Correction method for roadside sensing-based positioning

Abstract

A correction method for roadside sensing-based positioning, a computer-readable storage medium and an electronic apparatus. The method comprises: acquiring sensing-based positioning information of the current trajectory point of a traffic participant and sensing-based positioning information of first historical trajectory points of the traffic participant (S301); determining, among the first historical trajectory points, a target historical trajectory point matching the current trajectory point (S302); on the basis of sensing-based positioning information of the target historical trajectory point, acquiring a positioning deviation value of the target historical trajectory point (S303); and on the basis of the positioning deviation value, correcting the sensing-based positioning information of the current trajectory point (S304).

Description

Correction method for roadside perception positioning

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS

[0002] The present disclosure is based on and claims the priority of Chinese patent application No. 202410170945.1 filed on February 6, 2024, and all the disclosed contents are incorporated into the present disclosure by reference. Technical Field

[0003] The embodiments of the present disclosure relate to the field of communications, and in particular, to a correction method for roadside sensing and positioning. Background Art

[0004] In the vehicle-road cooperative roadside system, the roadside is equipped with sensors and computing units to form a perception system. It uses AI and other technologies to identify and locate vehicles, pedestrians, obstacles, etc. on the road, and sends this information to the vehicle side through v2x communication. The vehicle side obtains information about traffic participants on the road, thereby achieving obstacle avoidance and improving traffic safety.

[0005] Achieving advanced autonomous driving through roadside perception requires high-precision roadside perception information, which can accurately locate individual traffic participants. Currently, perception system vendors generally have positioning errors exceeding 1.5 meters, resulting in low accuracy in roadside perception of traffic participants, making this level of positioning inaccurate and insufficient for advanced autonomous driving. Summary of the Invention

[0006] According to one embodiment of the present disclosure, a method for correcting roadside perception positioning is provided, including: obtaining perception positioning information of a current trajectory point of a traffic participant and perception positioning information of a first historical trajectory point; determining a target historical trajectory point in the first historical trajectory point that matches the current trajectory point; obtaining a positioning deviation value of the target historical trajectory point based on the perception positioning information of the target historical trajectory point; and correcting the perception positioning information of the current trajectory point based on the positioning deviation value.

[0007] According to another embodiment of the present disclosure, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when running.

[0008] According to another embodiment of the present disclosure, an electronic device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to perform the steps in any one of the above method embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] FIG1 is a hardware structure block diagram of a mobile terminal for a method for correcting roadside sensing and positioning according to an embodiment of the present disclosure;

[0010] FIG2 is a system architecture diagram of a method for correcting roadside perception positioning according to an embodiment of the present disclosure;

[0011] FIG3 is a flow chart of a method for correcting roadside perception positioning according to an embodiment of the present disclosure;

[0012] FIG4 is a schematic diagram of historical roadside perception trajectories and historical real trajectories of traffic participants according to an embodiment of the present disclosure;

[0013] FIG5 is a schematic diagram of a time axis of a historical perception trajectory and a real trajectory according to an embodiment of the present disclosure;

[0014] FIG6 is a timeline diagram of another historical perception trajectory and real trajectory according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0015] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the accompanying drawings and in conjunction with embodiments.

[0016] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0017] Currently, manufacturers of roadside perception systems generally have significant positioning errors, which cannot support high-level autonomous driving. This problem is caused by many factors, including sensor accuracy, fusion algorithm maturity, and calibration accuracy. Although various manufacturers are continuously optimizing and improving their systems, rapid improvement is still not possible in the short term.

[0018] Based on this, this paper proposes a method for correcting roadside perception positioning. This method uses the V2X roadside system to pre-store the positioning deviation values ​​of the motion trajectory perception information and target true value information of all trajectory points of traffic participants. When the current perception position matches the historical perception target position, the positioning deviation value corresponding to the historical perception target position is used to correct the current perception position. Based on this positioning deviation value, the perception position of each target can be accurately corrected, thereby significantly improving positioning accuracy and enhancing market competitiveness. Furthermore, the solution adopted in this paper is simple to implement and low-cost.

