Intelligent traffic related devices and methods

Abstract

The invention provides intelligent traffic related devices and methods. One aspect of the present invention relates to a vehicle-mounted device for an intelligent traffic system, comprising: a communication module configured to send a first trigger message to a road side unit, the first trigger message comprising a timestamp, the first trigger message being used for triggering the road side unit to generate truth value labeling information corresponding to the timestamp, the communication module is further configured to receive the truth value labeling information when a preset truth value triggering condition is met; the acquisition module is used for acquiring vehicle end sensing information; the comparison module is configured to compare the truth value labeling information with the vehicle end sensing information to obtain a comparison result; and the evaluation module is configured to evaluate the accuracy of the truth value labeling information or the accuracy of the vehicle end sensing information based on the comparison result.

Description

Technical Field

[0001] The present invention generally relates to the technical field of intelligent transportation, and in particular to equipment and methods related to intelligent transportation. Background Art

[0002] Perception systems are widely used in the field of intelligent transportation, providing data support for intelligent transportation. In the field of intelligent transportation, perception systems can be divided into vehicle-side perception systems (i.e., vehicle-mounted perception systems) and roadside perception systems. At present, no optimal solution has been found for how to judge the accuracy of perception results of either vehicle-side perception systems or roadside perception systems. Summary of the invention

[0003] In this context, one aspect of the present invention provides a vehicle-mounted device for an intelligent transportation system, comprising: a communication module, configured to send a first trigger message to a roadside unit, which includes a timestamp, the first trigger message is used to trigger the roadside unit to generate true value annotation information corresponding to the timestamp, which includes status information of one or more roadside perception objects obtained by the roadside sensor sensing the surrounding environment, and the communication module is also configured to receive the true value annotation information when a predetermined true value trigger condition is met; an acquisition module, which acquires vehicle-side perception information, which includes status information of one or more vehicle-side perception objects obtained by the vehicle-mounted sensor sensing the surrounding environment; a comparison module, configured to compare the true value annotation information with the vehicle-side perception information to obtain a comparison result; and an evaluation module, configured to evaluate the accuracy of the true value annotation information and / or the accuracy of the vehicle-side perception information based on the comparison result.

[0004] Another aspect of the present invention provides a roadside unit for an intelligent transportation system, including a truth value system, wherein the roadside unit is configured to: receive a first trigger message including a timestamp; in response to receiving the first trigger message, generate truth value annotation information corresponding to the timestamp by the truth value system; receive a second trigger message; and in response to receiving the second trigger message, send the truth value annotation information; wherein the truth value annotation information includes: a timestamp, which is consistent with the timestamp included in the first trigger message; a response identifier, which corresponds to a unique identifier of the first trigger message; a vehicle identifier, which is consistent with the unique identifier of the vehicle included in the first trigger message; and status information of one or more roadside perception objects obtained by the roadside sensor sensing the surrounding environment.

[0005] Another aspect of the present invention provides a perception information evaluation method, which is optionally performed by the vehicle-mounted device as described above, and the method includes: sending a first trigger message to a roadside unit, which includes a timestamp, and the first trigger message is used to trigger the roadside unit to generate true value annotation information corresponding to the timestamp, which includes status information of one or more roadside perception objects obtained by the roadside sensor sensing the surrounding environment, and obtaining vehicle-side perception information, which includes status information of one or more vehicle-side perception objects obtained by the vehicle-mounted sensor sensing the surrounding environment; receiving the true value annotation information when a predetermined true value trigger condition is met; comparing the true value annotation information with the vehicle-side perception information to obtain a comparison result; and evaluating the accuracy of the true value annotation information and / or the accuracy of the vehicle-side perception information based on the comparison result.

[0006] Another aspect of the present invention provides a method for sending true value labeling information, which is optionally performed by a roadside unit as described above, and the method includes: receiving a first trigger message, which includes a timestamp; in response to receiving the first trigger message, generating true value labeling information corresponding to the timestamp; receiving a second trigger message; and in response to receiving the second trigger message, sending the true value labeling information; wherein the true value labeling information includes: a timestamp, which is consistent with the timestamp included in the first trigger message; a response identifier, which corresponds to the unique identifier of the first trigger message; a vehicle identifier, which is consistent with the unique identifier of the vehicle included in the first trigger message; and status information of one or more roadside perception objects obtained by the roadside sensor sensing the surrounding environment.

