Traffic light identification method and device, electronic equipment and storage medium

Abstract

The invention provides a traffic light identification method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the intersection feature information of a target region according to a traffic light identification request, and the intersection feature information comprises a first traffic light group number, a first intersection turning direction and an intersection geographic position; acquiring a second traffic light group number of the target area, and determining angle information between the autonomous vehicle and each second traffic light group of the target area according to the second traffic light groups and the positioning information of the autonomous vehicle; determining the steering of the autonomous vehicle according to the intersection feature information, and determining a target traffic light signal of the autonomous vehicle according to the steering and angle information; and performing notification and control processing on the autonomous vehicle according to the target traffic light signal. The method has the beneficial effects that by adopting the map information and the traffic light real-time identification method, the identification accuracy of the color and direction of the traffic light is improved, and the identification cost is reduced.

Description

Technical Field

[0001] The present invention relates to the fields of autonomous driving and computer technology, and in particular to a traffic light recognition method, device, electronic device and storage medium. Background Art

[0002] There are two ways for autonomous vehicles to recognize traffic lights. One is to obtain traffic light signals through V2X devices, and the other is to recognize traffic light signals through cameras. Both methods have defects.

[0003] Usually, there are two or three groups of traffic lights on each pole at each intersection, which are used to indicate the traffic light signals for left turn, straight go and right turn respectively. The leftmost one is the left turn light, the middle one is the straight go light, and the rightmost one is the right turn light.

[0004] Currently, cameras have a high accuracy in recognizing the color of traffic lights, but a low accuracy in recognizing the direction of traffic light arrows. Therefore, for the color of a single set of traffic lights, whether it is red, green or yellow, the camera can accurately recognize it. However, for two or three sets of traffic lights, the camera often cannot accurately identify the direction of the traffic lights, that is, it cannot accurately distinguish between the traffic light signals for left turn, straight go and right turn. Summary of the invention

[0005] The main purpose of the embodiments of the present invention is to provide a traffic light recognition method, device, electronic device and storage medium to improve the recognition accuracy of the color and direction of traffic lights and reduce the recognition cost.

[0006] One aspect of the present invention provides a traffic light recognition method, comprising:

[0007] According to the traffic light recognition request, obtain the intersection characteristic information of the target area, wherein the intersection characteristic information includes the first traffic light group number, the first intersection turn and the intersection geographical location;

[0008] Collecting the number of second traffic light groups in the target area, and determining angle information between the autonomous driving vehicle and each of the second traffic light groups in the target area according to the positioning information of the second traffic light groups and the autonomous driving vehicle;

[0009] Determine the direction of the autonomous driving vehicle according to the intersection feature information, and determine the target traffic light signal of the autonomous driving vehicle according to the direction and the angle information;

[0010] According to the target traffic light signal, notification and control processing of the autonomous driving vehicle is performed.

[0011] According to the traffic light recognition method, before the step of obtaining the intersection feature information of the target area according to the traffic light recognition request, the method further includes:

[0012] The autonomous driving vehicle drives along the road in the target area, and obtains the latitude, longitude and heading angle during driving through a high-precision positioning device;

[0013] Collect the number of traffic lights, intersection turns and intersection geographical locations at the intersections on the driving route, where intersection turns also include intersection locations;

[0014] A map file of the target area is generated based on the collected latitude and longitude, heading angle and intersection feature information.

[0015] According to the traffic light recognition method, obtaining the intersection feature information of the target area according to the traffic light recognition request includes:

[0016] The latitude, longitude and heading angle of the autonomous driving vehicle are monitored in real time, and whether the autonomous driving vehicle enters the target area is detected based on the map file and the latitude, longitude and heading angle of the autonomous driving vehicle. If so, the intersection feature information is obtained.

[0017] According to the traffic light recognition method, determining the angle information between the autonomous driving vehicle and each group of traffic lights in the target area according to the positioning information of the second traffic light group and the autonomous driving vehicle includes:

[0018] When the positioning information of the autonomous driving vehicle determines that the autonomous driving vehicle is at an intersection, a first picture of the target area is captured by a camera device, the first picture is screened and a second picture including traffic light group information is acquired;

[0019] The angle information of each group of traffic lights is calculated according to the second image and the position of the camera device, wherein the angle information includes the distance, color, validity and angle of the traffic light group, wherein the angle is the angle between the traffic light group and the camera device.

