Camera lane line confidence coefficient verification method and system based on high-precision map

Abstract

The invention discloses a camera lane line confidence coefficient verification method and system based on a high-precision map. The method comprises the following steps: acquiring map equidistant shape point data identified by a high-precision map sensor; acquiring camera equidistant shape point data identified by a camera sensor; according to the map equidistant shape point data and the camera equidistant shape point data, carrying out confidence judgment on a lane line identified by a camera sensor; wherein the shape point spacing in the map equidistant shape point data is equal to the shape point spacing in the camera equidistant shape point data. Therefore, the lane line information identified by the foresight camera is verified by using the characteristics of high stability and accuracy of the map sensor and small environmental interference.

Description

Technical Field

[0001] The present invention relates to the technical field of map data processing, and in particular to a camera lane line confidence verification method and system based on a high-precision map. Background Art

[0002] The existing technology still uses a single sensor to calculate the confidence of the front vision camera, that is, the confidence is still set and judged based on the lane line pixels seen by the camera. However, vision is more susceptible to environmental interference and the shape of the road lane lines varies greatly, which may lead to unreliable confidence recognition.

[0003] Therefore, in order to solve the above problems, the present invention aims to solve the problem that the front vision sensor's perception of the road is related to the environment, resulting in inaccurate recognition of lane lines, which requires verification of confidence data. Summary of the invention

[0004] The present invention provides a camera lane line confidence verification method and system based on high-precision maps, which utilizes the stability and accuracy of high-precision map sensors and the characteristics of being less affected by environmental interference to verify the lane line information recognized by the front-view camera.

[0005] In a first aspect, a method for verifying the confidence of a camera lane line based on a high-precision map is provided, comprising the following steps:

[0006] Obtain the map equidistant point data recognized by the high-precision map sensor;

[0007] Obtain the camera equidistant point data recognized by the camera sensor;

[0008] Performing confidence judgment on the lane line identified by the camera sensor according to the map equidistant point data and the camera equidistant point data;

[0009] Among them, the shape point spacing in the map equally-spaced shape point data is equal to the shape point spacing in the camera equally-spaced shape point data.

[0010] According to the first aspect, in a first possible implementation manner of the first aspect, the step of “obtaining map equidistant point data recognized by a high-precision map sensor” specifically includes the following steps:

[0011] Obtain lane edge line point data of the lane where the vehicle is located detected by the high-precision map sensor;

[0012] The lane edge line shape point data is curve fitted based on the least squares algorithm to obtain a map lane edge line curve, and the map lane edge line curve is evenly sampled to obtain map evenly spaced shape point data.

[0013] According to the first aspect, in a second possible implementation manner of the first aspect, the step of “obtaining camera equidistant point data recognized by the camera sensor” specifically includes the following steps:

[0014] A camera lane edge curve of a lane where a vehicle is located is obtained by a camera sensor, and the camera lane edge curve is sampled at equal intervals to obtain camera equal-interval point data.

[0015] According to the first aspect, in a third possible implementation manner of the first aspect, the step of “performing a confidence judgment on the lane line recognized by the camera sensor according to the map equidistant point data and the camera equidistant point data” specifically includes the following steps:

[0016] Performing Euclidean distance calculation on the camera's equally spaced point data at equal intervals, and calculating the first standard deviation of all obtained Euclidean distance values;

[0017] When it is detected that the first standard deviation is greater than a first preset threshold, it is determined that the camera sensor has identified a lane line with low confidence;

[0018] When it is detected that the first standard deviation is less than or equal to a first preset threshold, the Euclidean distance calculation is performed on the map equidistant point data and the camera equidistant point data, and the confidence of the lane line recognized by the camera sensor is judged based on the standard deviation of the Euclidean distance value.

