Information processing system, information processing apparatus, traffic signal control method, and program

Abstract

To allow particular vehicle to smoothly travel at a location where a traffic light is installed.SOLUTION: An information processing system comprises an imaging unit 300, a traffic light 200 for executing a display to control the travel of a vehicle and an information processing device 100. The information processing device 100 determines whether or not the vehicle is an object vehicle on the basis of an image of the vehicle imaged by the imaging unit 300 and controls a display operation of the traffic light 200 on the basis of the determined result.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an information processing system, an information processing apparatus, a traffic signal control method, and a program.

Background Art

[0002] In recent years, a technology for switching the display of a traffic signal based on the traffic volume of vehicles traveling in a lane imaged by an imaging unit has been considered (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the technology as described in Patent Document 1, a method for controlling a traffic signal by the passage of a specific vehicle is not considered. Therefore, there is a problem that a specific vehicle cannot smoothly pass through a place where a traffic signal is installed.

[0005] An object of the present invention is to provide an information processing system, an information processing apparatus, a traffic signal control method, and a program that enable a specific vehicle to smoothly pass through a place where a traffic signal is installed.

Means for Solving the Problems

[0006] The information processing system of the present invention includes an imaging unit, a traffic signal that performs a display for controlling the travel of a vehicle, and an information processing apparatus, wherein the information processing apparatus includes a determination unit that determines whether the vehicle is a target vehicle based on an image of the vehicle imaged by the imaging unit, It has a traffic signal control unit that controls the display operation of the traffic signal based on the result determined by the determination unit.

[0007] In addition, the information processing apparatus of the present invention has a determination unit that determines whether the vehicle is a target vehicle based on an image of the vehicle captured by the imaging unit, and a traffic signal control unit that controls the display operation of a traffic signal that performs a display for controlling the travel of the vehicle based on the result determined by the determination unit.

[0008] In addition, the traffic signal control method of the present invention includes a process of determining whether the vehicle is a target vehicle based on an image of the vehicle captured by the imaging unit, and a process of controlling the display operation of a traffic signal that performs a display for controlling the travel of the vehicle based on the determined result.

[0009] In addition, the program of the present invention is a program for causing a computer to perform a procedure of determining whether the vehicle is a target vehicle based on an image of the vehicle captured by the imaging unit, and a procedure of controlling the display operation of a traffic signal that performs a display for controlling the travel of the vehicle based on the determined result.

Advantages of the Invention

[0010] In the present invention, a specific vehicle can smoothly pass through a location where a traffic signal is installed.

Brief Description of the Drawings

[0011]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Embodiments for Carrying Out the Invention

[0012] Hereinafter, embodiments of the present invention will be described with reference to the drawings. (First Embodiment)

[0013] FIG. 1 is a diagram showing a first embodiment of the information processing system of the present invention. As shown in FIG. 1, the information processing system in this embodiment includes an information processing apparatus 100, a traffic signal 200, and an imaging unit 300. The information processing apparatus 100, the traffic signal 200, and the imaging unit 300 are connected to each other via a communication network 400. The connection between each of the information processing apparatus 100, the traffic signal 200, and the imaging unit 300 and the communication network 400 may be via wireless communication or via wired communication. Also, each of the information processing apparatus 100, the traffic signal 200, and the imaging unit 300 may be directly connected to be communicable with each other. Note that each of the traffic signal 200 and the imaging unit 300 is not limited to one, and may be plural. The number of traffic signals 200 and the number of imaging units 300 may be different from each other, but the traffic signal 200 and the imaging unit 300 are associated with each other.

[0014] The traffic signal 200 performs a display for controlling the travel of vehicles. The traffic signal 200 may include blue and red lamps like a general traffic signal, and may light the blue lamp when permitting vehicles to travel and light the red lamp when prohibiting vehicles from traveling. The traffic signal 200 performs a display based on an instruction signal transmitted from the information processing apparatus 100 via the communication network 400.