[0020] According to the traffic light recognition method, the angle information of each group of traffic lights is calculated according to the second image and the position of the camera device, including:

[0021] Taking the camera device as the origin, constructing a FLU coordinate system;

[0022] Calculate the line connecting the traffic light group and the camera device in the FLU coordinate system to obtain the angle formed with the front direction of the longitudinal axis of the autonomous driving vehicle, sort the traffic light group according to the angle between the left and right sides of the autonomous driving vehicle, and obtain the traffic light grouping, where the traffic light grouping is used to characterize the turning set of traffic lights.

[0023] According to the traffic light recognition method, determining the target traffic light signal of the autonomous driving vehicle according to the steering and the angle information includes:

[0024] According to the number of traffic light groups identified by the camera device and the number of traffic light groups in the intersection feature information, the following processing is performed:

[0025] When the number of traffic light groups in the intersection characteristic information is 0, it indicates a temporary traffic light failure, and the traffic light signal of the first number of traffic light groups in the intersection characteristic information is used as the target traffic light signal;

[0026] When the number of traffic light groups in the intersection characteristic information is greater than or equal to 1, a traffic light signal corresponding to the first traffic light group number in a second traffic light group number is searched from the traffic light grouping to obtain a target traffic light signal.

[0027] According to the traffic light recognition method, the notification and control processing of the autonomous driving vehicle is performed according to the target traffic light signal, including:

[0028] According to the target traffic light signal, at least one of voice broadcast and interactive display is used for prompting.

[0029] Another aspect of an embodiment of the present invention provides a traffic light recognition device, comprising:

[0030] The first module is used to obtain the intersection characteristic information of the target area according to the traffic light recognition request, wherein the intersection characteristic information includes the first traffic light group number, the first intersection turn and the intersection geographical location;

[0031] The second module is used to collect the number of second traffic light groups in the target area, and determine the angle information between the autonomous driving vehicle and each of the second traffic light groups in the target area according to the positioning information of the second traffic light groups and the autonomous driving vehicle;

[0032] A third module is used to determine the steering direction of the autonomous driving vehicle according to the intersection feature information, and determine the target traffic light signal of the autonomous driving vehicle according to the steering direction and the angle information;

[0033] The fourth module is used to perform notification and control processing on the autonomous driving vehicle according to the target traffic light signal.

[0034] Another aspect of an embodiment of the present invention provides an electronic device, including a processor and a memory;

[0035] The memory is used to store programs;

[0036] The processor executes the program to implement the method described above.

[0037] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the method described above.

[0038] The beneficial effects of the present invention are as follows: traffic light information is identified by only using a camera device, compared with a priori traffic lights, and intersection turns consistent with the priori traffic lights and real-time traffic light information are selected to determine the turn traffic light signal and perform automatic steering of autonomous driving. In this way, there is no need to use expensive equipment, which reduces the cost of traffic light identification; the fusion of map information and traffic light identification is combined with the prior knowledge of the number of traffic light groups in the map to prevent misidentification when a certain traffic light is off, or the difficulty in distinguishing directions when only one traffic light is effective, thereby improving recognition accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:

[0040] Figure 1 4 is a schematic diagram of a traffic light recognition system according to an embodiment of the present invention.

[0041] Figure 2 It is a schematic diagram of the traffic light recognition process according to an embodiment of the present invention.

[0042] Figure 3 It is a schematic diagram of the map information drawing process of an embodiment of the present invention.

[0043] Figure 4 It is a schematic diagram of the traffic light angle information analysis process according to an embodiment of the present invention.

[0044] Figure 5 It is a flow chart of traffic light angle calculation according to an embodiment of the present invention.

[0045] Figure 6 Schematic diagram of a traffic light system for an autonomous driving vehicle according to an embodiment of the present invention.

[0046] Figure 7 Schematic diagram of a device for traffic light recognition according to an embodiment of the present invention. DETAILED DESCRIPTION

[0047] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention.

[0048] Reference Figure 1 ,in Figure 1 1 is a block diagram of a traffic light recognition system, which includes an autonomous driving vehicle 200 and an intersection 400 on which it is traveling, and also includes a map drawing vehicle 500. The autonomous driving vehicle 200 includes a camera 210, a vehicle terminal 220, and a positioning device 230. The camera 210 is used to take photos of the traffic light 100, the positioning device 230 is used to provide vehicle positioning information, and the vehicle terminal 220 is used to store the map information drawn by the map drawing vehicle 500, and, according to the traffic light recognition request, obtain the intersection feature information of the target area, the intersection feature information includes the number of first traffic light groups, the first intersection turn and the intersection geographical location; collect the number of second traffic light groups in the target area, and determine the angle information between the autonomous driving vehicle and each second traffic light group in the target area according to the second traffic light group and the positioning information of the autonomous driving vehicle; determine the turn of the autonomous driving vehicle according to the intersection feature information, and determine the target traffic light signal of the autonomous driving vehicle according to the turn and angle information; perform notification and control processing on the autonomous driving vehicle according to the target traffic light signal.

