Stop line fusion method and system, electronic equipment and storage medium

By calculating and filtering the direction vector and confidence of the stop line, the problem of large errors in stop line fusion in severe weather by autonomous driving vehicles is solved, improving driving accuracy and safety, and improving user experience.

CN119027764APending Publication Date: 2024-11-26WUHAN ZHONGHAITING DATA TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202410918400.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-10
Publication Date
2024-11-26

AI Technical Summary

Technical Problem

In severe weather conditions, when the sensor of the autonomous driving vehicle fails, multiple collections of stop lines lead to large fusion errors, affecting the accuracy of driving decisions, and the prior art has failed to effectively reduce this error.

Method used

By calculating the direction vector and confidence of each acquisition stop line, the stop lines with confidence greater than the preset threshold are filtered for fusion, and the fused stop lines are generated to eliminate data points with low confidence.

Benefits of technology

It improves the accuracy of the stop line in autonomous driving scenarios, enhances the safety of the vehicle driving process, and improves the user's ride experience.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119027764A_ABST
    Figure CN119027764A_ABST
Patent Text Reader

Abstract

The invention provides a stop line fusion method and system, electronic equipment and a storage medium, and the method comprises the steps: obtaining a collection data set of a target stop line, and obtaining a plurality of collection stop lines; calculating a direction vector of each collection stop line to obtain a direction vector set; based on the direction vector set, calculating confidence coefficients corresponding to the plurality of collection stop lines; and fusing the collection stop lines of which the confidence coefficients are greater than a preset confidence coefficient threshold value to generate fused stop lines. According to the method, the confidence coefficients of the multiple collection stop lines are calculated, so that the collection stop lines with the confidence coefficients lower than the preset threshold value in the stop lines collected for multiple times are removed, the accuracy of the target stop line in the automatic driving scene is greatly improved, and then the safety in the vehicle driving process is greatly improved; and the riding and driving experience of the user is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and more specifically, to a stop line fusion method, system, electronic device and storage medium. Background Art

[0002] In the field of autonomous driving, in order to accurately control vehicle driving, it is often necessary to draw high-precision maps. The ground marking data drawn by high-precision maps, each ground marking graphic represents a different physical meaning, which directly participates in the driving decision of the autonomous vehicle. When the sensors of the autonomous vehicle fail due to severe weather such as heavy fog, hail, and heavy rain, the vehicle can make driving decisions based on the ground marking data in the known high-precision map.

[0003] Among them, due to the factors such as equipment in the process of fusion, the stop lines collected multiple times may have certain errors in position. If the stop lines with large offsets are not lowered or removed during the fusion process, the relative position of the fused stop lines and the surrounding ground traffic elements in the real scene may be very different, or even unreasonable. Therefore, how to further reduce the stop line fusion error caused by multiple stop line collection is an urgent problem to be solved. Summary of the invention

[0004] The present invention aims at the technical problems existing in the prior art and provides a stop line fusion method, system, electronic device and storage medium to solve the problem of how to further reduce the stop line fusion error caused by multiple acquisition of stop lines.

[0005] According to a first aspect of the present invention, a stop line fusion method is provided, comprising:

[0006] Acquire a collection data set of a target stop line to obtain a plurality of collection stop lines;

[0007] Calculate the direction vector of each acquisition stop line to obtain a direction vector set;

[0008] Based on the direction vector set, calculating the confidences corresponding to the plurality of acquisition stop lines;

[0009] The acquisition stop lines whose confidences are greater than a preset confidence threshold are fused to generate fused stop lines.

[0010] Based on the above technical solution, the present invention can also make the following improvements.

[0011] Preferably, the step of calculating the direction vector of each acquisition stop line to obtain a direction vector set includes:

[0012] Get the two endpoints A of each acquisition stop line iand B i , calculate the direction vector of each acquisition stop line Get the direction vector set

[0013] The direction vector for:

[0014]

[0015] Among them, i is the serial number of the acquisition stop line, A i and B i These are the two endpoints of the acquisition stop line.

