Lane line precision verification method and related device
By setting a confidence region on the lane line and selecting the coordinate point shortest from the vertical reference line as the matching point, the problem of large offset of the matching point in the existing technology is solved, and more accurate lane line accuracy verification is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHIDAO NETWORK TECH (BEIJING) CO LTD
- Filing Date
- 2023-03-14
- Publication Date
- 2026-07-21
AI Technical Summary
In existing technologies, when using circles to find matching points, there may be a large lateral offset, which cannot truly reflect the solution effect of lane lines.
By setting a confidence region, any coordinate point on the actual lane line is selected as the current point, and a confidence region perpendicular to the lane line direction is constructed. The coordinate points on the calculated lane line within the confidence region are determined as the points to be matched, and the point with the shortest distance from the point to be matched to the perpendicular reference line is taken as the target matching point to verify the accuracy of the calculated lane line.
It improves the correlation between the matching point and the current point, which can better reflect the solution effect of the lane line and accurately verify the accuracy of the lane line solution.
Smart Images
Figure CN116481510B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of autonomous driving technology, and in particular to lane line accuracy verification methods and related devices. Background Technology
[0002] With the rapid development of autonomous driving technology, the requirements for vehicle positioning accuracy are becoming increasingly stringent. The positioning accuracy of ordinary navigation maps is no longer sufficient to meet the needs of autonomous vehicles. Therefore, major autonomous driving companies have begun developing high-precision maps. To reduce costs, lower-priced positioning devices are typically used to collect underlying map information, which is then solved using the SLAM algorithm to obtain the calculated lane lines. To determine the accuracy of lane line creation in high-precision maps, a small number of high-precision devices are used to collect lane line data for accuracy comparison. This verifies the accuracy of the calculated lane lines; that is, the coordinates of the actual lane lines obtained by combining the positioning coordinates collected by the high-precision devices with the coordinates calculated using the SLAM algorithm are compared with the calculated lane line data obtained using lower-priced positioning devices.
[0003] To complete the accuracy verification, the corresponding matching points need to be accurately matched, such as... Figure 1 As shown, in related technologies, a coordinate point on the actual lane line calculated by high-precision equipment is mainly used as the current point. A circle is drawn with this current point as the center O and a set radius threshold r. If there is no matching data within the circle, the accuracy of the positioning coordinates for this segment is not high; if there are multiple matching points within the circle, such as... Figure 1 For coordinate points A and B shown, the coordinate point B, which is closest to the center O of the circle, is taken as the matching point. Then, the offset distance between the current point and the matching point is calculated. Finally, the positioning accuracy of the solved lane line is determined according to the accuracy setting requirements. This method of using a circle to find the matching point may result in a large lateral offset relative to the actual matching point, and therefore cannot truly reflect the solution effect of the lane line. Summary of the Invention
[0004] To overcome the problems existing in related technologies, this application provides a lane line accuracy verification method and related device, which can better reflect the calculation effect of lane lines.
[0005] The first aspect of this application provides a lane line accuracy verification method, including:
[0006] Obtain the actual lane line and the calculated lane line of the lane line to be verified, and determine the direction of the lane line based on the actual lane line;
[0007] Select any coordinate point on the actual lane line as the current point, and use the current point as the center point to construct a confidence region according to the accuracy requirements of the calculated lane line. The vertical reference line of the confidence region is perpendicular to the direction of the lane line.
[0008] The coordinates of the solved lane line within the confidence region are determined as the points to be matched;
[0009] The point to be matched that has the shortest distance from the vertical reference line is taken as the target matching point;
[0010] The accuracy of the lane line calculation is verified based on the relationship between the current point and the target matching point.
[0011] A second aspect of this application provides a lane line accuracy verification device, comprising:
[0012] The first processing module is used to obtain the actual lane line and the calculated lane line of the lane line to be verified, and to determine the direction of the lane line based on the actual lane line.
[0013] The second processing module is used to select any coordinate point on the actual lane line as the current point, take the current point as the center point, and construct a confidence region according to the accuracy requirements of the calculated lane line, wherein the vertical reference line of the confidence region is perpendicular to the direction of the lane line.
[0014] The third processing module is used to determine the coordinate points on the solved lane line within the confidence area as the points to be matched;
[0015] The fourth processing module is used to select the point to be matched that has the shortest distance from the vertical reference line as the target matching point;
[0016] The fifth processing module is used to verify the calculation accuracy of the calculated lane lines based on the relationship between the current point and the target matching point.