[0019] According to the third possible implementation manner of the first aspect, in the fourth possible implementation manner of the first aspect, the step of “calculating the Euclidean distance between the map equidistant point data and the camera equidistant point data” specifically includes the following steps:

[0020] The camera equally spaced point data includes the left linear point (X cameral , Y cameral ) and the right linear point (X camerar , Y camerar );

[0021] The map equally spaced point data includes the left linear point (X mapl , Y mapl ) and the right linear point (X mapr , Y mapr );

[0022] The calculation formula for calculating the Euclidean distance between the left linear points of the lane line on the map and the left linear points of the lane line at equal intervals is:

[0023] The calculation formula for calculating the Euclidean distance between the right linear points of the lane line on the map and the right linear points of the lane line at equal intervals is:

[0024] According to the fourth possible implementation manner of the first aspect, in the fifth possible implementation manner of the first aspect, the step of “performing a confidence judgment on the lane line recognized by the camera sensor according to the standard deviation of the Euclidean distance value” specifically includes the following steps:

[0025] After calculating the Euclidean distance between the left linear points of the lane line on the map and the left linear points of the lane line at equal intervals, calculate the second standard deviation of the left lane line based on the Euclidean distance value;

[0026] After calculating the Euclidean distance between the right linear points of the lane line on the map and the right linear points of the lane line at equal intervals, calculate the third standard deviation of the right lane line based on the Euclidean distance value;

[0027] When it is detected that the second standard deviation is greater than the second preset threshold, or the third standard deviation is greater than the second preset threshold, or the absolute difference between the second standard deviation and the third standard deviation is greater than the third preset threshold, it is determined that the camera sensor has identified a lane line with low confidence.

[0028] In the second aspect, a camera lane line confidence verification system based on a high-precision map is provided, comprising:

[0029] A map data acquisition module is used to acquire map equidistant point data recognized by a high-precision map sensor;

[0030] A camera data acquisition module, used to acquire camera equally spaced shape point data recognized by a camera sensor; wherein the shape point spacing in the map equally spaced shape point data is equal to the shape point spacing in the camera equally spaced shape point data; and,

[0031] The judgment module is in communication with the map data acquisition module and the camera data acquisition module, and is used to make a confidence judgment on the lane line recognized by the camera sensor based on the map equidistant point data and the camera equidistant point data.

[0032] Compared with the prior art, the advantages of the present invention are as follows: Compared with relying solely on the front-view camera for confidence judgment, the high-precision map data has high accuracy and is less affected by the environment, and can effectively describe the lane line characteristics of the vehicle in real time. Therefore, under the premise of relatively accurate positioning, the confidence judgment of the lane line results recognized by the camera sensor can be accurately performed. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1It is a flow chart of a camera lane line confidence verification method based on a high-precision map according to the present invention;

[0034] Figure 2 It is a structural schematic diagram of a camera lane line confidence verification system based on a high-precision map of the present invention. DETAILED DESCRIPTION

[0035] Reference will now be made in detail to specific embodiments of the present invention, examples of which are illustrated in the accompanying drawings. Although the present invention will be described in conjunction with specific embodiments, it will be understood that it is not intended to limit the present invention to the embodiments described. On the contrary, it is intended to cover changes, modifications and equivalents included in the spirit and scope of the present invention as defined by the appended claims. It should be noted that the method steps described herein can all be implemented by any functional block or functional arrangement, and any functional block or functional arrangement can be implemented as a physical entity or a logical entity, or a combination of the two.

[0036] In order to enable those skilled in the art to better understand the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0037] Note: The example to be introduced below is only a specific example, and is not intended to limit the embodiments of the present invention to the following specific steps, values, conditions, data, sequences, etc. Those skilled in the art can apply the concept of the present invention to construct more embodiments not mentioned in this specification by reading this specification.

[0038] See also Figure 1 and 2 , an embodiment of the present invention provides a camera lane line confidence verification method based on a high-precision map, comprising the following steps:

[0039] S100, obtaining map equidistant point data recognized by a high-precision map sensor;

[0040] S200, obtaining camera equidistant point data recognized by the camera sensor;

[0041] S300, judging the confidence of the lane line recognized by the camera sensor according to the map equidistant point data and the camera equidistant point data;

[0042] Among them, the shape point spacing in the map equally-spaced shape point data is equal to the shape point spacing in the camera equally-spaced shape point data.

