information and the collection time information according to the vehicle driving navigation data.

[0103] The analysis module 50 is further used to determine the traffic light status data according to the traffic light information, the intersection identification information and the collection time information.

[0104] The result module 60 is used to obtain the traffic light status result according to the traffic light status data and the intersection identification information.

[0105] The traffic light state generation device provided by the present application adopts the traffic light state generation method in the above embodiment, which can solve the technical problem of how to improve the accuracy and efficiency of obtaining the traffic light state. Compared with the prior art, the beneficial effects of the traffic light state generation device provided by the present application are the same as the beneficial effects of the traffic light state generation method provided by the above embodiment, and other technical features in the traffic light state generation device are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0106] In one embodiment, the analysis module 50 is also used to filter the traffic light information according to the intersection sign information to obtain data of the same driving direction; sort the data of the same driving direction according to the collection time information to obtain traffic light status data, and the traffic light status data includes red light status data, yellow light status data, and green light traffic data.

[0107] In one embodiment, the result module 60 is also used to determine the driving intersection based on the intersection identification information; calculate the traffic light status data through weighted average to obtain the traffic light status data at the time of passing the driving intersection; use a time series smoothing strategy to filter the traffic light status data at the time of passing the driving intersection to obtain filtered data; and obtain the traffic light status result based on the filtered data.

[0108] The present application provides a traffic light state generating device, which includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the traffic light state generating method in the above-mentioned embodiment 1.

[0109] Reference below Figure 5 , which shows a schematic diagram of the structure of a traffic light state generating device suitable for implementing the embodiment of the present application. The traffic light state generating device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The traffic light status generating device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0110] like Figure 5As shown, the traffic light state generating device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the traffic light state generating device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the traffic light state generating device to communicate with other devices wirelessly or by wire to exchange data. Although the traffic light state generating device with various systems is shown in the figure, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0111] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0112] The traffic light state generation device provided by the present application adopts the traffic light state generation method in the above embodiment, which can solve the technical problem of how to improve the accuracy and efficiency of obtaining the traffic light state. Compared with the prior art, the beneficial effects of the traffic light state generation device provided by the present application are the same as the beneficial effects of the traffic light state generation method provided by the above embodiment, and the other technical features in the traffic light state generation device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0113] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0114] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0115] The present application provides a computer-readable medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the traffic light state generating method in the above-mentioned embodiment.

[0116] The computer-readable medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0117] The computer readable medium may be included in the traffic light state generating device; or may exist independently without being assembled into the traffic light state generating device.

[0118] The computer-readable medium carries one or more programs. When the one or more programs are executed by the traffic light state generating device, the traffic light state generating device can write computer program codes for performing the operations of the present application in one or more programming languages ​​or a combination thereof. The programming languages ​​include object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0119] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0120] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0121] The readable medium provided by the present application is a computer-readable medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned traffic light state generation method, and can solve the technical problem of how to improve the accuracy and efficiency of obtaining the traffic light state. Compared with the prior art, the beneficial effects of the computer-readable medium provided by the present application are the same as the beneficial effects of the traffic light state generation method provided by the above-mentioned embodiment, and will not be repeated here.

[0122] The present application also provides a computer program product, including a computer program, which implements the steps of the above-mentioned traffic light state generation method when executed by a processor.

[0123] The computer program product provided by the present application can solve the technical problem of how to improve the accuracy and efficiency of obtaining the traffic light status. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the traffic light status generation method provided by the above embodiment, which will not be repeated here.

[0124] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for generating a traffic light state, characterized in that: The method is applied to a vehicle, and the method comprises: Obtain vehicle driving navigation data; Determine traffic light information according to the vehicle driving information in the vehicle driving navigation data; or, Determine traffic light information according to the position information in the vehicle driving navigation data; The vehicle driving navigation data and the traffic light information are uploaded to the cloud platform.