[0015] The imaging unit 300 images vehicles traveling on a road. The imaging unit 300 may be a camera that images vehicles traveling on a road at a time interval equal to or less than a preset time interval (for example, a video camera that continuously images). The imaging unit 300 transmits image data indicating the captured image to the information processing apparatus 100 via the communication network 400. The timing at which the imaging unit 300 transmits the image data indicating the captured image to the information processing apparatus 100 is preferably such that the time from when the imaging unit 300 images a vehicle until the image data indicating the image is transmitted to the information processing apparatus 100 is as short as possible.

[0016] FIG. 2 is a diagram showing an example of the installation state of the traffic signal 200 and the imaging unit 300 shown in FIG. 1. In the example shown in FIG. 2, a case where two traffic signals 200-1 and 200-2 and two imaging units 300-1 and 300-2 are installed is shown. Each of the imaging units 300-1 and 300-2 is installed so as to be able to image vehicles traveling in opposite directions on a road with one-way alternating traffic, respectively. For example, as shown in FIG. 2, the imaging unit 300-1 is installed at a position where it can image a target vehicle 500 traveling from the left direction to the right direction in FIG. 2. On the other hand, the imaging unit 300-2 is installed at a position where it can image a general vehicle 600 traveling from the right direction to the left direction in FIG. 2. Each of the traffic signals 200-1 and 200-2 is installed at a position visible to the vehicle to permit or stop (prohibit travel) of the vehicles traveling in opposite directions on a road with one-way alternating traffic. Note that the traffic signal 200 may be installed not only on a road with one-way alternating traffic as shown in FIG. 2 but also at a position where it can display so that one vehicle does not obstruct the travel of the other vehicle at a general intersection. In that case, the imaging unit 300 is installed at a position where it can image the vehicles traveling toward the intersection.

[0017] FIG. 3 is a diagram showing an example of the components included in the information processing apparatus 100 shown in FIG. 1. As shown in FIG. 3, the information processing apparatus 100 shown in FIG. 1 includes a determination unit 110, a traffic signal control unit 120, a feature amount calculation unit 130, a learning model generation unit 140, and a learning model 150. Note that FIG. 3 shows only the main components related to this embodiment among the components included in the information processing apparatus 100 shown in FIG. 1. The learning model generation unit 140 and the learning model 150 may be provided outside the information processing apparatus 100.

[0018] The feature amount calculation unit 130 extracts a feature amount from the image of the vehicle imaged and transmitted by the imaging unit 300. The method for calculating the feature amount performed by the feature amount calculation unit 130 may be a general method for extracting a value obtained by quantifying the target feature from the image, and is not particularly limited. The feature amount calculation unit 130 outputs the calculated (extracted) feature amount to the determination unit 110.

[0019] The learning model generation unit 140 stores in advance the feature amounts of the target vehicle as teacher data, and performs machine learning on the feature amounts of the target vehicle to generate a learning model 150. Here, the target vehicle is a vehicle to be targeted, and in this embodiment, it is a vehicle that travels on the road with priority over other vehicles such as an autonomous driving vehicle. The learning model generation unit 140 is used in the so-called training phase of machine learning.

[0020] The learning model 150 is a learning model generated by the learning model generation unit 140. The learning model 150 outputs vehicle information corresponding to the feature amounts using the teacher data generated by the learning model generation unit 140. The learning model 150 may have, for example, a structure of a neural network in which a plurality of neurons are interconnected. A neuron is an element that performs a predetermined calculation on a plurality of inputs and outputs one value as a calculation result. The learning model 150 is stored in a storage unit (not shown). The learning method in the learning model 150 may use a general method for generating a learning model. FIG. 4 is a diagram showing an example of the input and output of the learning model 150 shown in FIG. 3. As shown in FIG. 4, the learning model 150 shown in FIG. 3 is a learning model that outputs vehicle information indicating whether the vehicle from which the feature amounts are extracted is the target vehicle when the feature amounts are input.