[0016] Preferably, the step of calculating the confidences corresponding to the plurality of acquisition stop lines based on the direction vector set comprises:

[0017] Set any direction vector in the direction vector set as the reference vector Based on it, the vector mean of all direction vectors in the direction vector set is calculated

[0018] Get the center point P of each acquisition stop line i The reference center point P0 corresponding to the reference vector is calculated for each center point P i The vector to the reference center point P0

[0019] Based on the vector and vector mean Confidences corresponding to the multiple acquisition stop lines are calculated.

[0020] Preferably, the vector based and vector mean The step of calculating the confidences corresponding to the plurality of acquisition stop lines comprises:

[0021] The vector Projection to the mean of the vector On the basis of the projection length set D = {d0, d1, ..., d n};

[0022] The projection length set D is normalized, and the probability p of the processed result in the standard normal distribution is calculated. i ;

[0023] Based on the probability p i , calculate the confidence levels corresponding to the multiple acquisition stop lines.

[0024] Preferably, the projection length set D is normalized and the probability p of the processed result in the standard normal distribution is calculated.i The steps include:

[0025] Get the minimum value d in the projection length set D min , subtract the minimum value d from each projection length in the projection length set D min , get the length set D',

[0026] Get the maximum projection length d' of the length set D' max , based on the maximum projection length d′ max The length set D' is normalized and the probability p of the processed result in the standard normal distribution is calculated. i .

[0027] Preferably, the normalization is:

[0028]

[0029] Among them, i is the serial number of the projection length set, d i ′ is the length of the i-th projection in the length set D′, d′ max is the maximum projection length of the length set D'.

[0030] Preferably, the confidence value is:

[0031] β i =2*(1-p i );

[0032] Among them, i is the serial number of the acquisition stop line, β i is the confidence of the i-th acquisition stop line, p i is the probability of the i-th acquisition stop line corresponding to the length set.

[0033] According to a second aspect of the present invention, there is provided a stop line fusion system, comprising:

[0034] A data acquisition module, used to acquire an acquisition data set of a target stop line, and obtain multiple acquisition stop lines;

[0035] A vector calculation module is used to calculate the direction vector of each acquisition stop line to obtain a direction vector set;

[0036] A confidence calculation module, used to calculate the confidences corresponding to the multiple acquisition stop lines based on the direction vector set;

[0037] The stop line fusion module is used to fuse the acquisition stop lines whose confidence is greater than a preset confidence threshold to generate a fused stop line.

[0038] According to a third aspect of the present invention, there is provided an electronic device comprising a memory and a processor, wherein the processor is configured to implement any step of the stop line fusion method in the first aspect when executing a computer management program stored in the memory.

[0039] According to a fourth aspect of the present invention, there is provided a computer-readable storage medium on which a computer management program is stored. When the computer management program is executed by a processor, the steps of any stop line fusion method in the first aspect are implemented.

[0040] The present invention provides a stop line fusion method, system, electronic device and storage medium, the method comprising: obtaining a collection data set of a target stop line to obtain multiple collection stop lines; calculating the direction vector of each collection stop line to obtain a direction vector set; based on the direction vector set, calculating the confidence corresponding to the multiple collection stop lines; fusing the collection stop lines whose confidence is greater than a preset confidence threshold to generate a fused stop line. The present invention calculates the confidence of multiple collection stop lines, thereby eliminating the collection stop lines whose confidence is lower than the preset threshold among the stop lines collected multiple times, thereby greatly improving the accuracy of the target stop line in the automatic driving scene, thereby greatly improving the safety of the vehicle during driving, and enhancing the user's driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flow chart of a stop line fusion method provided by the present invention;

[0042] Figure 2 A schematic diagram of a stop line for multiple acquisitions provided by the present invention;

[0043] Figure 3 A schematic diagram of the normalized distance of the stop line provided by the present invention;

[0044] Figure 4 A schematic diagram of the structure of a stop line fusion system provided by the present invention;

[0045] Figure 5 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0046] Figure 6 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0047] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0048] Figure 1A flow chart of a stop line fusion method provided by the present invention is as follows: Figure 1 As shown, the method includes:

[0049] Step S100: Acquire a collection data set of a target stop line to obtain a plurality of collection stop lines;

[0050] It should be noted that the execution subject of the method of this embodiment can be a computer terminal device with data processing, network communication and program running functions, such as a computer, a tablet computer, etc.; it can also be a server device with the same or similar functions, or a cloud server with similar functions, and this embodiment does not limit this. For ease of understanding, this embodiment and the following embodiments will be described using a server device as an example.