[0019] The method embodiments provided in the embodiments of the present disclosure can be executed in a mobile terminal, a computer terminal or a similar computing device. Taking running on a computer terminal as an example, FIG1 is a hardware structure block diagram of a mobile terminal of a roadside perception positioning correction method in an embodiment of the present disclosure. As shown in FIG1 , the computer terminal may include one or more (only one is shown in FIG1 ) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, wherein the above-mentioned computer terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that the structure shown in FIG1 is only for illustration and does not limit the structure of the above-mentioned computer terminal. For example, the computer terminal may also include more or fewer components than those shown in FIG1 , or have a configuration different from that shown in FIG1 .

[0020] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the correction method for roadside sensing positioning in the embodiment of the present disclosure. The processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, that is, implementing the above-mentioned method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0021] The transmission device 106 is used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by a computer terminal's communications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0022] Figure 2 is a system architecture diagram of the correction method of roadside perception positioning according to an embodiment of the present disclosure. The embodiment of the present disclosure can run on the system architecture shown in Figure 2. As shown in Figure 2, the system architecture may include: a roadside perception system, a roadside device (Road Side Unit, RSU), a V2X terminal (such as an on-board unit (OBU)), a calibration program, etc.

[0023] The roadside perception system may include roadside sensors and an AI computing unit. The roadside sensors can be used to collect perception information about the trajectory points of traffic participants and can be connected to the AI ​​computing unit via a wired connection. Roadside sensors may include radar, cameras, and other devices.

[0024] RSU, RSU can communicate directly with the V2X terminal through the direct communication interface (Proximity Communication5, PC5); RSU can receive BSM messages and PSM messages sent by the V2X terminal, and transmit the BSM messages and PSM messages to the calibration program.

[0025] The V2X terminal can be equipped with the Global Navigation Satellite System (GNSS) and Real-time kinematic (RTK), which can support high-precision positioning and Global Positioning System (GPS) timing, and the RSU can support GPS timing.

[0026] The calibration program is a software part that can run in the RSU, AI computing unit, or other roadside equipment. The calibration program can be connected to the AI ​​computing unit and RSU respectively. The calibration program can use IP communication or inter-process communication with the AI ​​computing unit and RSU respectively.

[0027] The calibration program can receive BSM messages and PSM messages transmitted by the RSU device, and obtain real information such as the time, longitude and latitude, type of traffic participant, speed, track angle, etc. of the traffic participants from the BSM messages and PSM messages to obtain real data of different trajectory points; it can receive the perception data of the trajectory points transmitted by the AI ​​computing unit, and perform clock alignment based on the perception trajectory points, calculate and save the positioning deviation value of each perception trajectory point; the positioning deviation value of the trajectory point can be used to match the current target perception position, obtain the corresponding deviation value, correct the current positioning, and return it to the roadside perception system.

[0028] It should be noted that the calibration program in the embodiment of the present disclosure can run in the roadside perception system, can run in the RSU unit, or can run independently of the roadside perception system and RSU in other modules. The embodiment of the present disclosure does not limit this.

[0029] In this embodiment, a method for correcting roadside sensing and positioning is provided, which runs on the above-mentioned computer terminal or network architecture. FIG3 is a flow chart of the method for correcting roadside sensing and positioning according to an embodiment of the present disclosure. As shown in FIG3 , the flow chart includes the following steps:

[0030] Step S301: Acquire the perception positioning information of the current trajectory point of the traffic participant and the perception positioning information of the first historical trajectory point.

[0031] In an embodiment of the present invention, each trajectory point may include a perceptual positioning information.

[0032] As an example, the perception positioning information of the trajectory point of each traffic participant can be obtained in real time from the roadside perception system, for example, the perception positioning latitude and longitude (Lng0, Lat0) of the trajectory point.

[0033] As an example, data on roadside traffic participants can be obtained from the roadside perception system, and the trajectories of all roadside traffic participants can be obtained and saved. Trajectories are composed of many track points, and the perception location information for each track point can include time, longitude and latitude, traffic participant type, speed, track angle, and more.