[0021] The determination unit 110 inputs the feature amounts output from the feature amount calculation unit 130 into the learning model 150 that has learned the target vehicle. Then, the determination unit 110 determines whether the vehicle imaged by the imaging unit 300 is the target vehicle by obtaining from the learning model 150 whether the vehicle from which the feature amounts are extracted is the target vehicle.

[0022] The signal control unit 120 controls the display operation of the traffic signal 200 based on the result determined by the determination unit 110. When the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle, the signal control unit 120 controls the traffic signal 200 to perform a display that does not interfere with the driving of vehicles other than the target vehicle. For example, when the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle, the signal control unit 120 causes the display of the traffic signal 200 installed at a position visible from the target vehicle to turn blue, and controls the display of the traffic signal 200 installed at a position visible from a vehicle traveling from a direction that obstructs the driving of the target vehicle to turn red. When controlling the traffic signal 200, the signal control unit 120 transmits a predetermined control signal to the traffic signal 200. This control signal only needs to be a signal whose control content can be recognized between the signal control unit 120 and the traffic signal 200, and is not particularly specified.

[0023] Hereinafter, the information processing method in the information processing system shown in FIG. 1 will be described. FIG. 5 is a flowchart for explaining an example of the information processing method in the information processing system shown in FIG. 1.

[0024] When the imaging unit 300 images the vehicle (step S1), the imaging unit 300 transmits the image data indicating the captured image to the information processing apparatus 100 via the communication network 400. When the image data is transmitted from the imaging unit 300, the feature amount calculation unit 130 calculates (extracts) the feature amount from the image indicated by the transmitted image data (step S2). The feature amount calculation unit 130 outputs the calculated feature amount to the determination unit 110. Then, the determination unit 110 inputs the feature amount output from the feature amount calculation unit 130 to the learning model 150 (step S3). The determination unit 110 determines whether the vehicle information output from the learning model 150 indicates the target vehicle (step S4). When the vehicle information output from the learning model 150 indicates the target vehicle, the traffic signal control unit 120 controls the traffic signal 200 to perform a display such that vehicles other than the target vehicle do not obstruct the travel of the target vehicle (step S5). Specifically, the traffic signal control unit 120 transmits a control signal for controlling the traffic signal 200 to perform a display such that vehicles other than the target vehicle do not obstruct the travel of the target vehicle to the traffic signal 200, and the traffic signal 200 controls the display according to the transmitted control signal.

[0025] As described above, in this embodiment, the imaging unit 300 images the traveling vehicle, the information processing apparatus 100 extracts the feature amount from the captured image, and determines whether the vehicle is the target vehicle based on the extracted feature amount. As a result of the determination, if it is the target vehicle, the information processing apparatus 100 controls the display of the traffic signal 200. For example, in the example shown in FIG. 2, when the information processing apparatus 100 determines that the vehicle imaged by the imaging unit 300-1 is the target vehicle 500, the traffic signal 200-1 is caused to display permission to travel, and the traffic signal 200-2 is caused to display prohibition of travel. Thereby, a specific vehicle can smoothly pass through the location where the traffic signal is installed. (Second Embodiment)

[0026] FIG. 6 is a diagram showing a second embodiment of the information processing system of the present invention. As shown in FIG. 6, the information processing system in this embodiment includes an information processing device 101, a traffic signal 200, and an imaging unit 300. The information processing device 101, the traffic signal 200, and the imaging unit 300 are connected to each other via a communication network 400. The connection between each of the information processing device 101, the traffic signal 200, and the imaging unit 300 and the communication network 400 may be via wireless communication or via wired communication. Also, each of the information processing device 101, the traffic signal 200, and the imaging unit 300 may be directly connected to be communicable with each other. Each of the traffic signal 200 and the imaging unit 300 is the same as that in the first embodiment.