[0017] A third aspect of this application provides an electronic device, comprising:
[0018] Processor; and
[0019] The memory stores executable code, which, when executed by the processor, causes the processor to perform the lane line accuracy verification method as described above.
[0020] A fourth aspect of this application provides a non-transitory machine-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the lane line accuracy verification method as described above.
[0021] The technical solution provided in this application may include the following beneficial effects:
[0022] In this technical solution, after obtaining the actual lane line and the calculated lane line to be verified, the direction of the lane line is determined based on the actual lane line. Then, any coordinate point on the actual lane line is selected as the current point, and a confidence region is constructed using the current point as the center point, according to the accuracy requirements of the calculated lane line. The vertical reference line of this confidence region is perpendicular to the lane line direction. Next, coordinate points on the calculated lane line within the confidence region are determined as matching points. The matching point with the shortest distance from the vertical reference line is selected as the target matching point. Finally, the accuracy of the calculated lane line is verified based on the relationship between the current point and the target matching point. This technical solution, by setting a confidence region and prioritizing the selection of the coordinate point with the shortest distance from the vertical reference line as the matching point, has a higher correlation with the current point compared to other coordinate points, thus better reflecting the calculation effect of the calculated lane line.
[0023] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description
[0024] The above and other objects, features and advantages of this application will become more apparent from the more detailed description of exemplary embodiments thereof in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments thereof.
[0025] Figure 1-2 This is a schematic diagram illustrating the method for determining target matching points in related technologies;
[0026] Figure 3 This is a schematic flowchart illustrating the lane line accuracy verification method according to an embodiment of this application;
[0027] Figure 4-5 This is a schematic diagram illustrating the target matching point determination method in an embodiment of this application;
[0028] Figure 6-7 This is another schematic diagram illustrating the target matching point determination method shown in the embodiments of this application;
[0029] Figure 8-9 This is another schematic diagram illustrating the target matching point determination method shown in the embodiments of this application;
[0030] Figure 10 This is a schematic flowchart illustrating the lane line accuracy verification method according to an embodiment of this application;
[0031] Figure 11 This is a schematic diagram of the lane line accuracy verification device shown in the embodiments of this application;
[0032] Figure 12 This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application. Detailed Implementation
[0033] Preferred embodiments of the present application will now be described in more detail with reference to the accompanying drawings. While preferred embodiments of the present application are shown in the drawings, it should be understood that the present application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.
[0034] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.
[0035] It should be understood that although the terms "first," "second," "third," etc., may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.
[0036] The applicant discovered in the research that, in order to avoid large lateral offsets between the matching point and the actual matching point when using a circle to find the matching point, and to truly reflect the solution effect of the lane line, it is first necessary to select a coordinate point with high correlation to the current point calculated by the high-precision equipment data as the matching point. Then, the distance between the current point and the matching point is calculated to determine the positioning accuracy. The current point is any coordinate point on the actual lane line calculated using the high-precision equipment data.
[0037] To address the aforementioned issues, this application provides a lane line accuracy verification method that can better reflect the calculation effect of the lane lines.
[0038] The technical solutions of the embodiments of this application are described in detail below with reference to the accompanying drawings.
[0039] Figure 3 This is a schematic flowchart illustrating the lane line accuracy verification method according to an embodiment of this application. See also... Figure 3 This application provides a method for verifying lane line accuracy, which specifically includes the following steps:
[0040] S30: Obtain the actual lane line and the calculated lane line of the lane line to be verified, and determine the direction of the lane line based on the actual lane line.
[0041] The actual lane lines are calculated using positioning coordinate data collected by high-precision equipment combined with the SLAM algorithm. The calculated lane lines are obtained using positioning coordinate data collected by lower-cost positioning equipment combined with the SLAM algorithm. The lane line direction is determined based on the actual lane lines. Specifically, two coordinate points can be selected on the actual lane lines, and the lane line direction can be calculated according to a preset formula. In a specific embodiment, the preset calculation formula can be: Where M(x1, y1) and N(x2, y2) are two points on the actual lane line.
[0042] S31: Select any coordinate point on the actual lane line as the current point, and construct a confidence region based on the accuracy requirements of the calculated lane line, using the current point as the center point.
[0043] The vertical reference line of the confidence region is perpendicular to the direction of the lane line.