[0007] Another aspect of the present invention provides an intelligent transportation system, which includes: the vehicle-mounted device as described above; the roadside unit as described above; and an edge cloud and a cloud server that can communicate with the vehicle-mounted device and the roadside unit.

[0008] According to another aspect of the present invention, a machine-readable storage medium is provided, which stores executable instructions. When the instructions are executed, one or more processors execute the method as described above.

[0009] A summary of the main aspects of the present invention is provided above so that these aspects can be basically understood. This summary is not intended to limit the scope of any or all aspects of the present invention. The purpose of this summary is to provide some implementations of these aspects in a simplified form as a preface to the detailed description that will be provided later. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The technical solution of the present invention will become clearer from the following detailed description in conjunction with the accompanying drawings. It is understood that these drawings are only used for exemplary description and are not intended to limit the scope of protection of the present invention.

[0011] Figure 1 is a schematic block diagram of an intelligent transportation system according to an embodiment of the present invention.

[0012] Figure 2 Shows Figure 1 An embodiment of an intelligent transportation system in.

[0013] Figure 3 Shows Figure 1 A way to implement on-board equipment of intelligent transportation system.

[0014] Figure 4 is a flow chart of a method for evaluating perception information according to an embodiment of the present invention.

[0015] Figure 5 It is a flowchart of a method for sending true value annotation information according to an embodiment of the present invention. DETAILED DESCRIPTION

[0016] The specific implementation of the present invention is described below in conjunction with the accompanying drawings.

[0017] Figure 1 An intelligent transportation system 100 (hereinafter referred to as the system 100 ) according to an embodiment of the present invention is schematically shown, which includes a vehicle-mounted device 10 and a roadside unit 20 capable of communicating with the vehicle-mounted device 10 .

[0018] According to an embodiment of the present invention, the vehicle-mounted sensor (not shown) senses the surrounding environment at the vehicle end and obtains perception information, which includes relevant information of traffic participants in the surrounding environment (i.e., vehicle-end perception objects hereinafter). The roadside sensor (not shown) senses the surrounding environment at the roadside and the roadside unit 20 generates true value annotation information, which includes relevant information of traffic participants in the surrounding environment (hereinafter referred to as roadside perception objects). Then, when the true value trigger condition is met, the vehicle-mounted device 10 receives the true value annotation information generated at the roadside unit 20, and compares the received true value annotation information with the perception information obtained at the vehicle end, thereby evaluating the vehicle-end perception performance or the roadside perception performance.

[0019] Figure 2 One embodiment of the system 100 is shown. Figure 2 As shown, the system 100 may further include an edge cloud 30 and a cloud server 40. The edge cloud 30 can be respectively connected to the vehicle-mounted device 10, the roadside unit 20 and the cloud server 40 for communication. The cloud server 40 can be respectively connected to the vehicle-mounted device 10, the roadside unit 20 and the edge cloud 30 for communication. In this embodiment, the roadside unit 20 may store the generated true value annotation information in the edge cloud 30 and / or the cloud server 40. Thus, the vehicle-mounted device 10 may receive the true value annotation information from the edge cloud 30 or the cloud server 40.

[0020] It is advantageous to send the true value annotation information to the vehicle side through the edge cloud 30 and / or the cloud server 40. Because for the vehicle, the edge cloud can provide nearby computing and communication, thereby improving latency. The communication between the vehicle and the edge cloud requires only a few network jumps, thereby saving bandwidth. The cloud server can be implemented as a central controller and schedule multiple edge clouds, so that the true value annotation information can be sent by the edge cloud that is most suitable for the vehicle through scheduling. In addition, by deploying access rights for specific vehicles at the edge cloud and cloud server, the data security and reliability during the transmission of the true value annotation information can be improved.