[0049] In some embodiments, reference Figure 2 The traffic light recognition process diagram shown includes but is not limited to steps S100 to S400:

[0050] S100, according to the traffic light recognition request, obtaining intersection characteristic information of the target area, the intersection characteristic information including the number of first traffic light groups, the first intersection turn and the geographical location of the intersection.

[0051] In some embodiments, it also includes drawing map information of the intersection feature information, referring to Figure 3 The map information drawing process shown in the figure includes but is not limited to steps S510 to S530:

[0052] S510, driving the autonomous driving vehicle along a road in the target area, and obtaining the latitude, longitude and heading angle during driving by using a high-precision positioning device;

[0053] S530, collecting the number of traffic light groups, intersection turns and intersection geographical locations at the intersections in the driving path, wherein the intersection turns also include the intersection location;

[0054] S540, generating a map file of the target area according to the collected longitude and latitude, heading angle and intersection feature information.

[0055] It is understandable that when the autonomous driving vehicle obtains intersection feature information, the map information of the area is drawn as in the embodiment.

[0056] For example, the autonomous driving vehicle is manually driven to the lane where the route map needs to be drawn, and the personal PC is connected to the high-precision positioning device on the autonomous driving vehicle to run the drawing software. The vehicle is manually driven along the required route, and the drawing software will collect signals such as longitude, latitude, heading angle, etc. on the route in real time. When the vehicle is about to drive to the intersection, the direction of the vehicle at the intersection is marked, such as left turn, straight or right turn, and the location of the exit is marked. At the same time, the number of traffic light groups in the direction of the vehicle at the intersection is marked, such as 1 group, 2 groups, or 3 groups.

[0057] When the route collection is completed, the drawing software will generate a map file in a specific format, which will contain information such as the longitude and latitude of the road, heading angle, and marked intersection feature information.

[0058] After the map file is generated using the drawing software, there is no need to repeat this work if the subsequent road conditions do not change.

[0059] S200, collecting the number of second traffic light groups in the target area, and determining the angle information between the autonomous driving vehicle and each second traffic light group in the target area based on the positioning information of the second traffic light groups and the autonomous driving vehicle.

[0060] In some embodiments, the latitude, longitude and heading angle of the autonomous driving vehicle are monitored in real time, and whether the vehicle enters the target area is detected based on the map file and the latitude, longitude and heading angle of the autonomous driving vehicle. If so, the intersection feature information is obtained.

[0061] In some embodiments, reference Figure 4 The traffic light angle information analysis process diagram shown in FIG. 1 includes but is not limited to steps S210 to S220:

[0062] S210, when the positioning information of the autonomous driving vehicle determines that the autonomous driving vehicle is at an intersection, collecting a first picture of the target area through a camera device, screening the first picture and obtaining a second picture including traffic light group information;

[0063] S220, calculating angle information of each group of traffic lights according to the second image and the position of the camera device, wherein the angle information includes the distance, color, validity and angle of the traffic light group, wherein the angle is the angle between the traffic light group and the camera device.

[0064] For example, after the on-board camera recognizes the traffic light, it outputs 8 frames of CAN messages to the automatic driving controller. Each frame of the message contains the distance, color, validity, and angle information of each group of traffic lights. The camera can effectively recognize up to 8 groups of traffic lights. Each frame of the message is valid only when it recognizes the traffic light, otherwise it is invalid.

[0065] In some embodiments, reference Figure 5The traffic light angle calculation flow chart shown includes but is not limited to steps S211 to S212:

[0066] S211, constructing a FLU coordinate system with the camera device as the origin;

[0067] S212, calculate the connection line between the traffic light group and the camera device in the FLU coordinate system, obtain the angle formed with the front direction of the longitudinal axis of the autonomous driving vehicle, sort the traffic light group according to the left and right sides of the autonomous driving vehicle and the size of the angle, and obtain the traffic light grouping, wherein the traffic light grouping is used to represent the turning set of the traffic lights.