[0027] FIG. 7 is a diagram showing an example of components provided in the information processing device 101 shown in FIG. 6. As shown in FIG. 7, the information processing device 101 shown in FIG. 6 includes a determination unit 110, a traffic signal control unit 121, a feature amount calculation unit 130, a learning model generation unit 140, a learning model 150, and a database 161. Note that FIG. 7 shows only the main components related to this embodiment among the components included in the information processing device 101 shown in FIG. 6. Each of the determination unit 110, the feature amount calculation unit 130, the learning model generation unit 140, and the learning model 150 is the same as that in the first embodiment.

[0028] The database 161 stores in advance the time when the traffic signal control unit 121 controls the traffic signal 200. For example, the database 161 stores the location where the traffic signal 200 is installed in association with the time when the traffic signal control unit 121 controls the traffic signal 200. Also, the database 161 stores the time zone in association with the time when the traffic signal control unit 121 controls the traffic signal 200. Further, the database 161 may store the type of the target vehicle determined by the learning model 150 based on the feature amount extracted by the feature amount calculation unit 130 in association with the time when the traffic signal control unit 121 controls the traffic signal 200. The association stored in the database 161 can be edited from the outside.

[0029] FIG. 8 is a diagram showing an example of the association stored in the database 161 shown in FIG. 7. In the example shown in FIG. 8, the location and the control time are associated and stored in the database 161 shown in FIG. 7. The location is location identification information indicating the location where the traffic signal 200 is installed. The location identification information is stored in advance in the imaging unit 300 that captures an image for controlling the traffic signal 200, and is information transmitted together with the image data when the imaging unit 300 transmits the image data indicating the captured image to the information processing apparatus 101. The location identification information may be any information that can identify the location, and may be a combination of alphabets and numbers. Also, the traffic signals 200 (or the imaging units 300) installed in a certain area may commonly use the same location identification information. The control time is information indicating the time from when the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle until the traffic signal control unit 121 controls the traffic signal 200.

[0030] As shown in FIG. 8, the database 161 stores the location "A" and the control time "30 seconds" associated with each other. This indicates that, for the image data transmitted together with the location identification information of "A", when the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle, the signal control unit 121 controls the signal 200 to display for "30 seconds" in such a way that vehicles other than the target vehicle do not interfere with the running of the target vehicle. Also, the database 161 stores the location "B" and the control time "1 minute" associated with each other. This indicates that, for the image data transmitted together with the location identification information of "B", when the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle, the signal control unit 121 controls the signal 200 to display for "1 minute" in such a way that vehicles other than the target vehicle do not interfere with the running of the target vehicle. Also, the database 161 stores the location "C" and the control time "40 seconds" associated with each other. This indicates that, for the image data transmitted together with the location identification information of "C", when the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle, the signal control unit 121 controls the signal 200 to display for "40 seconds" in such a way that vehicles other than the target vehicle do not interfere with the running of the target vehicle. Also, the database 161 stores the location "D" and the control time "50 seconds" associated with each other. This indicates that, for the image data transmitted together with the location identification information of "D", when the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle, the signal control unit 121 controls the signal 200 to display for "50 seconds" in such a way that vehicles other than the target vehicle do not interfere with the running of the target vehicle.

[0031] The signal control unit 121 controls the display operation of the traffic signal 200 based on the result determined by the determination unit 110. When the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle, the signal control unit 121 reads out the control time from the database 161 based on the location identification information transmitted together with the image data, and controls the traffic signal 200 to perform a display that does not interfere with the driving of the target vehicle by other vehicles during that control time. For example, when the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle, the signal control unit 121 uses the location identification information transmitted together with the image data as a search key, reads out the control time associated with the location identification information from the database 161, and controls the display of the traffic signal 200 installed at a position visible from the target vehicle to turn blue during that control time. Also, the signal control unit 121 controls the display of the traffic signal 200 installed at a position visible from a vehicle traveling from a direction that obstructs the driving of the target vehicle to turn red during that control time. When controlling the traffic signal 200, the signal control unit 121 transmits a predetermined control signal to the traffic signal 200. This control signal only needs to be a signal whose control content can be recognized between the signal control unit 121 and the traffic signal 200, and is not particularly specified.