[0051] It can be understood that the target stop line mentioned above may be a stop line on the road for which a virtual stop line needs to be constructed in the navigation map.

[0052] In the specific implementation, a data set Ω is collected multiple times for a certain stop line on the road. There are n stop lines in total. Figure 2 , Figure 2 A schematic diagram of the stop line of multiple acquisitions provided by the present invention. The stop line s of each acquisition i From point A i and point B i Composition, the center point is

[0053] Step S200: Calculate the direction vector of each acquisition stop line to obtain a direction vector set;

[0054] Furthermore, the step of calculating the direction vector of each acquisition stop line to obtain a direction vector set includes:

[0055] Get the two endpoints A of each acquisition stop line i and B i , calculate the direction vector of each acquisition stop line Get the direction vector set

[0056] The direction vector for:

[0057]

[0058] Among them, i is the serial number of the acquisition stop line, A i and B i These are the two endpoints of the acquisition stop line.

[0059] In the specific implementation, each stop line s is calculated i Direction vector Get the direction vectors of all stop lines

[0060] Step S300: calculating the confidences corresponding to the plurality of acquisition stop lines based on the direction vector set;

[0061] Furthermore, the step of calculating the confidences corresponding to the plurality of acquisition stop lines based on the direction vector set includes:

[0062] Step S301: Setting any direction vector in the direction vector set as a reference vector Based on it, the vector mean of all direction vectors in the direction vector set is calculated

[0063] In the specific implementation, As a reference, calculate any direction vector and The cosine of the angle If α i ≤0, Calculate the mean of all vectors

[0064] Step S302: Obtain the center point P of each acquisition stop line i The reference center point P0 corresponding to the reference vector is calculated for each center point P i The vector to the reference center point P0

[0065] In the specific implementation, each stop line s is calculated i The center point P i The vector with P0

[0066] Step S303: Based on the vector and vector mean Confidences corresponding to the multiple acquisition stop lines are calculated.

[0067] Further, the vector based on and vector mean The step of calculating the confidences corresponding to the plurality of acquisition stop lines comprises:

[0068] Step S3031: The vector Projection to the mean of the vector On the basis of the projection length set D = {d0, d1, ..., d n};

[0069] Step S3032: normalize the projection length set D and calculate the probability p of the processed result in the standard normal distribution. i ;

[0070] Furthermore, the projection length set D is normalized, and the probability p of the processed result in the standard normal distribution is calculated. i The steps include:

[0071] Step S30321: Obtain the minimum value d in the projection length set D min , subtract the minimum value d from each projection length in the projection length set D min , get the length set D';

[0072] Step S30322: Obtain the maximum projection length d′ of the length set D′ max , based on the maximum projection length d′ max The length set D' is normalized and the probability p of the processed result in the standard normal distribution is calculated. i .

[0073] Step S3033: Based on the probability p i , calculate the confidence levels corresponding to the multiple acquisition stop lines.

[0074] In the specific implementation, the vector is calculated exist The projection length on Get the length set D = {d0, d1, ..., d n}, calculate the minimum value d in the length set D min =min n D, the length of each projection minus the minimum value d min , get the new projection length d i ′=d i -d min , and obtain the new length D′={d′0,d′1,…,d′ n}; and the maximum projection length d′ can be obtained max =max n d i ′, each d i 'Normalized to between 0 and 1 Its effect can be seen in Figure 3 , Figure 3 Schematic diagram of the normalized distance of the stop line provided by the present invention, calculating c i The probability p in the standard normal distribution i , then stop line s i The confidence value β i =2*(1-p i ), and thus obtain the confidence value β of all stop lines i .