[0034] For example, the perception positioning information of the first historical trajectory point may be obtained from the roadside perception system, wherein the first historical trajectory point may be a historical trajectory point of the same traffic participant type as the current trajectory point.

[0035] In an exemplary embodiment, obtaining the sensory positioning information of the first historical trajectory point includes:

[0036] Acquire the perception and positioning information of the second historical trajectory point, and acquire the perception and positioning information of the first historical trajectory point of the same traffic participant type as the current trajectory point from the perception and positioning information of the second historical trajectory point.

[0037] As an example, the second historical trajectory point can be a collection of historical trajectory points of various types of traffic participants stored by the roadside perception system. From the second historical trajectory points, a trajectory point of the same type as the currently perceived traffic participant can be selected, i.e., the first historical trajectory point, to obtain the perception location information for the first historical trajectory point.

[0038] In an exemplary embodiment, acquiring the perception positioning information of the first historical trajectory point of the same traffic participant type as the current trajectory point from the perception positioning information of the second historical trajectory point includes:

[0039] Filtering the second historical trajectory points based on one or more of a preset positioning range, a preset time range, and a preset confidence level of the second real positioning information;

[0040] The perception positioning information of the first historical trajectory point of the same traffic participant type as the current trajectory point is obtained from the filtered perception positioning information of the second historical trajectory point.

[0041] In the embodiment of the present invention, the number and type of historical trajectory points may be various. The amount of perception positioning information data of the historical trajectory points is huge, which may cause storage and calculation problems. Therefore, it is necessary to filter the historical trajectory points.

[0042] As an example, the screening condition may include one or more of a preset positioning range, a preset time range, and a preset confidence level of the second real positioning information.

[0043] For example, preset positioning range: set a certain position range, if the target position is within this range, it will be saved, and data outside this position range will not be saved;

[0044] Preset time range: track points within a certain time period before the current moment, expired data will be destroyed;

[0045] Preset one or more of the confidence levels of the second real positioning information: Set the BSM or PSM position confidence level. For receiving BSM or PSM data, the position confidence level of the traffic participant is a certain value or above. For example, if the set value is 0.5 meters, if the confidence level is 0.5 meters, 0.2 meters, or 0.1 meters, it will be saved. If the confidence level is 1 meter, 5 meters, etc., it will not be saved.

[0046] Exemplarily, the second historical trajectory point can be filtered based on one or more of a preset positioning range, a preset time range, and a preset confidence level of the second real positioning information, and the perceived positioning information of the first historical trajectory point of the same traffic participant type as the current trajectory point can be obtained from the perceived positioning information of the filtered second historical trajectory point.

[0047] Step S302: Determine a target historical trajectory point in the first historical trajectory point that matches the current trajectory point.

[0048] In addition, roadside sensor acquisition and calculations often experience delays. For example, camera acquisition often experiences a 100ms delay, while AI calculations require 20ms. Therefore, it is necessary to consider these sensor acquisition and calculation delays. A delay offset value can be pre-set. For example, if the delay offset value is set to 120ms, the timestamp of each perceived positioning information minus 120ms is the actual timestamp of the perceived positioning information. The delay offset value can be preset based on specific circumstances and is not limited in this embodiment of the present invention.

[0049] In an exemplary embodiment, step S302 includes:

[0050] Step S3021: Calculate the distance between the current trajectory point and the first historical trajectory point based on the sensing positioning information of the current trajectory point and the sensing positioning information of the first historical trajectory point;

[0051] Step S3022: Determine, from the first historical trajectory points, a trajectory point whose distance is less than a preset distance as a target historical trajectory point that matches the current trajectory point.

[0052] As an example, the absolute distance between the current track point and the filtered first historical track point may be calculated based on the perception positioning information of the current track point and the perception positioning information of the first historical track point.

[0053] If the calculated absolute distance is less than the preset distance, it can be considered that the current trajectory point successfully matches the first historical trajectory point, and one or more target historical trajectory points can be screened out.