[0021] Figure 3 FIG. 1 shows an implementation of the vehicle-mounted device 10. Figure 3 As shown, the vehicle-mounted device 10 includes a communication module 11, an acquisition module 12, a determination module 13, a comparison module 14, and an evaluation module 15. It is understood that the naming of these modules is functional and is not intended to limit their physical locations. For example, these modules can be implemented on the same chip or in different chips.

[0022] These modules can be implemented in hardware or software or a combination of software and hardware. For the hardware-implemented part, it can be implemented in one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic units designed to perform their functions, or combinations thereof. For the software-implemented part, it can be implemented with the aid of microcodes, program codes, or code segments, and can also be stored in machine-readable storage media such as storage components.

[0023] Figure 4 FIG. 4 shows a perception information evaluation method 400 according to an embodiment of the present invention. The method 400 can be executed at the vehicle-mounted device 10 .

[0024] See also Figure 4 In block 402, the communication module 11 sends a first trigger message to the roadside unit 20. The first trigger message includes a timestamp (ie, the time when the first trigger message is sent) and request information for requesting true value labeling information.

[0025] In one embodiment, the first trigger message also includes: the location information of the vehicle at the timestamp, the unique identifier of the first trigger message (i.e., a symbol for uniquely identifying the first trigger message), and the unique identifier of the vehicle (i.e., a symbol for uniquely identifying the vehicle). In this way, the first trigger message can indicate: the sender of the message (i.e., the vehicle), the sending time (i.e., the timestamp), and the current location of the sender (i.e., the location of the vehicle at the timestamp).

[0026] After the roadside unit 20 receives the first trigger message, the truth value system in the roadside unit 20 generates truth value annotation information corresponding to the timestamp, that is, the truth value standard information of the timestamp.

[0027] In one embodiment, the true value annotation information includes status information of one or more roadside perception objects. It is understood that the roadside perception objects should be within the field of view of the roadside sensor and can be identified by the roadside unit 20. Objects that are not within the field of view of the roadside sensor or cannot be identified by the roadside unit 20 will not be included in the true value annotation information.

[0028] It should be noted that for the sake of clarity, in this article, the perception objects contained in the true value annotation information are referred to as roadside perception objects, which are distinguished from the vehicle-side perception objects contained in the vehicle-side perception information mentioned below.

[0029] The status information of each roadside perception object may include one or more of the following status parameters of the object: 1) object type, for example, motor vehicles, non-motor vehicles, pedestrians, animals and roadside facilities; 2) object size, for example, length, width and height information of the object; 3) object shape, for example, square, cone, cylinder; 4) object position at the timestamp, for example, longitude, latitude and altitude coordinates; 5) object speed at the timestamp; 6) object acceleration at the timestamp; 7) object motion trend, for example, the instantaneous motion direction of the object at the timestamp, and the predicted motion trajectory of the object within a period of time after the timestamp.

[0030] The truth value annotation information may also include: a timestamp, which corresponds to the timestamp contained in the first trigger message, such as can be derived from the timestamp in the first trigger message; a response identifier, which corresponds to the unique identifier of the first trigger message (for example, an additional identifier is added on the basis of the unique identifier of the first trigger message); and a vehicle identifier, which is consistent with the unique identifier of the vehicle contained in the first trigger message.

[0031] In block 404, the acquisition module 12 acquires vehicle-side perception information. The vehicle-side perception information is obtained by the vehicle-mounted sensor sensing the surrounding environment at the timestamp. The perception information includes state information of one or more vehicle-side perception objects.

[0032] It is understandable that the vehicle-side perception objects and the road-side perception objects should be at least partially consistent, because both the on-board sensors and the road-side sensors perceive the same traffic scene. Since their fields of view may be different, their perception capabilities may also be different, and their perception precision and accuracy are not exactly the same, so their perception objects may only partially overlap, that is, there are some differences in their perception objects.

[0033] The vehicle-side perception information may include the state information of each vehicle-side perception object, which may include one or more state parameters of the object. Regarding the state parameters, the above-mentioned expression method of the state parameters of the roadside perception object can be referred to and applied, which will not be repeated here.