[0068] It can be understood that the distance and angle are based on the FLU coordinate system, the camera position is the coordinate origin, and the angle is the angle formed by the line connecting the traffic light and the camera and the front direction of the vehicle's longitudinal axis. The traffic light is positive on the left side of the camera, and the angle increases as it is to the left. The traffic light is negative on the right side of the camera, and the angle decreases as it is to the right.

[0069] S300, determining the direction of the autonomous driving vehicle based on the intersection feature information, and determining the target traffic light signal of the autonomous driving vehicle based on the steering and angle information.

[0070] In some embodiments, the following processing is performed based on the number of traffic light groups identified by the camera device and the number of traffic light groups in the intersection characteristic information: when the number of traffic light groups in the intersection characteristic information is 0, it indicates a temporary traffic light failure, and the traffic light signal of the first traffic light group number in the intersection characteristic information is used as the target traffic light signal; when the number of traffic light groups in the intersection characteristic information is greater than or equal to 1, the traffic light signal corresponding to the first traffic light group number in the second traffic light group number is searched from the traffic light group to obtain the target traffic light signal.

[0071] For example, the fusion processing of map information and real-time collected traffic light information is as follows:

[0072] After the autonomous driving controller (on-board terminal) receives the traffic light signal output by the camera, it sorts each valid group of traffic light signals from large to small according to the angle, and the serial numbers are 0, 1, 2..., so as to distinguish left turn, straight go, and right turn traffic light signals.

[0073] 1. When approaching an intersection, if the direction of the intersection marked on the read map is a left turn:

[0074] 1) If the number of traffic light groups in the direction of vehicle travel at the intersection marked in the read map is 1, as long as one group of traffic lights is identified as valid, the traffic light signal with the sequence number 0 is regarded as the left turn traffic light signal.

[0075] 2) If the number of traffic light groups for the direction of vehicle travel at the intersection marked in the read map is 2, when two groups of traffic lights are identified to be valid, the traffic light signal with the sequence number 0 is regarded as the left turn traffic light signal.

[0076] 3) If the number of traffic light groups in the direction of vehicle travel at the intersection marked in the read map is 3, when three groups of traffic lights are identified to be valid, the traffic light signal with the sequence number 0 is regarded as the left turn traffic light signal.

[0077] 2. When approaching an intersection, if the direction of the intersection marked on the read map is straight ahead:

[0078] 1) If the number of traffic light groups in the direction of vehicle travel at the intersection marked in the read map is 1, as long as one group of traffic lights is identified as valid, the traffic light signal with the sequence number 0 is regarded as the straight traffic light signal.

[0079] 2) If the number of traffic light groups for the direction of vehicle travel at the intersection marked in the read map is 2, when two groups of traffic lights are identified to be valid, the traffic light signal of the group with sequence number 1 is regarded as the straight-ahead traffic light signal.

[0080] 3) If the number of traffic light groups in the direction of vehicle travel at the intersection marked in the read map is 3, when three groups of traffic lights are identified to be valid, the traffic light signal of the group with sequence number 1 is regarded as the straight-ahead traffic light signal.

[0081] 3. When approaching an intersection, if the direction of the intersection marked on the read map is a right turn:

[0082] 1) If the number of traffic light groups in the direction of vehicle travel at the intersection marked in the read map is 3, when three groups of traffic lights are identified to be valid, the traffic light signal with the sequence number 2 is regarded as the right turn traffic light signal.

[0083] S400: Notification and control processing of the autonomous driving vehicle is performed according to the target traffic light signal.

[0084] In some embodiments, the prompt may be provided through at least one of voice broadcast and interactive display, as follows:

[0085] When it is recognized that the traffic light signal in the direction of the vehicle's current travel at the intersection is red, the automatic driving controller sends a "red light ahead" voice broadcast command to the speaker, and at the same time sends a command to make the HMI light up the red light icon; when it is recognized that the traffic light signal in the direction of the vehicle's current travel at the intersection is green, the automatic driving controller sends a "green light ahead" voice broadcast command to the speaker, and at the same time sends a command to make the HMI light up the green light icon; when it is recognized that the traffic light signal in the direction of the vehicle's current travel at the intersection is yellow, the automatic driving controller sends a "yellow light ahead" voice broadcast command to the speaker, and at the same time sends a command to make the HMI light up the yellow light icon.

[0086] In some embodiments, reference Figure 6 The schematic diagram of the traffic light system of an autonomous driving vehicle is shown. The on-board equipment of the autonomous driving vehicle includes a high-precision positioning device, an autonomous driving controller, a human-computer interaction module, and a camera.