[0075] Step S400: fusing the acquisition stop lines whose confidences are greater than a preset confidence threshold to generate a fused stop line.

[0076] It is understandable that, based on the defects in the background technology, an embodiment of the present invention proposes a stop line fusion method. The method includes: obtaining a collection data set of a target stop line to obtain multiple collection stop lines; calculating the direction vector of each collection stop line to obtain a direction vector set; based on the above direction vector set, calculating the confidence corresponding to the above multiple collection stop lines; fusing the above collection stop lines whose confidence is greater than a preset confidence threshold to generate a fused stop line. The present invention calculates the confidence of multiple collection stop lines, thereby eliminating the collection stop lines whose confidence is lower than the preset threshold among the stop lines collected multiple times, thereby greatly improving the accuracy of the target stop line in the autonomous driving scenario, thereby greatly improving the safety of the vehicle during driving and enhancing the user's driving experience.

[0077] See also Figure 4 , Figure 4 A schematic diagram of a stop line fusion system structure provided by an embodiment of the present invention is shown in FIG. Figure 4 As shown, a stop line fusion system includes a data acquisition module 100, a vector calculation module 200, a confidence calculation module 300 and a stop line fusion module 400, wherein:

[0078] The data acquisition module 100 is used to obtain the acquisition data set of the target stop line to obtain multiple acquisition stop lines; the vector calculation module 200 is used to calculate the direction vector of each acquisition stop line to obtain a direction vector set; the confidence calculation module 300 is used to calculate the confidence corresponding to the multiple acquisition stop lines based on the direction vector set; the stop line fusion module 400 is used to fuse the acquisition stop lines whose confidence is greater than a preset confidence threshold to generate a fused stop line.

[0079] It can be understood that the stop line fusion system provided by the present invention corresponds to the stop line fusion method provided by the aforementioned embodiments, and the relevant technical features of the stop line fusion system can refer to the relevant technical features of the stop line fusion method, which will not be repeated here.

[0080] See also Figure 5 , Figure 5 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention provides an electronic device, including a memory 1310, a processor 1320, and a computer program 1311 stored in the memory 1310 and executable on the processor 1320. When the processor 1320 executes the computer program 1311, the following steps are implemented:

[0081] Acquire a collection data set of a target stop line to obtain multiple collection stop lines; calculate the direction vector of each collection stop line to obtain a direction vector set; based on the direction vector set, calculate the confidences corresponding to the multiple collection stop lines; fuse the collection stop lines whose confidences are greater than a preset confidence threshold to generate a fused stop line.

[0082] See also Figure 6 , Figure 6 Schematic diagram of an embodiment of a computer-readable storage medium provided by the present invention. Figure 6 As shown, this embodiment provides a computer-readable storage medium 1400, on which a computer program 1411 is stored. When the computer program 1411 is executed by a processor, the following steps are implemented:

[0083] Acquire a collection data set of a target stop line to obtain multiple collection stop lines; calculate the direction vector of each collection stop line to obtain a direction vector set; based on the direction vector set, calculate the confidences corresponding to the multiple collection stop lines; fuse the collection stop lines whose confidences are greater than a preset confidence threshold to generate a fused stop line.

[0084] The present invention provides a stop line fusion method, system, electronic device and storage medium, the method comprising: obtaining a collection data set of a target stop line to obtain multiple collection stop lines; calculating the direction vector of each collection stop line to obtain a direction vector set; based on the direction vector set, calculating the confidence corresponding to the multiple collection stop lines; fusing the collection stop lines whose confidence is greater than a preset confidence threshold to generate a fused stop line. The present invention calculates the confidence of multiple collection stop lines, thereby eliminating the collection stop lines whose confidence is lower than the preset threshold among the stop lines collected multiple times, thereby greatly improving the accuracy of the target stop line in the automatic driving scene, thereby greatly improving the safety of the vehicle during driving, and enhancing the user's driving experience.