[0044] In a specific embodiment, any coordinate point on the actual lane line can be selected as the current point. Using this current point as the center point, a confidence region is constructed based on the accuracy requirements of the calculated lane line. The vertical reference line of this confidence region is perpendicular to the lane line direction, and the confidence region can be circular (e.g., ...). Figure 4-5 As shown), ellipse (as shown) Figure 6-7 As shown), rhombus (as shown) Figure 8-9 (As shown) or other shapes, such as squares or rectangles. It should be noted that the size of the confidence region can be adjusted according to the actual accuracy requirements.
[0045] S32: Determine the coordinates of the lane lines within the confidence region as the points to be matched.
[0046] In a specific embodiment, the coordinate points on the calculated lane line that fall within the confidence region are determined as points to be matched. If there is no matching data in the confidence region, the accuracy of the positioning coordinates of this segment is not high; if there are multiple matching points in the confidence region, the multiple matching points are used as points to be matched.
[0047] In a specific embodiment, such as Figure 4-5 As shown, four points to be matched within the confidence region (circle) can be identified, specifically a, b, c, and d; as... Figure 6-7 As shown, two points to be matched within the confidence region (ellipse) can be identified, specifically e and f; as... Figure 8-9 As shown, two points to be matched within the confidence region (rhombus) can be identified, specifically m and n.
[0048] S33: Select the point to be matched that has the shortest distance from the vertical reference line as the target matching point.
[0049] For the multiple points to be matched determined in step S22, calculate the distance from each point to the vertical reference line, and select the point with the shortest distance as the target matching point. In a specific embodiment, such as... Figure 4-5 As shown, point 'a' within the confidence region (circle) can be identified as the target matching point; as... Figure 6-7 As shown, point e within the confidence region (ellipse) can be identified as the target matching point; as... Figure 8-9 As shown, point m within the confidence region (diamond) can be identified as the target matching point.
[0050] In special cases, if a point to be matched happens to fall on the vertical reference line, then that point on the vertical reference line is selected as the target matching point. If multiple points to be matched happen to fall on the vertical reference line, then the point closest to the center point is selected as the target matching point.
[0051] It should be noted that, in this embodiment of the application, by setting a confidence region, the target matching point is preferentially selected as the matching point that falls on the vertical reference line. If there is no matching point on the vertical reference line, the coordinate point that is closest to the vertical reference line is selected as the target matching point. The target matching point determined in this way has a higher correlation with the current point compared with other coordinate points.
[0052] S34: Verify the accuracy of the lane line calculation based on the relationship between the current point and the target matching point.
[0053] In a specific embodiment, after the target matching point is determined in step S32, the accuracy of the lane line calculation is verified based on the relationship between the current point and the target matching point.
[0054] This application provides a lane line accuracy verification method. After obtaining the actual lane line and the calculated lane line to be verified, the lane line direction is determined based on the actual lane line. Then, any coordinate point on the actual lane line is selected as the current point, and a confidence region is constructed based on the accuracy requirements of the calculated lane line, with the current point as the center point. The vertical reference line of this confidence region is perpendicular to the lane line direction. Then, the coordinate points on the calculated lane line within the confidence region are determined as matching points. The matching point with the shortest distance from the matching point to the vertical reference line is selected as the target matching point. Finally, the calculation accuracy of the calculated lane line is verified based on the relationship between the current point and the target matching point. This application, by setting a confidence region, prioritizes selecting the coordinate point with the shortest distance to the vertical reference line as the matching point. This matching point has a higher correlation with the current point than other coordinate points, thus better reflecting the calculation effect of the calculated lane line.
[0055] To clearly determine the target matching point, such as Figure 10 As shown, this application also discloses a lane line accuracy verification method, which includes:
[0056] The method specifically includes the following steps:
[0057] S100: Obtain the actual lane line and the calculated lane line of the lane line to be verified, and determine the direction of the lane line based on the actual lane line.
[0058] The actual lane lines are calculated using positioning coordinate data collected by high-precision equipment combined with the SLAM algorithm. The calculated lane lines are obtained using positioning coordinate data collected by lower-cost positioning equipment combined with the SLAM algorithm. The lane line direction is determined based on the actual lane lines. Specifically, two coordinate points can be selected on the actual lane lines, and the lane line direction can be calculated according to a preset formula. In a specific embodiment, the preset calculation formula can be: Where M(x1, y1) and N(x2, y2) are two points on the actual lane line.
[0059] S101: Select any coordinate point on the actual lane line as the current point, and construct a confidence region based on the accuracy requirements of the calculated lane line, using the current point as the center point.
[0060] The vertical reference line of the confidence region is perpendicular to the direction of the lane line.