[0054] If the first historical trajectory point is not matched, the target type screening condition can be relaxed (for example, pedestrians, filtering pedestrians and non-motor vehicles), or the preset value of the absolute distance can be increased and the first historical trajectory point can be matched again.

[0055] Step S303: Acquire a positioning deviation value of the target historical trajectory point according to the sensed positioning information of the target historical trajectory point.

[0056] As an example, the positioning deviation value corresponding to each historical trajectory point may be pre-stored. When determining the target historical trajectory point, the positioning deviation value of the target historical trajectory point may be obtained based on the perceived positioning information of the target historical trajectory point.

[0057] Step S304: Correct the perceived positioning information of the current trajectory point according to the positioning deviation value.

[0058] In the embodiment of the present invention, the perceived positioning information of the current trajectory point can be corrected according to the positioning deviation value.

[0059] For example, if the longitude of the current track point before correction is Lng0 and the positioning deviation value is Abbr(Lng), then the longitude after correction is: Lng0+Abbr(Lng); if the latitude of the current track point before correction is Lat0 and the positioning deviation value is Abbr(Lat), then the latitude after correction is Lat0+Abbr(Lat).

[0060] In an exemplary embodiment, the correcting the perceived positioning information of the current trajectory point according to the positioning deviation value includes:

[0061] In the case where there are multiple first historical trajectory points, an average positioning deviation value of the positioning deviation values ​​of the multiple first historical trajectory points is calculated; and the perceived positioning information of the current trajectory point is corrected according to the average positioning deviation value.

[0062] As an example, the first historical trajectory point may be one or more. If there are multiple first historical trajectory points, an average positioning deviation value of the positioning deviation values ​​of the multiple first historical trajectory points may be calculated, and the perceived positioning information of the current trajectory point may be corrected based on the average positioning deviation value.

[0063] As an example, the average positioning deviation value may include an average longitude deviation and an average latitude deviation, and the average longitude deviation and the average latitude deviation may be calculated separately.

[0064] For example, the average longitude deviation is calculated by calculating the average longitude deviation of the first historical track point: Abbr(Lng) = (Abbr(Lng1) + Abbr(Lng2) + Abbr(Lng3) + ... + Abbr(LngN)) / N

[0065] Average latitude deviation, calculate the average latitude deviation of the first historical track point: Abbr(Lat)=(Abbr(Lat1)+Abbr(Lat2)+Abbr(Lat3)+...+Abbr(LatN)) / N

[0066] As an example, if the values ​​of Abbr(Lng) and Abbr(Lat) are both smaller than a preset positioning deviation threshold, it can be considered that the deviation value is negligible and does not need to be corrected.

[0067] In an embodiment of the present invention, the sensory positioning information of a traffic participant's current trajectory point and the sensory positioning information of a first historical trajectory point are obtained; a target historical trajectory point matching the current trajectory point is determined within the first historical trajectory point; a positioning deviation value of the target historical trajectory point is obtained based on the sensory positioning information of the target historical trajectory point; and the sensory positioning information of the current trajectory point is corrected based on the positioning deviation value. Based on this positioning deviation value, the sensory positioning of each trajectory point can be accurately corrected, resolving the low accuracy of roadside sensory positioning of traffic participants in related technologies. This significantly improves positioning accuracy and enhances market competitiveness. Furthermore, the solution adopted in the present disclosure is simple to implement and low-cost.

[0068] In an exemplary embodiment, before step S301, the method further includes:

[0069] Acquire first real positioning information corresponding to the perceived positioning information of the first historical trajectory point; and determine a positioning deviation value corresponding to the historical first perceived positioning information based on the perceived positioning information of the first historical trajectory point and the first real positioning information.

[0070] As an example, the real positioning information may refer to the time, longitude and latitude, type of traffic participant, speed, track angle and other information of the traffic participant obtained by the roadside terminal from the BSM or PSM message of the V2X terminal.

[0071] Exemplarily, first real positioning information corresponding to the perceived positioning information of the first historical trajectory point may be obtained, and a positioning deviation value corresponding to the first historical perceived positioning information may be determined based on the perceived positioning information of the first historical trajectory point and the first real positioning information.