[0087] The high-precision positioning device provides the vehicle with real-time centimeter-level positioning information and outputs signals such as latitude, longitude, altitude, and heading angle. The human-computer interaction module includes HMI and speakers, which are used for traffic light display and voice prompts respectively. The automatic driving controller is used to store and read map files, receive vehicle positioning information, perform traffic light and map fusion processing, and issue voice prompts and traffic light display instructions.

[0088] The drawing software is a host computer that can run on a personal PC and is used to draw the path map required for autonomous driving.

[0089] Through this embodiment, a single or multiple groups of traffic light signals are identified by a camera in combination with an autonomous driving feature map, which can not only accurately identify the color of the traffic light, but also accurately identify the direction of the traffic light arrows, and is used to provide autonomous driving vehicles with left turn, straight go and right turn traffic light signals at intersections.

[0090] In some embodiments, reference Figure 7 The traffic light recognition device shown in the figure includes a first module 710 , a second module 720 , a third module 730 and a fourth module 740 .

[0091] Among them, the first module is used to obtain the intersection characteristic information of the target area according to the traffic light recognition request, and the intersection characteristic information includes the number of first traffic light groups, the first intersection turn and the geographical location of the intersection; the second module is used to collect the number of second traffic light groups in the target area, and determine the angle information between the autonomous driving vehicle and each second traffic light group in the target area according to the positioning information of the second traffic light group and the autonomous driving vehicle; the third module is used to determine the turn of the autonomous driving vehicle according to the intersection characteristic information, and determine the target traffic light signal of the autonomous driving vehicle according to the turn and angle information; the fourth module is used to perform notification and control processing on the autonomous driving vehicle according to the target traffic light signal.

[0092] Exemplarily, with the cooperation of the first module, the second module, the third module and the fourth module in the device, the embodiment device can implement any of the aforementioned traffic light recognition methods, namely, according to the traffic light recognition request, obtaining the intersection characteristic information of the target area, the intersection characteristic information including the number of first traffic light groups, the first intersection turn and the geographical location of the intersection; collecting the number of second traffic light groups in the target area, and determining the angle information of the autonomous driving vehicle and each second traffic light group in the target area according to the positioning information of the second traffic light group and the autonomous driving vehicle; determining the turn of the autonomous driving vehicle according to the intersection characteristic information, and determining the target traffic light signal of the autonomous driving vehicle according to the turn and angle information; and performing notification and control processing on the autonomous driving vehicle according to the target traffic light signal. The beneficial effects of the present invention are as follows: traffic light information is identified by only using a camera device, compared with a priori traffic lights, and intersection turns consistent with the a priori traffic lights and real-time traffic light information are selected to determine the turn traffic light signal and perform automatic steering of autonomous driving. In this way, there is no need to use expensive equipment, which reduces the cost of traffic light identification; by combining the prior knowledge of the number of traffic light groups in the map, it is possible to prevent misidentification when a certain traffic light is off, or the difficulty in distinguishing directions when only one traffic light is effective, thereby improving recognition accuracy.

[0093] An embodiment of the present invention further provides an electronic device, the electronic device comprising a processor and a memory;

[0094] The memory stores a program;

[0095] The processor executes the program to perform the aforementioned traffic light recognition method; the electronic device has the function of carrying and running the software system for traffic light recognition provided by the embodiment of the present invention.

[0096] An embodiment of the present invention further provides a computer-readable storage medium, wherein the storage medium stores a program, and the program is executed by a processor to implement the traffic light recognition method as described above.

[0097] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiments presented and described in the flow chart of the present invention are provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operations and logic flows presented by the embodiments of the present invention. Optional embodiments are expected, wherein the order of various operations is changed and wherein the sub-operations described as a part of a larger operation are performed independently.

[0098] The embodiment of the present invention also discloses a computer program product or a computer program, which includes a computer instruction stored in a computer-readable storage medium. A processor of a computer device can read the computer instruction from the computer-readable storage medium, and the processor executes the computer instruction, so that the computer device executes the aforementioned traffic light recognition method.