[0032] Hereinafter, the information processing method in the information processing system shown in FIG. 6 will be described. FIG. 9 is a flowchart for explaining an example of the information processing method in the information processing system shown in FIG. 6. Here, a case where the association shown in FIG. 8 is stored in the database 161 shown in FIG. 7 will be described as an example.

[0033] When the imaging unit 300 images the vehicle (step S11), the imaging unit 300 transmits the image data indicating the captured image to the information processing apparatus 101 via the communication network 400. At this time, the imaging unit 300 transmits the location identification information set (stored) in advance in the imaging unit 300 to the information processing apparatus 101 together with the image data. When the image data is transmitted from the imaging unit 300, the feature amount calculation unit 130 calculates (extracts) the feature amount from the image indicated by the transmitted image data (step S12). The feature amount calculation unit 130 outputs the calculated feature amount to the determination unit 110. Then, the determination unit 110 inputs the feature amount output from the feature amount calculation unit 130 to the learning model 150 (step S13). The determination unit 110 determines whether the vehicle information output from the learning model 150 indicates the target vehicle (step S14). When the vehicle information output from the learning model 150 indicates the target vehicle, the traffic signal control unit 121 reads out the control time from the database 161 based on the location identification information transmitted together with the image data (step S15). Subsequently, the traffic signal control unit 121 controls the traffic signal 200 to perform a display for a control time such that vehicles other than the target vehicle do not obstruct the travel of the target vehicle (step S16). Specifically, the traffic signal control unit 121 transmits a control signal for controlling the traffic signal 200 to perform a display for a control time such that vehicles other than the target vehicle do not obstruct the travel of the target vehicle to the traffic signal 200, and the traffic signal 200 controls the display according to the transmitted control signal.

[0034] FIG. 10 is a diagram showing another example of the association stored in the database 161 shown in FIG. 7. In the example shown in FIG. 10, the time zone and the control time are stored in the database 161 shown in FIG. 7 in association with each other. The time zone is time zone information indicating the time zone including the time when the determination unit 110 determines that the vehicle from which the feature amount is extracted is the target vehicle. The control time is information indicating the time when the traffic signal control unit 121 controls the traffic signal 200 after the determination unit 110 determines that the vehicle from which the feature amount is extracted is the target vehicle.

[0035] As shown in FIG. 10, the database 161 stores the time period "0:00 to 5:00" and the control time "1 minute" associated with each other. This indicates that when the time at which the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle is included in the time period "0:00 to 5:00", the traffic signal control unit 121 controls the traffic signal 200 to display for "1 minute" in such a way that vehicles other than the target vehicle do not obstruct the travel of the target vehicle. Also, the database 161 stores the time period "5:00 to 10:00" and the control time "30 seconds" associated with each other. This indicates that when the time at which the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle is included in the time period "5:00 to 10:00", the traffic signal control unit 121 controls the traffic signal 200 to display for "30 seconds" in such a way that vehicles other than the target vehicle do not obstruct the travel of the target vehicle. Also, the database 161 stores the time period "10:00 to 16:00" and the control time "50 seconds" associated with each other. This indicates that when the time at which the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle is included in the time period "10:00 to 16:00", the traffic signal control unit 121 controls the traffic signal 200 to display for "50 seconds" in such a way that vehicles other than the target vehicle do not obstruct the travel of the target vehicle. Also, the database 161 stores the time period "16:00 to 20:00" and the control time "30 seconds" associated with each other. This indicates that when the time at which the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle is included in the time period "16:00 to 20:00", the traffic signal control unit 121 controls the traffic signal 200 to display for "30 seconds" in such a way that vehicles other than the target vehicle do not obstruct the travel of the target vehicle. Also, the database 161 stores the time period "20:00 to 0:00" and the control time "1 minute" associated with each other. This indicates that when the time at which the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle is included in the time period "20:00 to 0:00", the traffic signal control unit 121 controls the traffic signal 200 to display for "1 minute" in such a way that vehicles other than the target vehicle do not obstruct the travel of the target vehicle.