[0043] Specifically, in this embodiment, the existing technology still uses a single sensor to determine and set the confidence level for the front vision camera. However, vision is more susceptible to environmental interference and the shapes of road lane lines vary greatly, which may lead to unreliable confidence level recognition. Therefore, in order to address this problem, the stability and accuracy of the high-resolution map sensor and its low environmental interference are used to verify the lane line information recognized by the front vision camera.

[0044] Therefore, compared with the confidence judgment based on the forward-looking camera alone, the present invention can effectively describe the lane line characteristics of the vehicle in real time due to the high-precision map data with high accuracy and little interference from the environment. Therefore, under the premise of relatively accurate positioning, the confidence judgment of the lane line results recognized by the camera sensor can be accurately performed.

[0045] Preferably, in another embodiment of the present application, the step of “S100, obtaining map equidistant point data recognized by a high-precision map sensor” specifically includes the following steps:

[0046] Obtain lane edge line point data of the lane where the vehicle is located detected by the high-precision map sensor;

[0047] The lane edge line shape point data is curve fitted based on the least squares algorithm to obtain a map lane edge line curve, and the map lane edge line curve is evenly sampled to obtain map evenly spaced shape point data.

[0048] Specifically, in this embodiment, the lane edge point data of the lane where the current vehicle is located can be obtained through the high-precision map sensor, and the coordinate conversion of the obtained left and right lane edge point data of the map is performed in combination with the vehicle's position information and heading angle to convert them into point data ∑(X mapl , Y mapl ) and ∑(X mapr , Y mapr ).

[0049] For the acquired left and right lane line point data, curve fitting is performed, with the direction of the vehicle head moving as the positive X direction, and the curve is solved by least squares. In this way, the left and right lane line curves provided by the high-precision map sensor can be obtained as follows:

[0050]

[0051] For the high-precision map sensor that has been obtained, the sampling interval is temporarily set to 0.5 meters. Therefore, the map equidistant point data of the left and right side lines of the lane where the current vehicle is located can be obtained at an interval of 0.5 meters:

[0052] ∑(Xmapl , Y mapl ) and ∑(X mapr , Y mapr ).

[0053] Preferably, in another embodiment of the present application, the step of “S200, obtaining camera equidistant point data recognized by the camera sensor” specifically includes the following steps:

[0054] A camera lane edge curve of a lane where a vehicle is located is obtained by a camera sensor, and the camera lane edge curve is sampled at equal intervals to obtain camera equal-interval point data.

[0055] Specifically, in this embodiment, the third-order lane curve equation provided by the visual sensor can be obtained through the forward-looking sensor as follows:

[0056]

[0057] For the curve lane line equation of the front vision sensor that has been obtained, by setting the sampling interval to 0.5 meters, the left and right lane edge line point data with equal spacing can be obtained:

[0058] ∑(X cameral , Y cameral ) and ∑(X camerar , Y camerar ).

[0059] Preferably, in another embodiment of the present application, the step of “S300, judging the confidence of the lane line recognized by the camera sensor according to the map equidistant point data and the camera equidistant point data” specifically includes the following steps:

[0060] Performing Euclidean distance calculation on the camera's equally spaced point data at equal intervals, and calculating the first standard deviation of all obtained Euclidean distance values;

[0061] When it is detected that the first standard deviation is greater than a first preset threshold, it is determined that the camera sensor has identified a lane line with low confidence;

[0062] When it is detected that the first standard deviation is less than or equal to a first preset threshold, the Euclidean distance calculation is performed on the map equidistant point data and the camera equidistant point data, and the confidence of the lane line recognized by the camera sensor is judged based on the standard deviation of the Euclidean distance value.

[0063] Specifically, in this embodiment, for the equidistant shape point data of the front-view camera that has been acquired, the length of the shape point distance with the same distance between the left and right edges is calculated by Euclidean distance:

[0064]

[0065] Due to X cameral and X camerar The values ​​are equal, so the distance formula can be equivalent to:

[0066]

[0067] The first standard deviation A is calculated by performing standard deviation statistics on the distance parameters of the left and right lane lines of the camera that have been obtained. camera .

[0068] When it is detected that the first standard deviation is greater than a first preset threshold, it is determined that the camera sensor has identified a lane line with low confidence.