[0034] In block 406, the determination module 13 determines whether the communication module 11 receives a response signal within a predetermined time after the first trigger message is sent. That is, the determination module 13 determines whether the communication module 11 receives a response signal within a predetermined time after the timestamp. The advantage of doing so is that it can determine whether the current communication link between the vehicle-mounted device 10 and the roadside unit 20 is unobstructed. It can be understood that the predetermined time is pre-set based on a specific application scenario (for example, a communication mode or a network deployment status of the vehicle's environment).

[0035] If the result of the judgment in box 406 is "No", that is, no response signal is received within a predetermined time after the first trigger message is sent, this indicates that the communication link between the vehicle-mounted device 10 and the roadside unit 20 may be blocked. At this time, enter box 408. In box 408, the reason for the blocked communication link can be detected, for example, the first trigger message can be sent again.

[0036] If the result of the determination in block 406 is “yes”, that is, a response signal is received within a predetermined period of time after the first trigger message is sent, the process proceeds to block 410 .

[0037] In block 410, the determination module 13 selects a true value trigger condition from a plurality of pre-determined true value trigger conditions. The plurality of true value trigger conditions include one or more of the following: 1) whether the vehicle is parked; 2) whether the vehicle has sufficient power or fuel, for example, whether the remaining power or fuel of the vehicle exceeds a corresponding threshold; 3) whether the vehicle is parked at a predetermined location; 4) whether the vehicle is within a predetermined range from the predetermined location; 5) whether the current time is within a predetermined time period every day; 6) whether the vehicle has been authorized to receive true value annotation information.

[0038] The determination module 13 can select a truth value trigger condition from the multiple truth value trigger conditions based on one or more of the following: 1) the brand of the vehicle, for example, different OEMs have different standards for when or where to obtain truth value annotation information; 2) the region or city where the vehicle is located, for example, there are differences in the deployment of the Internet of Vehicles in different regions or different cities, so the most suitable time and place for sending the truth value can be selected for the region or city where the vehicle is currently located; 3) the vehicle usage habits of the vehicle user (i.e., the end user), for example, the vehicle user may be accustomed to driving the vehicle early in the morning and using it frequently, and driving the vehicle back to the garage at night. At this time, it is suitable to perform the sending and receiving operations of the truth value annotation information every night.

[0039] According to an embodiment of the present invention, it is advantageous to adopt the strategy in the above-mentioned box 410. This is because there is a situation where, after requesting the true value labeling information, that is, after sending the first trigger message, the vehicle immediately leaves the location where the request is sent and enters a driving area or driving state that is not suitable for receiving a large amount of data, and it is necessary to wait for the vehicle to enter a suitable receiving location and receiving state before receiving the true value labeling information. In such a situation, the strategy in box 410 can cope with it well.

[0040] In block 412 , the determination module 13 determines whether the selected true trigger condition is satisfied.

[0041] If the result of the determination in block 412 is “No”, that is, the selected true value trigger condition is not satisfied, the determination operation in block 412 continues to be executed without executing subsequent operations.

[0042] If the judgment result in block 412 is “yes”, that is, the selected true value trigger condition is satisfied, then the process proceeds to block 416 .

[0043] In block 416 , the communication module 11 sends a second trigger message. The second trigger message is used to trigger the sending of the true value annotation information generated at the roadside unit 20 .

[0044] In block 418 , the communication module 11 receives the ground truth annotation information.

[0045] According to an embodiment of the present invention, the true value annotation information can be sent from the roadside unit 20 to the vehicle-mounted device 10. The following sending method can also be adopted: the roadside device 20 stores the generated true value annotation information in the edge cloud 30 and the cloud server 40 in advance. The communication module 11 sends the second trigger message to the cloud server 40, and the cloud server 40 determines which edge cloud is currently most suitable (for example, closest to the vehicle) to send the true value annotation information to the vehicle, and performs corresponding scheduling so that the determined most suitable edge cloud sends the true value annotation information to the vehicle.

[0046] In block 420, the comparison module 14 compares the true value annotation information with the vehicle-side perception information. The comparison module 14 may compare the state parameters of the roadside perception object with the corresponding state parameters of the corresponding vehicle-side perception object. For example, the comparison module 14 compares the state parameters (e.g., moving speed) of the same category of the pedestrian object perceived by the roadside sensor with the state parameters of the same pedestrian object perceived by the vehicle-mounted sensor.