[0036] The signal control unit 121 controls the display operation of the traffic signal 200 based on the result determined by the determination unit 110. When the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle, the signal control unit 121 reads out the control time from the database 161 based on the determined time, and controls the traffic signal 200 to perform a display that does not obstruct the travel of the target vehicle by other vehicles for that control time. For example, when the determination unit 110 determines that the vehicle from which the feature amount has been extracted is the target vehicle, the signal control unit 121 uses the time zone including the determined time as a search key, reads out the control time associated with that time zone from the database 161, and makes the display of the traffic signal 200 installed at a position visible from the target vehicle turn blue for that control time. Also, for the control time, the display of the traffic signal 200 installed at a position visible from a vehicle traveling from a direction that obstructs the travel of the target vehicle is controlled to be red. When controlling the traffic signal 200, the signal control unit 121 transmits a predetermined control signal to the traffic signal 200. This control signal only needs to be a signal whose control content can be recognized between the signal control unit 121 and the traffic signal 200, and is not particularly specified.

[0037] FIG. 11 is a flowchart for explaining another example of the information processing method in the information processing system shown in FIG. 6. Here, a case where the association shown in FIG. 10 is stored in the database 161 shown in FIG. 7 will be described as an example.

[0038] When the imaging unit 300 images the vehicle (step S21), the imaging unit 300 transmits image data indicating the captured image to the information processing device 101 via the communication network 400. When the image data is transmitted from the imaging unit 300, the feature amount calculation unit 130 calculates (extracts) the feature amount from the image indicated by the transmitted image data (step S22). The feature amount calculation unit 130 outputs the calculated feature amount to the determination unit 110. Then, the determination unit 110 inputs the feature amount output from the feature amount calculation unit 130 to the learning model 150 (step S23). The determination unit 110 determines whether the vehicle information output from the learning model 150 indicates the target vehicle (step S24). When the vehicle information output from the learning model 150 indicates the target vehicle, the control time is read from the database 161 based on the time zone including the current time (step S25). Subsequently, the traffic signal control unit 121 controls the traffic signal 200 to perform a display that does not interfere with the travel of the target vehicle by other vehicles during the control time (step S26). Specifically, the traffic signal control unit 121 transmits a control signal for controlling the traffic signal 200 to perform a display that does not interfere with the travel of the target vehicle by other vehicles during the control time to the traffic signal 200, and the traffic signal 200 controls the display according to the transmitted control signal.

[0039] In this embodiment, the imaging unit 300 images the moving vehicle, the information processing device 101 extracts feature amounts from the captured image, determines whether the vehicle is a target vehicle based on the extracted feature amounts, and controls the display of the traffic signal 200 if it is a target vehicle. For example, in the example shown in FIG. 2, when the information processing device 100 determines that the vehicle imaged by the imaging unit 300-1 is the target vehicle 500, it causes the traffic signal 200-1 to display permission to travel and causes the traffic signal 200-2 to display prohibition of travel. As a result, a specific vehicle can smoothly pass through the location where the traffic signal is installed. Further, the information processing device 101 designates the time for controlling the display of the traffic signal 200. The information processing device 101 designates a control time according to the location and time zone where the traffic signal 200 is installed. As a result, a specific vehicle can smoothly pass through the location where the traffic signal is installed at an appropriate time according to the location and time zone.