[0069] Preferably, in another embodiment of the present application, the step of "calculating the Euclidean distance between the map equidistant point data and the camera equidistant point data" specifically includes the following steps:

[0070] The camera equally spaced point data includes the left linear point (X cameral , Y cameral ) and the right linear point (X camerar , Y camerar );

[0071] The map equally spaced point data includes the left linear point (X mapl , Y mapl ) and the right linear point (X mapr , Y mapr );

[0072] The calculation formula for calculating the Euclidean distance between the left linear points of the lane line on the map and the left linear points of the lane line at equal intervals is:

[0073] The calculation formula for calculating the Euclidean distance between the right linear points of the lane line on the map and the right linear points of the lane line at equal intervals is:

[0074] Preferably, in another embodiment of the present application, the step of “determining the confidence of the lane line identified by the camera sensor according to the standard deviation of the Euclidean distance value” specifically includes the following steps:

[0075] After calculating the Euclidean distance between the left linear points of the lane line on the map and the left linear points of the lane line at equal intervals, calculate the second standard deviation of the left lane line based on the Euclidean distance value;

[0076] After calculating the Euclidean distance between the right linear points of the lane line on the map and the right linear points of the lane line at equal intervals, calculate the third standard deviation of the right lane line based on the Euclidean distance value;

[0077] When it is detected that the second standard deviation is greater than the second preset threshold, or the third standard deviation is greater than the second preset threshold, or the absolute difference between the second standard deviation and the third standard deviation is greater than the third preset threshold, it is determined that the camera sensor has identified a lane line with low confidence.

[0078] It should be noted that if the camera sensor detects only a single-side line, the standard deviation parameter is calculated by obtaining the same-side line of the high-precision map in the same way, and the threshold is set to make a threshold judgment on the camera confidence.

[0079] See also Figure 2 As shown, an embodiment of the present invention further provides a camera lane line confidence verification system based on a high-precision map, comprising:

[0080] A map data acquisition module is used to acquire map equidistant point data recognized by a high-precision map sensor;

[0081] A camera data acquisition module, used to acquire camera equally spaced shape point data recognized by a camera sensor; wherein the shape point spacing in the map equally spaced shape point data is equal to the shape point spacing in the camera equally spaced shape point data; and,

[0082] The judgment module is in communication with the map data acquisition module and the camera data acquisition module, and is used to make a confidence judgment on the lane line recognized by the camera sensor based on the map equidistant point data and the camera equidistant point data.

[0083] The beneficial effects of the present invention are as follows:

[0084] Compared with the confidence judgment based on the forward-looking camera alone, the present invention can effectively describe the lane line characteristics of the vehicle in real time due to the high-precision map data with high accuracy and little interference from the environment. Therefore, under the premise of relatively accurate positioning, the confidence judgment of the lane line results recognized by the camera sensor can be accurately performed.

[0085] Specifically, this embodiment corresponds one-to-one to the above method embodiment, and the functions of each module have been described in detail in the corresponding method embodiment, so they will not be repeated here.

[0086] Based on the same inventive concept, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, all or part of the method steps of the above method are implemented.

[0087] The present invention implements all or part of the process in the above method, and can also be completed by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of each method embodiment can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, USB flash drive, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0088] Based on the same inventive concept, an embodiment of the present application also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program running on the processor, and when the processor executes the computer program, all or part of the method steps in the above method are implemented.

[0089] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of a computer device, and uses various interfaces and lines to connect various parts of the entire computer device.

[0090] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the computer device by running or executing the computer programs and / or modules stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the mobile phone (such as audio data, video data, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0091] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, servers 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 and optical storage, etc.) containing computer-usable program codes.

[0092] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), servers, 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 a 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 processor, or other programmable data processing device to produce 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.

[0093] 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.

[0094] 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 The steps for the functions specified in one or more boxes.

[0095] 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 camera lane line confidence verification method based on high-precision maps, characterized in that: The following steps are involved: Obtain the map equidistant point data recognized by the high-precision map sensor; Obtain the camera equidistant point data recognized by the camera sensor; Performing confidence judgment on the lane line recognized by the camera sensor according to the map equidistant point data and the camera equidistant point data; Among them, the shape point spacing in the map equally-spaced shape point data is equal to the shape point spacing in the camera equally-spaced shape point data.