[0085] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0086] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0087] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0088] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0089] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0090] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0091] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A stop line fusion method, characterized in that: The method comprises: Acquire a collection data set of a target stop line to obtain a plurality of collection stop lines; Calculate the direction vector of each acquisition stop line to obtain a direction vector set; Based on the direction vector set, calculating the confidences corresponding to the plurality of acquisition stop lines; The acquisition stop lines whose confidences are greater than a preset confidence threshold are fused to generate fused stop lines.

2. The stop line fusion method according to claim 1, characterized in that: The step of calculating the direction vector of each acquisition stop line to obtain a direction vector set includes: Get the two endpoints A of each acquisition stop line i and B i , calculate the direction vector of each acquisition stop line Get the direction vector set The direction vector for: Among them, i is the serial number of the acquisition stop line, A i and B i These are the two endpoints of the acquisition stop line.

3. The stop line fusion method according to claim 1, characterized in that: The step of calculating the confidences corresponding to the plurality of acquisition stop lines based on the direction vector set comprises: Set any direction vector in the direction vector set as the reference vector Based on it, the vector mean of all direction vectors in the direction vector set is calculated Get the center point P of each acquisition stop line i The reference center point P0 corresponding to the reference vector is calculated for each center point P i The vector to the reference center point P0 Based on the vector and vector mean Confidences corresponding to the multiple acquisition stop lines are calculated.

4. The stop line fusion method according to claim 3, characterized in that: The vector based and vector mean The step of calculating the confidences corresponding to the plurality of acquisition stop lines comprises: The vector Projection to the mean of the vector On the basis of the projection length set D = {d0, d1, ..., d n }; The projection length set D is normalized, and the probability p of the processed result in the standard normal distribution is calculated. i ; Based on the probability p i , calculate the confidence levels corresponding to the multiple acquisition stop lines.

5. The stop line fusion method according to claim 4, characterized in that: The projection length set D is normalized, and the probability p of the processed result in the standard normal distribution is calculated. i The steps include: Get the minimum value d in the projection length set D min , subtract the minimum value d from each projection length in the projection length set D min , get the length set D'; Get the maximum projection length d' of the length set D' max , based on the maximum projection length d′ max The length set D' is normalized and the probability p of the processed result in the standard normal distribution is calculated. i .

6. The stop line fusion method according to claim 5, characterized in that: The normalization is: Among them, i is the serial number of the projection length set, d′ i is the length of the i-th projection in the length set D', d' max is the maximum projection length of the length set D'.

7. The stop line fusion method according to claim 4, characterized in that: The confidence value is: β i =2*(1- i ); Among them, i is the serial number of the acquisition stop line, β i is the confidence of the i-th acquisition stop line, p i is the probability of the i-th acquisition stop line corresponding to the length set.

8. A stop line fusion system, characterized in that: include A data acquisition module, used to acquire an acquisition data set of a target stop line, and obtain multiple acquisition stop lines; A vector calculation module is used to calculate the direction vector of each acquisition stop line to obtain a direction vector set; A confidence calculation module, used to calculate the confidences corresponding to the multiple acquisition stop lines based on the direction vector set; The stop line fusion module is used to fuse the acquisition stop lines whose confidence is greater than a preset confidence threshold to generate a fused stop line.

9. An electronic device, characterized in that: It comprises a memory and a processor, wherein the processor is used to implement the steps of the stop line fusion method according to any one of claims 1 to 7 when executing a computer management program stored in the memory.

10. A computer-readable storage medium, characterized in that: A computer management program is stored thereon, and when the computer management program is executed by a processor, the steps of the stop line fusion method according to any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Lane position determination method and device based on automatic driving vehicle and storage medium

    CN110633800A

  • High-precision map stop line fusion method and system, server and storage medium

    CN112541048A

  • Lane position acquisition method and device, computer equipment and storage medium

    CN114332805A

  • Map matching method and device, Internet of Vehicles equipment and readable storage medium

    CN117091611A

  • A method of Stop-line Detection for Autonomous Vehicles

    KR101862994B1