[0040] In addition to the location and time zone where the traffic signal 200 is installed, the control time may be specified according to the type of the target vehicle. In this case, the learning model generation unit 140 causes the learning model 150 to learn the feature amounts of a plurality of types of target vehicles, and the determination unit 110 makes a determination using the type of the target vehicle output from the learning model 150 for the feature amounts input to the learning model 150. The database 161 stores the control time for each type of target vehicle, and the traffic signal control unit 121 reads out the control time from the database 161 based on the type of the target vehicle determined by the determination unit 110 using the learning model 150 and controls the traffic signal 200 as described above. By doing so, a specific vehicle can smoothly pass through the location where the traffic signal is installed at an appropriate time according to the type of the vehicle.

[0041] As described above, each component has been described with each function (process) being shared, but this assignment is not limited to the above. Also, the configuration of the components is also merely an example and is not limited to this. Further, the above-described embodiments may be combined.

[0042] The processing performed by each of the above-described components may be performed by a logic circuit fabricated according to the purpose. Alternatively, a computer program (hereinafter referred to as a program) that describes the processing content as a procedure may be recorded on a recording medium readable by an apparatus (for example, information processing apparatuses 100 and 101; hereinafter referred to as an information processing apparatus) having each component, and the program recorded on this recording medium may be read by the information processing apparatus and executed. The recording medium readable by the information processing apparatus refers to a removable recording medium such as a floppy (registered trademark) disk, a magneto-optical disk, a DVD (Digital Versatile Disc), a CD (Compact Disc), a Blu-ray (registered trademark) Disc, a USB (Universal Serial Bus) memory, an SD memory card, etc., and also refers to a memory such as a ROM (Read Only Memory) or a RAM (Random Access Memory) built in the information processing apparatus, an HDD (Hard Disc Drive), etc. The program recorded on this recording medium is read by a CPU provided in the information processing apparatus, and under the control of the CPU, the same processing as described above is performed. Here, the CPU operates as a computer that executes the program read from the recording medium on which the program is recorded.

Explanation of Signs

[0043] 100,101 Information processing apparatus 110 Determination unit 120,121 Signal control unit 130 Feature quantity calculation unit 140 Learning model generation unit 150 Learning model 161 Database 200,200-1,200-2 Traffic signal 300,300-1,300-2 Imaging unit 400 Communication network 500 Target vehicle 600 General vehicle

Claims

1. An information processing system having an imaging unit, a traffic signal that displays for controlling the running of a vehicle, and an information processing device, wherein the information processing device includes a feature quantity calculation unit that calculates a feature quantity of a vehicle from an image of the vehicle captured by the imaging unit; a learning model generation unit that stores in advance the feature quantity of a target vehicle as teacher data and generates a learning model by performing machine learning on the feature quantity of the target vehicle; a determination unit that inputs the feature quantity calculated by the feature quantity calculation unit into the learning model and obtains from the learning model information indicating whether the vehicle from which the feature quantity is calculated is the target vehicle, thereby determining whether the vehicle is the target vehicle; a traffic signal control unit that controls the display operation of the traffic signal based on the result determined by the determination unit; a database that stores in association location identification information indicating the location where the traffic signal is installed and the time when the traffic signal control unit controls the display operation of the traffic signal; wherein when the determination unit determines that the vehicle from which the feature quantity is calculated is the target vehicle, the traffic signal control unit reads from the database the time for controlling the display operation of the traffic signal based on the location identification information indicating the location where the traffic signal associated with the imaging unit is installed, which is transmitted from the imaging unit together with the image of the vehicle captured by the imaging unit, and controls the traffic signal to perform a display such that a vehicle other than the target vehicle does not obstruct the running of the target vehicle for the time read from the database after the determination unit determines that the vehicle from which the feature quantity is calculated is the target vehicle. An information processing system.

2. The information processing system according to claim 1, wherein the target vehicle is an autonomous vehicle. An information processing system.

3. The information processing system according to claim 1 or claim 2, wherein the imaging unit is installed at a position where it can image a vehicle traveling on a road with one-way alternating traffic, and the traffic signal is installed at a position visible to vehicles traveling on the road. An information processing system.