[0072] In an exemplary embodiment, obtaining first real positioning information corresponding to the perceived positioning information of the first historical trajectory point includes:

[0073] Obtain second real positioning information of a second historical trajectory point of a traffic participant; and obtain the first real positioning information for the first timestamp from the second real positioning information based on the first timestamp of the perceived positioning information of the first historical trajectory point.

[0074] As an example, a V2X terminal can receive BSM or PSM messages periodically sent by traffic participants through V2X communication, obtain the actual driving trajectories of all traffic participants, and save them. The V2X terminal can communicate with the RSU through the PC5 port, and the RSU receives BSM or PSM messages sent by the V2X terminal.

[0075] As an example, the time, longitude and latitude, type of traffic participant, speed, track angle and other information of the traffic participant can be obtained from the BSM or PSM message, that is, the real positioning information of the traffic participant can be obtained.

[0076] As an example, the second real positioning information of the second historical trajectory point may refer to the real positioning information of historical trajectory points of various types of traffic participants.

[0077] For example, the second real positioning information of the second historical trajectory point of the traffic participant can be obtained, and the first real positioning information for the first timestamp can be obtained from the second real positioning information according to the first timestamp of the perceived positioning information of the first historical trajectory point.

[0078] In an exemplary embodiment, the timestamp of the first real positioning information is close to and earlier than the first timestamp; and determining, based on the perceived positioning information of the first historical trajectory point and the first real positioning information, a positioning deviation value corresponding to the historical first perceived positioning information includes:

[0079] Predicting third real positioning information at the first timestamp based on the first real positioning information and the first timestamp;

[0080] According to the third real positioning information and the perceived positioning information of the first historical trajectory point, a positioning deviation value corresponding to the historical first perceived positioning information is determined and saved.

[0081] As an example, the timestamp of the first real positioning information may be a timestamp that is close to the first timestamp and earlier than the first timestamp.

[0082] As an example, the first timestamp of the perceived positioning information of the first historical trajectory point can be used as a reference to predict the third real positioning information at the same moment.

[0083] Exemplarily, the positioning deviation value corresponding to the historical first perceived positioning information can be determined and saved based on the third real positioning information and the perceived positioning information of the first historical trajectory point.

[0084] In an exemplary embodiment, obtaining the first real positioning information for the first timestamp from the second real positioning information includes:

[0085] Filtering the second historical trajectory points based on one or more of a preset positioning range, a preset time range, and a preset confidence level of the second real positioning information;

[0086] The first real positioning information for the first timestamp is obtained from the second real positioning information of the second historical trajectory point after filtering.

[0087] In the embodiment of the present invention, the number and type of historical trajectory points may be various. The amount of perception positioning information data of the historical trajectory points is huge, which may cause storage and calculation problems. Therefore, it is necessary to filter the historical trajectory points.

[0088] As an example, the screening condition may include one or more of a preset positioning range, a preset time range, and a preset confidence level of the second real positioning information.

[0089] For example, preset positioning range: set a certain position range, if the target position is within this range, it will be saved, and data outside this position range will not be saved;

[0090] Preset time range: track points within a certain time period before the current moment, expired data will be destroyed;

[0091] Preset one or more of the confidence levels of the second real positioning information: Set the BSM or PSM position confidence level. For receiving BSM or PSM data, the position confidence level of the traffic participant is a certain value or above. For example, if the set value is 0.5 meters, if the confidence level is 0.5 meters, 0.2 meters, or 0.1 meters, it will be saved. If the confidence level is 1 meter, 5 meters, etc., it will not be saved.

[0092] As an example, the first real positioning information for the first timestamp may be obtained from the second real positioning information of the second historical trajectory point after filtering.

[0093] The calculation process of the positioning deviation value of the historical trajectory point in the embodiment of the present disclosure is further illustrated below through an example.