[0099] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features described may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions, and internal relationships of various functional modules in the devices disclosed in the embodiments of the present invention, the actual implementation of the module will be understood within the conventional skills of engineers. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0100] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0101] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0102] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0103] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0104] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0105] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0106] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A traffic light recognition method, characterized in that: include: According to the traffic light recognition request, obtain the intersection characteristic information of the target area, wherein the intersection characteristic information includes the first traffic light group number, the first intersection turn and the intersection geographical location; Collecting the number of second traffic light groups in the target area, and determining angle information between the autonomous driving vehicle and each of the second traffic light groups in the target area according to the positioning information of the second traffic light groups and the autonomous driving vehicle; Determine the direction of the autonomous driving vehicle according to the intersection feature information, and determine the target traffic light signal of the autonomous driving vehicle according to the direction and the angle information; According to the target traffic light signal, notification and control processing of the autonomous driving vehicle is performed.

2. The traffic light recognition method according to claim 1, characterized in that: Before the step of obtaining the intersection feature information of the target area according to the traffic light recognition request, the method further includes: The autonomous driving vehicle drives along the road in the target area, and obtains the latitude, longitude and heading angle during driving through a high-precision positioning device; Collect the number of traffic lights, intersection turns and intersection geographical locations at the intersections along the driving route, where intersection turns also include intersection locations; A map file of the target area is generated based on the collected latitude and longitude, heading angle and intersection feature information.

3. The traffic light recognition method according to claim 2, characterized in that: The step of obtaining the intersection feature information of the target area according to the traffic light recognition request includes: The latitude, longitude and heading angle of the autonomous driving vehicle are monitored in real time, and whether the autonomous driving vehicle enters the target area is detected based on the map file and the latitude, longitude and heading angle of the autonomous driving vehicle. If so, the intersection feature information is obtained.

4. The traffic light recognition method according to claim 1, characterized in that: The determining, based on the positioning information of the second traffic light group and the autonomous driving vehicle, angle information between the autonomous driving vehicle and each group of traffic lights in the target area includes: When the positioning information of the autonomous driving vehicle determines that the autonomous driving vehicle is at an intersection, a first picture of the target area is captured by a camera device, the first picture is screened and a second picture including traffic light group information is acquired; The angle information of each group of traffic lights is calculated according to the second image and the position of the camera device, wherein the angle information includes the distance, color, validity and angle of the traffic light group, wherein the angle is the angle between the traffic light group and the camera device.

5. The traffic light recognition method according to claim 4, characterized in that: The calculating the angle information of each group of traffic lights according to the second picture and the position of the camera device includes: Taking the camera device as the origin, constructing a FLU coordinate system; Calculate the line connecting the traffic light group and the camera device in the FLU coordinate system to obtain the angle formed with the front direction of the longitudinal axis of the autonomous driving vehicle, sort the traffic light group according to the angle between the left and right sides of the autonomous driving vehicle, and obtain the traffic light grouping, where the traffic light grouping is used to characterize the turning set of traffic lights.

6. The traffic light recognition method according to claim 5, characterized in that: Determining a target traffic light signal of the autonomous driving vehicle according to the steering and the angle information includes: According to the number of traffic light groups identified by the camera device and the number of traffic light groups in the intersection feature information, the following processing is performed: When the number of traffic light groups in the intersection characteristic information is 0, it indicates a temporary traffic light failure, and the traffic light signal of the first number of traffic light groups in the intersection characteristic information is used as the target traffic light signal; When the number of traffic light groups in the intersection characteristic information is greater than or equal to 1, a traffic light signal corresponding to the first traffic light group number in a second traffic light group number is searched from the traffic light grouping to obtain a target traffic light signal.

7. The traffic light recognition method according to claim 1, characterized in that: The performing of notification and control processing on the automatic driving vehicle according to the target traffic light signal includes: According to the target traffic light signal, at least one of voice broadcast and interactive display is used for prompting.

8. A traffic light recognition device, characterized in that: include: The first module is used to obtain the intersection characteristic information of the target area according to the traffic light recognition request, wherein the intersection characteristic information includes the first traffic light group number, the first intersection turn and the intersection geographical location; The second module is used to collect the number of second traffic light groups in the target area, and determine the angle information between the autonomous driving vehicle and each of the second traffic light groups in the target area according to the positioning information of the second traffic light groups and the autonomous driving vehicle; A third module is used to determine the steering direction of the autonomous driving vehicle according to the intersection feature information, and determine the target traffic light signal of the autonomous driving vehicle according to the steering direction and the angle information; The fourth module is used to perform notification and control processing on the autonomous driving vehicle according to the target traffic light signal.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the traffic light recognition method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the traffic light recognition method according to any one of claims 1 to 7.

Images