2. The camera lane line confidence verification method based on a high-precision map as claimed in claim 1, characterized in that: The step of "obtaining map equidistant point data recognized by a high-precision map sensor" specifically includes the following steps: Obtain lane edge line point data of the lane where the vehicle is located detected by the high-precision map sensor; The lane edge line shape point data is curve fitted based on the least squares algorithm to obtain a map lane edge line curve, and the map lane edge line curve is evenly sampled to obtain map evenly spaced shape point data.

3. The camera lane line confidence verification method based on a high-precision map as claimed in claim 1, characterized in that: The step of "obtaining camera equidistant point data recognized by the camera sensor" specifically includes the following steps: A camera lane edge curve of a lane where a vehicle is located is obtained by a camera sensor, and the camera lane edge curve is sampled at equal intervals to obtain camera equal-interval point data.

4. The camera lane line confidence verification method based on a high-precision map as claimed in claim 1, characterized in that: The step of "making a confidence judgment on the lane line recognized by the camera sensor according to the map equidistant point data and the camera equidistant point data" specifically includes the following steps: Performing Euclidean distance calculation on the camera's equally spaced point data at equal intervals, and calculating the first standard deviation of all obtained Euclidean distance values; When it is detected that the first standard deviation is greater than a first preset threshold, it is determined that the camera sensor has identified a lane line with low confidence; When it is detected that the first standard deviation is less than or equal to a first preset threshold, the Euclidean distance calculation is performed on the map equidistant point data and the camera equidistant point data, and the confidence of the lane line recognized by the camera sensor is judged based on the standard deviation of the Euclidean distance value.

5. The camera lane line confidence verification method based on high-precision map as claimed in claim 4, characterized in that: The step of "calculating the Euclidean distance between the map equidistant point data and the camera equidistant point data" specifically includes the following steps: The camera equally spaced point data includes the left linear point (X cameral , Y cameral ) and the right linear point (X camerar , Y camerar ); The map equally spaced point data includes the left linear point (X mapl , Y mapl ) and the right linear point (X mapr , Y mapr ); The calculation formula for calculating the Euclidean distance between the left linear points of the lane line on the map and the left linear points of the lane line at equal intervals is: The calculation formula for calculating the Euclidean distance between the right linear points of the lane line on the map and the right linear points of the lane line at equal intervals is:

6. The camera lane line confidence verification method based on a high-precision map as claimed in claim 5, characterized in that: The step of "making a confidence judgment on the lane line recognized by the camera sensor according to the standard deviation of the Euclidean distance value" specifically includes the following steps: After calculating the Euclidean distance between the left linear points of the lane line on the map and the left linear points of the lane line at equal intervals, calculate the second standard deviation of the left lane line based on the Euclidean distance value; After calculating the Euclidean distance between the right linear points of the lane line on the map and the right linear points of the lane line at equal intervals, calculate the third standard deviation of the right lane line based on the Euclidean distance value; When it is detected that the second standard deviation is greater than the second preset threshold, or the third standard deviation is greater than the second preset threshold, or the absolute difference between the second standard deviation and the third standard deviation is greater than the third preset threshold, it is determined that the camera sensor has identified a lane line with low confidence.

7. A camera lane line confidence verification system based on high-precision maps, characterized in that: include: A map data acquisition module is used to acquire map equidistant point data recognized by a high-precision map sensor; A camera data acquisition module, used to acquire camera equally spaced shape point data recognized by a camera sensor; wherein the shape point spacing in the map equally spaced shape point data is equal to the shape point spacing in the camera equally spaced shape point data; as well as, The judgment module is in communication with the map data acquisition module and the camera data acquisition module, and is used to make a confidence judgment on the lane line recognized by the camera sensor based on the map equidistant point data and the camera equidistant point data.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the camera lane line confidence verification method based on a high-precision map as described in any one of claims 1 to 6 is implemented.

9. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor runs the computer program, the camera lane line confidence verification method based on a high-precision map as described in any one of claims 1 to 6 is implemented.

Images