[0094] Example 1

[0095] Figure 4 is a schematic diagram of the historical roadside perception trajectories and historical actual trajectories of a traffic participant according to an embodiment of the present disclosure. If the two trajectories are of the same type and the timestamp difference, distance difference, heading angle difference, and speed difference are within a certain preset range, the two trajectories can be considered to belong to the same traffic participant. Based on the perceived positioning information and actual positioning information of the traffic participant's trajectory points, a mapping relationship can be found for all trajectory points in the two types of trajectories. As shown in Figure 4, the actual trajectory of the traffic participant can be L1, and the roadside perception trajectory of the traffic participant can be L2.

[0096] The positioning deviation value of each trajectory point between the historical roadside perception trajectory point and the historical real trajectory point can be calculated and saved. Specifically, the following steps may be included:

[0097] Step 1: Find the real trajectory point closest to the timestamp of each historical perception trajectory point.

[0098] FIG5 is a schematic diagram of the time axis of the historical perception trajectory and the real trajectory according to an embodiment of the present disclosure. As shown in FIG5 , a trajectory point A of the roadside perception trajectory L2 can be taken, wherein the perception positioning information of the trajectory point A may include the timestamp T(A), position P(A), speed V(A), track angle Etc., find the track point B that is closest in time and earlier than T(A) in the real track L1, where the real positioning information of track point B may include timestamp T(B), position P(B), speed V(B), track angle wait.

[0099] As shown in FIG5 , on the time axis, we can find the trajectory point B whose real trajectory point moment is closest to the perceived trajectory point A.

[0100] Step 2: Based on the timestamp of track point A, calculate the position of track point B' of the real track at the same moment.

[0101] FIG6 is a timeline diagram of another historical perception trajectory and real trajectory according to an embodiment of the present disclosure. As shown in FIG6 , the starting position (x(B), y(B)), speed (V), and track angle of point B of the trajectory can be calculated. The time difference (T(A)-T(B)) is used to calculate the longitude and latitude of the position P(B') of the L1 trajectory point at time T(A):

[0102] Then convert the estimated position into longitude and latitude coordinates.

[0103] Step 3: Calculate the positioning deviation between the trajectory point A of the perceived trajectory and the trajectory point B' of the true trajectory.

[0104] Calculate the position deviation between position A and position B'. The position deviation can be an offset of longitude and latitude, including longitude deviation and latitude deviation.

[0105] Abbr(Lng) = B's longitude - A's longitude

[0106] Abbr(Lat) = B' position dimension value - A position dimension value

[0107] Step 4: Save the positioning deviation value of each trajectory point in the historical trajectory.

[0108] According to the above steps 1-3, the positioning deviation value of each track point of the perception track can be calculated and saved. For example, the data can be saved according to the (P(A), Abbr(Lng), Abbr(Lat)) mapping relationship.

[0109] This example calculates and saves the positioning deviation values ​​of the trajectory points of the perceived trajectory and the trajectory points of the actual trajectory, so that the perceived positioning of each trajectory point can be accurately corrected based on the positioning deviation value, thereby greatly improving the positioning accuracy and having strong market competitiveness. In addition, the solution adopted in this disclosure is simple to implement and low-cost.

[0110] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus the necessary general hardware platform, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), including a number of instructions for enabling a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in each embodiment of the present disclosure.

[0111] An embodiment of the present disclosure further provides a computer-readable storage medium, in which a computer program is stored. The computer program is configured to execute the steps of any one of the above method embodiments when run.

[0112] In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to, various media that can store computer programs, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0113] An embodiment of the present disclosure further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0114] In an exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0115] For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary implementation modes, and this embodiment will not be described in detail here.

[0116] Obviously, those skilled in the art should understand that the modules or steps of the present disclosure described above can be implemented using a general-purpose computing device, they can be concentrated on a single computing device, or distributed across a network composed of multiple computing devices, they can be implemented using program code executable by the computing device, and thus, they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be performed in a different order than herein, or they can be fabricated into separate integrated circuit modules, or multiple modules or steps can be fabricated into a single integrated circuit module for implementation. Thus, the present disclosure is not limited to any particular combination of hardware and software.