2. The method according to claim 1, wherein the step of determining the traffic light information according to the position information in the vehicle driving navigation data comprises: According to the location information of the vehicle driving navigation data, the distance between the vehicle and the front intersection, the driving direction, and the intersection ID are obtained; When the distance between the vehicle and the front intersection does not exceed a preset distance, acquiring image data; Traffic light information is obtained according to the image data combined with the driving direction and the intersection ID through a preset perception model.

3. The method according to claim 1, characterized in that The step of determining traffic light information according to the vehicle driving information in the vehicle driving navigation data comprises: Obtaining a vehicle speed and a time for maintaining the vehicle speed according to the vehicle driving information in the vehicle driving navigation data; When the vehicle speed is less than a preset speed threshold and the time for maintaining the vehicle speed exceeds a second preset time, the traffic light information is determined to be red; otherwise, the traffic light information is determined to be green.

4. The method according to claim 1, characterized in that The step of uploading the vehicle driving navigation data and the traffic light information to the cloud platform includes: Storing the vehicle driving navigation data and the traffic light information in corresponding date folders, wherein the date folders are divided according to system dates; When the vehicle driving navigation data meets a preset condition, the date folder is stored in the vehicle preset path and compressed to obtain a vehicle data compression package, wherein the preset condition is that the vehicle gear is in the P gear for more than a first preset time or the distance between the vehicle and the previous intersection exceeds a preset distance; The vehicle data compression package is uploaded to the cloud platform, so that the cloud platform decompresses and calculates the vehicle data compression package to obtain the traffic light status result.

5. A method for generating a traffic light state, characterized in that: The method is applied to a cloud platform, and the method includes: Receive vehicle driving navigation data and traffic light information sent by the vehicle; Obtaining intersection identification information and collection time information according to the vehicle driving navigation data; Determine traffic light status data according to the traffic light information, intersection identification information and collection time information; A traffic light status result is obtained according to the traffic light status data and the intersection identification information.

6. The method according to claim 5, characterized in that The determining of the traffic light status data according to the traffic light information, the intersection identification information and the collection time information includes: Filter the traffic light information according to the intersection identification information to obtain data of the same driving direction; The data of the same driving direction are sorted according to the collection time information to obtain traffic light status data, wherein the traffic light status data includes red light status data, yellow light status data, and green light traffic data; The obtaining of a traffic light status result according to the traffic light status data and the intersection identification information includes: Determine a driving intersection according to the intersection identification information; The traffic light state data is calculated by weighted average to obtain the traffic light state data at the time of passing the driving intersection; The traffic light state data at the time of passing the driving intersection is filtered using a time series smoothing strategy to obtain filtered data; A traffic light status result is obtained according to the filtered data.

7. A traffic light status generating device, characterized in that: The device comprises: An acquisition module is used to acquire vehicle driving navigation data; an identification module, configured to determine traffic light information based on vehicle driving information in the vehicle driving navigation data; or, to determine traffic light information based on position information in the vehicle driving navigation data; The uploading module is used to upload the vehicle driving navigation data and the traffic light information to the cloud platform.

8. A traffic light status generating device, characterized in that: The device comprises: A receiving module, used for receiving vehicle driving navigation data and traffic light information sent by the vehicle; A parsing module, used to obtain intersection identification information and collection time information according to the vehicle driving navigation data; The parsing module is further used to determine the traffic light status data according to the traffic light information, the intersection identification information and the collection time information; The result module is used to obtain the traffic light status result according to the traffic light status data and the intersection identification information.

9. A traffic light status generating device, characterized in that: The device comprises: a memory, a processor and a traffic light state generation program stored in the memory and running on the processor, wherein the traffic light state generation program is configured to implement the steps of the traffic light state generation method according to any one of claims 1 to 4 or 5-6.

10. A storage medium, characterized in that: The storage medium stores a traffic light state generation program, which, when executed by a processor, implements the steps of the traffic light state generation method according to any one of claims 1 to 4 or 5-6.

Images