[0047] According to an embodiment of the present invention, the comparison step in box 420 has two modes, namely, a first comparison mode (also referred to as a roadside reference mode) and a second comparison mode (also referred to as a vehicle-side reference mode). In the first comparison mode, the comparison module 14 uses the true value annotation information generated by the roadside as a reference to determine the vehicle-side perception performance. In the second comparison mode, the comparison module 14 uses the perception information generated by the vehicle-side as a reference to determine the roadside perception performance.

[0048] In box 422, the evaluation module 15 evaluates the readiness of the true value annotation information and / or the accuracy of the vehicle-side perception information based on the comparison result, that is, evaluates the roadside perception performance and / or the vehicle-side perception performance.

[0049] In general, in the first comparison mode, the true value annotation information generated by the roadside is used as a reference. The further the vehicle-side perception information obtained by the vehicle-side deviates from the true value annotation information, the lower the accuracy of the vehicle-side perception information is evaluated, that is, the worse the vehicle-side perception performance is. In the second comparison mode, the vehicle-side perception information generated by the vehicle-side is used as a reference. The further the true value annotation information generated by the roadside deviates from the vehicle-side perception information, the lower the accuracy of the true value annotation information is evaluated, that is, the worse the roadside perception performance is.

[0050] The following takes the evaluation in the first comparison mode as an example to introduce an embodiment of the evaluation method. It can be understood that the evaluation example in the second comparison mode can be implemented in a similar manner, which will not be described in detail.

[0051] In one embodiment, a comprehensive evaluation score according to multiple evaluation indicators is calculated based on the comparison result between the state parameters of the roadside perception object and the state parameters of the corresponding vehicle-side perception object. Multiple evaluation indicators include, for example, object recognition accuracy and recall rate, object position accuracy, and object speed accuracy. Each evaluation indicator is scored separately, and the weighted average or arithmetic mean of the scores according to multiple evaluation indicators is calculated as the comprehensive evaluation score. The higher the comprehensive evaluation score, the higher the accuracy of the true value annotation information, that is, the better the roadside perception performance. It can be understood that multiple evaluation indicators can be adjusted or added based on specific application scenarios.

[0052] It can be seen that according to the embodiments of the present invention, the accuracy of vehicle-side perception information (i.e., executing the first comparison mode and obtaining vehicle-side perception performance), or the readiness of truth-value annotation information (i.e., executing the second comparison mode and obtaining road-side perception performance) can be obtained, and both the readiness of truth-value annotation information and the accuracy of vehicle-side perception information can be obtained (i.e., executing the first comparison mode and obtaining vehicle-side perception performance, and executing the second comparison mode and obtaining road-side perception performance). This approach is advantageous. Because if the truth value system (the truth value system is used to generate a truth-value annotation signal for verifying the perception results perceived by the vehicle-mounted sensor) is installed on the vehicle, only the perception performance of one vehicle can be obtained. Therefore, in order to obtain the vehicle-side perception performance, a truth value system needs to be installed for each vehicle. The solution for the interaction between the vehicle-side and the road-side according to the embodiments of the present invention can solve this problem. Moreover, according to the embodiments of the present invention, it is also possible to evaluate the perception performance of the truth value system on the road side. Therefore, the solution according to the embodiments of the present invention has the advantages of low cost and high efficiency.

[0053] Figure 5 A method 500 for sending true value annotation information according to an embodiment of the present invention is shown. The method 500 may be executed at the roadside unit 20 .

[0054] In block 502, the roadside unit 20 receives a first trigger message, which includes a timestamp. The above description of the first trigger message is also applicable here and will not be repeated.

[0055] In block 504, the truth value system in the roadside unit 20 generates the truth value annotation information at the timestamp. The above description of the truth value annotation information is also applicable here and will not be repeated.

[0056] In block 506, the roadside unit 20 receives the second trigger message. The above description of the second trigger message is also applicable here and will not be repeated.

[0057] In block 508 , the roadside unit 20 sends true value annotation information in response to receiving the second trigger message.