[0117] The foregoing is merely an exemplary embodiment of the present disclosure and is not intended to limit the present disclosure. Those skilled in the art will readily appreciate that the present disclosure is susceptible to various modifications and variations. Any modifications, equivalent substitutions, improvements, and the like made within the principles of the present disclosure shall be included within the scope of protection of the present disclosure.

Claims

1. A method for correcting roadside sensing positioning, comprising: Obtaining the perception and positioning information of the current trajectory point of the traffic participant and the perception and positioning information of the first historical trajectory point; Determining a target historical trajectory point in the first historical trajectory point that matches the current trajectory point; Obtaining a positioning deviation value of the target historical trajectory point based on the perceived positioning information of the target historical trajectory point; Correct the perceived positioning information of the current trajectory point according to the positioning deviation value.

2. The method according to claim 1, wherein The determining a target historical trajectory point in the first historical trajectory point that matches the current trajectory point includes: Calculating the distance between the current trajectory point and the first historical trajectory point based on the sensing positioning information of the current trajectory point and the sensing positioning information of the first historical trajectory point; A trajectory point whose distance is less than a preset distance is determined from the first historical trajectory points as a target historical trajectory point that matches the current trajectory point.

3. The method according to claim 1, wherein Before obtaining the perception positioning information of the current trajectory point of the traffic participant and the perception positioning information of the first historical trajectory point, the method further includes: Acquire first real positioning information corresponding to the perceived positioning information of the first historical trajectory point; A positioning deviation value corresponding to the first historical perceived positioning information is determined according to the perceived positioning information of the first historical trajectory point and the first real positioning information.

4. The method according to claim 3, wherein: The acquiring of first real positioning information corresponding to the perceived positioning information of the first historical trajectory point includes: Obtaining second real positioning information of a second historical trajectory point of the traffic participant; According to the first timestamp of the perceived positioning information of the first historical trajectory point, the first real positioning information corresponding to the first timestamp is obtained from the second real positioning information.

5. The method according to claim 4, wherein The timestamp of the first real positioning information is close to and earlier than the first timestamp; The determining, based on the perceived positioning information of the first historical trajectory point and the first real positioning information, a positioning deviation value corresponding to the historical first perceived positioning information includes: Predicting third real positioning information at the first timestamp based on the first real positioning information and the first timestamp; According to the third real positioning information and the perceived positioning information of the first historical trajectory point, a positioning deviation value corresponding to the historical first perceived positioning information is determined and saved.

6. The method according to claim 4, wherein: The acquiring the first real positioning information for the first timestamp from the second real positioning information includes: Filtering the second historical trajectory points based on one or more of a preset positioning range, a preset time range, and a preset confidence level of the second real positioning information; The first real positioning information for the first timestamp is obtained from the second real positioning information of the second historical trajectory point after filtering.

7. The method according to claim 1, wherein The acquiring of the sensory positioning information of the first historical trajectory point includes: Acquire the perception and positioning information of the second historical trajectory point, and acquire the perception and positioning information of the first historical trajectory point of the same traffic participant type as the current trajectory point from the perception and positioning information of the second historical trajectory point.

8. The method according to claim 7, wherein: The acquiring, from the perception positioning information of the second historical trajectory point, the perception positioning information of the first historical trajectory point of the same traffic participant type as the current trajectory point, includes: Filtering the second historical trajectory points based on one or more of a preset positioning range, a preset time range, and a preset confidence level of the second real positioning information; The perception positioning information of the first historical trajectory point of the same traffic participant type as the current trajectory point is obtained from the filtered perception positioning information of the second historical trajectory point.

9. The method according to claim 1, wherein The correcting the perceived positioning information of the current trajectory point according to the positioning deviation value includes: In the case where there are multiple first historical trajectory points, calculating an average positioning deviation value of the positioning deviation values of the multiple first historical trajectory points; Correct the perceived positioning information of the current trajectory point according to the average positioning deviation value.

10. A computer-readable storage medium having a computer program stored therein, wherein: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

11. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 9 when executing the computer program.

Images