4. a feature quantity calculation unit that calculates a feature quantity of a vehicle from an image of the vehicle captured by the imaging unit; a learning model generation unit that stores in advance the feature quantity of a target vehicle as teacher data and generates a learning model by performing machine learning on the feature quantity of the target vehicle; The feature amount calculated by the feature amount calculation unit is input into the learning model, and information indicating whether the vehicle for which the feature amount is calculated is the target vehicle is obtained from the learning model, thereby determining whether the vehicle is the target vehicle. A determination unit; Based on the result determined by the determination unit, it has a traffic signal control unit that controls the display operation of a traffic signal that performs a display for controlling the driving of the vehicle. When the determination unit determines that the vehicle for which the feature amount is calculated is the target vehicle, the traffic signal control unit, together with the image of the vehicle captured by the imaging unit, is transmitted from the imaging unit and is associated with the imaging unit. Based on the location identification information indicating the location where the installed traffic signal is located, the time for controlling the display operation of the traffic signal is read from a database that associates the location identification information indicating the location where the traffic signal is installed with the time for the traffic signal control unit to control the display operation of the traffic signal. After the determination unit determines that the vehicle for which the feature amount is calculated is the target vehicle, the time read from the database, the traffic signal, is controlled so as to perform a display such that a vehicle other than the target vehicle does not interfere with the driving of the target vehicle. An information processing device.

5. In the information processing device according to claim 4, The target vehicle is an information processing device that is an autonomous vehicle.

6. A process of calculating a feature amount of the vehicle from an image of the vehicle captured by the imaging unit; A process of storing in advance the feature amount of the target vehicle as teacher data and performing machine learning on the feature amount of the target vehicle to generate a learning model; A process of inputting the calculated feature amount into the learning model and obtaining information indicating whether the vehicle for which the feature amount is calculated is the target vehicle from the learning model, thereby determining whether the vehicle is the target vehicle; A process of controlling the display operation of a traffic signal that performs a display for controlling the driving of the vehicle based on the determined result. When it is determined that the vehicle for which the feature amount has been calculated is the target vehicle, based on the location identification information indicating the location where the traffic signal associated with the imaging unit is installed, which has been transmitted from the imaging unit together with the image of the vehicle captured by the imaging unit, the time for controlling the display operation of the traffic signal is read from a database that stores the location identification information indicating the location where the traffic signal is installed in association with the time for controlling the display operation of the traffic signal, and the traffic signal is controlled to perform a display such that vehicles other than the target vehicle do not obstruct the travel of the target vehicle, for a time read from the database after it is determined that the vehicle for which the feature amount has been calculated is the target vehicle. A traffic signal control method for performing such a process.

7. On a computer, a procedure for calculating a feature amount of a vehicle from an image of the vehicle captured by an imaging unit; a procedure for storing in advance the feature amount of the target vehicle as teacher data and generating a learning model by performing machine learning on the feature amount of the target vehicle; a procedure for inputting the calculated feature amount into the learning model and obtaining information indicating whether the vehicle for which the feature amount has been calculated is the target vehicle from the learning model, thereby determining whether the vehicle is the target vehicle; a procedure for controlling the display operation of a traffic signal that performs a display for controlling the travel of the vehicle based on the determined result; When it is determined that the vehicle for which the feature amount has been calculated is the target vehicle, based on the location identification information indicating the location where the traffic signal associated with the imaging unit is installed, which has been transmitted from the imaging unit together with the image of the vehicle captured by the imaging unit, the time for controlling the display operation of the traffic signal is read from a database that stores the location identification information indicating the location where the traffic signal is installed in association with the time for controlling the display operation of the traffic signal, and the traffic signal is controlled to perform a display such that vehicles other than the target vehicle do not obstruct the travel of the target vehicle, for a time read from the database after it is determined that the vehicle for which the feature amount has been calculated is the target vehicle. A program for causing a computer to execute such procedures.

Images