[0058] The present invention also provides a machine-readable storage medium storing executable instructions, which, when executed, enable one or more processors to perform the above method 400 or 500 .

[0059] It is to be understood that the processor can be implemented using electronic hardware, computer software or any combination thereof. Whether these processors are implemented as hardware or software will depend on specific application and the overall design constraints imposed on the system. As an example, the processor provided in the present invention, any part of the processor or any combination of the processor can be implemented as a microprocessor, a microcontroller, a digital signal processor (DSP), a field programmable gate array (FPGA), a programmable logic device (PLD), a state machine, a gate logic, a discrete hardware circuit and other suitable processing components configured to perform the various functions described in the present disclosure. The function of the processor provided in the present invention, any part of the processor or any combination of the processor can be implemented as software performed by a microprocessor, a microcontroller, a DSP or other suitable platforms.

[0060] It is to be understood that software should be broadly considered to represent instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software modules, applications, software applications, software packages, routines, subroutines, objects, running threads, processes, functions, etc. Software can reside in a computer-readable medium. A computer-readable medium can include, for example, a memory, which can be, for example, a magnetic storage device (e.g., a hard disk, a floppy disk, a magnetic stripe), an optical disk, a smart card, a flash memory device, a random access memory (RAM), a read-only memory (ROM), a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), a register, or a removable disk. Although the memory is shown as being separated from the processor in the various aspects provided in the present disclosure, the memory can also be located inside the processor (e.g., a cache or a register).

[0061] Although some embodiments have been described above, these embodiments are given by way of example only and are not intended to limit the scope of the invention. The appended claims and their equivalents are intended to cover all modifications, substitutions and changes made within the scope and spirit of the invention.

Claims

1. A vehicle-mounted device for an intelligent transportation system, comprising: A communication module is configured to send a first trigger message to a roadside unit, the first trigger message comprising a timestamp, the first trigger message being used to trigger the roadside unit to generate true value annotation information corresponding to the timestamp, the true value annotation information comprising state information of one or more roadside perception objects obtained by the roadside sensor sensing the surrounding environment, and the communication module is further configured to receive the true value annotation information when a predetermined true value trigger condition is met; An acquisition module, which acquires vehicle-side perception information, which includes state information of one or more vehicle-side perception objects obtained by the vehicle-mounted sensor sensing the surrounding environment; A comparison module, configured to compare the true value annotation information with the vehicle-side perception information to obtain a comparison result; and An evaluation module is configured to evaluate the accuracy of the true value annotation information and / or the accuracy of the vehicle-side perception information based on the comparison result.

2. The vehicle-mounted device according to claim 1, wherein: The comparison module has: A first comparison mode, in which the true value annotation information is used as a reference so that the evaluation module can evaluate the accuracy of the vehicle-side perception information; as well as The second comparison mode, in this mode, the vehicle-side perception information is used as a reference so that the evaluation module can evaluate the accuracy of the true value annotation information.

3. The vehicle-mounted device according to claim 1 or 2, wherein: The first trigger message also includes: The location of the vehicle at the timestamp; A unique identifier of the first trigger message; and Unique identifier of this vehicle.

4. The vehicle-mounted device according to any one of claims 1 to 3, wherein: The state information of the one or more roadside perception objects includes a state parameter indicating the state of each roadside perception object; and The status information of the one or more vehicle-side perception objects includes status parameters representing each vehicle-side perception object.

5. The vehicle-mounted device according to claim 4, wherein: The state parameters of the state of each roadside perception object and the state parameters of each vehicle-side perception object respectively include any one or more of the following parameters: The object type, which includes motor vehicles, non-motor vehicles, pedestrians, animals, or roadside facilities; Object size, which includes the object's length, width, and height; The object shape includes square, cone, or cylinder; the object's location at the timestamp, including longitude, latitude, and altitude coordinates; the object's velocity at said timestamp; the acceleration of the object at said timestamp; The motion trend at the timestamp includes a predicted motion trajectory of the object within a predetermined time period after the timestamp.

6. The vehicle-mounted device according to any one of claims 1 to 5, wherein: The communication module receives the true value labeling information from the roadside unit; or The communication module receives the true value annotation information from an edge cloud that is communicatively connected to the vehicle and the roadside unit.

7. The vehicle-mounted device according to any one of claims 1 to 6, wherein: The true value trigger condition includes the following multiple predetermined true value trigger conditions: Whether the vehicle is parked; Whether the remaining power or fuel level of the vehicle exceeds the corresponding predetermined threshold; Whether the vehicle is parked at the designated location; whether the vehicle is located within a predetermined range from the predetermined location; Whether the current time is in the scheduled time period of each day; and Whether the vehicle has been authorized to receive information.

8. The vehicle-mounted device according to claim 7, further comprising a determination module configured to: Determining whether the communication module receives a response signal from the roadside unit within a predetermined time after the first trigger message is sent; If yes, selecting a true value trigger condition from the plurality of predetermined true value trigger conditions; Further determining whether the selected true value trigger condition is satisfied; as well as If yes, the communication module sends a second trigger message to the roadside unit so that the roadside unit sends the true value labeling information to the vehicle.

9. The vehicle-mounted device according to claim 8, wherein: The determination module is also configured to: If it is determined that no response signal is received from the roadside unit within a predetermined period of time after the first trigger message is sent, no subsequent operation is performed.

10. The vehicle-mounted device according to claim 4, wherein: The evaluation module is further configured to: generate an evaluation report based on the comparison result, which includes a comprehensive score based on multiple evaluation indicators, Among them, the multiple evaluation indicators include object recognition accuracy and recall rate, object position accuracy, and object speed accuracy obtained based on comparison between object parameters of roadside perception objects and object parameters of corresponding vehicle-side perception objects.

11. A roadside unit for an intelligent transportation system, comprising a truth value system, wherein the roadside unit is configured to: receiving a first trigger message including a timestamp; In response to receiving the first trigger message, generating, by the truth value system, truth value annotation information corresponding to the timestamp; receiving a second trigger message; as well as In response to receiving a second trigger message, sending the true value annotation information; The true value annotation information includes: A timestamp, which is consistent with the timestamp included in the first trigger message; a response identifier corresponding to the unique identifier of the first trigger message; A vehicle identifier, which is consistent with the unique identifier of the vehicle included in the first trigger message; and The state information of one or more roadside perception objects obtained by the roadside sensors sensing the surrounding environment.

12. A method for evaluating perception information, optionally performed by a vehicle-mounted device according to any one of claims 1 to 10, the method comprising: Sending a first trigger message to a roadside unit, the first trigger message comprising a timestamp, wherein the first trigger message is used to trigger the roadside unit to generate true value annotation information corresponding to the timestamp, the true value annotation information comprising state information of one or more roadside perception objects obtained by the roadside sensor sensing the surrounding environment, Acquire vehicle-side perception information, which includes state information of one or more vehicle-side perception objects obtained by the vehicle-mounted sensor sensing the surrounding environment; When a predetermined truth value trigger condition is met, receiving the truth value annotation information; Comparing the true value annotation information with the vehicle-side perception information to obtain a comparison result; as well as The accuracy of the true value annotation information and / or the accuracy of the vehicle-side perception information is evaluated based on the comparison result.

13. A method for sending true value annotation information, optionally performed by the roadside unit according to claim 11, the method comprising: receiving a first trigger message including a timestamp; In response to receiving the first trigger message, generating true value annotation information corresponding to the timestamp; receiving a second trigger message; as well as In response to receiving a second trigger message, sending the true value annotation information; The true value annotation information includes: A timestamp, which is consistent with the timestamp included in the first trigger message; a response identifier corresponding to the unique identifier of the first trigger message; A vehicle identifier, which is consistent with the unique identifier of the vehicle included in the first trigger message; and The state information of one or more roadside perception objects obtained by the roadside sensors sensing the surrounding environment.

14. An intelligent transportation system, comprising: The vehicle-mounted device according to any one of claims 1 to 10; The roadside unit according to claim 11; as well as An edge cloud and a cloud server capable of being communicatively connected with the vehicle-mounted device and the roadside unit.

15. A machine-readable storage medium storing executable instructions which, when executed, cause one or more processors to perform the method of claim 12 or 13.

Images