[0061] In a specific embodiment, any coordinate point on the actual lane line can be selected as the current point. Using this current point as the center point, a confidence region is constructed based on the accuracy requirements of the calculated lane line. The vertical reference line of this confidence region is perpendicular to the lane line direction, and the confidence region can be circular (e.g., ...). Figure 4-5 As shown), ellipse (as shown) Figure 6-7 As shown), rhombus (as shown) Figure 8-9 (As shown) or other shapes, such as squares or rectangles. It should be noted that the size of the confidence region can be adjusted according to the actual accuracy requirements.
[0062] S102: Determine the coordinates of the lane lines within the confidence region as the points to be matched.
[0063] In a specific embodiment, the coordinate points on the calculated lane line that fall within the confidence region are determined as points to be matched. If there is no matching data in the confidence region, the accuracy of the positioning coordinates of this segment is not high; if there are multiple matching points in the confidence region, the multiple matching points are used as points to be matched.
[0064] In a specific embodiment, such as Figure 4-5 As shown, four points to be matched within the confidence region (circle) can be identified, specifically a, b, c, and d; as... Figure 6-7 As shown, two points to be matched within the confidence region (ellipse) can be identified, specifically e and f; as... Figure 8-9 As shown, two points to be matched within the confidence region (rhombus) can be identified, specifically m and n.
[0065] S103: Obtain the coordinates of each point to be matched, and calculate the distance from each point to be matched to the vertical reference line to obtain the first distance corresponding to each point to be matched.
[0066] S104: Determine the point to be matched corresponding to the shortest first distance as the target matching point.
[0067] In a specific embodiment, such as Figure 4-5 As shown, the target matching point can be determined to be a or c; as Figure 6-7 As shown, the target matching point can be determined as e; as Figure 8-9 As shown, the target matching point can be determined to be m.
[0068] In a specific embodiment, there may be multiple points to be matched, that is, multiple points to be matched have the same first distance and are all on the vertical reference line. In order to accurately match the target matching point with higher relevance, the method may further include: calculating the distance from each point to be matched to the center point to obtain the second distance corresponding to each point to be matched; and determining the point to be matched corresponding to the shortest second distance as the target matching point.
[0069] In specific embodiments, there may be multiple points to be matched corresponding to the shortest first distance, and these points may not be on the vertical reference line, such as... Figure 4-5 As shown, the target matching point can be determined as a or c. To accurately match target matching points with higher relevance, the method can further include: calculating the distance from each point to be matched to the parallel reference line of the confidence region, obtaining the third distance d3 corresponding to each point to be matched; determining the point to be matched corresponding to the shortest third distance d3 as the target matching point, and then... Figure 4-5 Therefore, coordinate point a can be finally determined as the target matching point.
[0070] or;
[0071] In specific embodiments, there may be multiple points to be matched corresponding to the shortest first distance, and these points may not be on the vertical reference line, such as... Figure 4-5 As shown, in order to accurately match target matching points with higher relevance, the method may further include: obtaining the coordinates of the current point and calculating the distance between each point to be matched and the current point to obtain the fourth distance d4 corresponding to each point to be matched; and determining the point to be matched corresponding to the shortest fourth distance d4 as the target matching point.
[0072] S105: After obtaining the target matching point corresponding to each coordinate point on the actual lane line, obtain the first coordinate of each coordinate point and the second coordinate of the target matching point corresponding to that coordinate point;
[0073] S106: Obtain multiple offset distances based on each first coordinate and the corresponding second coordinate;
[0074] S107: Verify the accuracy of lane line calculation based on multiple offset distances and lane line accuracy requirements.
[0075] Specifically, the above-mentioned verification of the lane line calculation accuracy based on multiple offset distances and lane line calculation accuracy requirements includes: determining the verification range according to the lane line calculation accuracy requirements; and calculating the lane line calculation accuracy based on the number of offset distances falling within the verification range.
[0076] This application provides a lane line accuracy verification method. After obtaining the actual lane line and the calculated lane line to be verified, the lane line direction is determined based on the actual lane line. Then, any coordinate point on the actual lane line is selected as the current point, and a confidence region is constructed based on the accuracy requirements of the calculated lane line, with the current point as the center point. The vertical reference line of this confidence region is perpendicular to the lane line direction. Then, the coordinate points on the calculated lane line within the confidence region are determined as matching points. The matching point with the shortest distance from the matching point to the vertical reference line is selected as the target matching point. Finally, the calculation accuracy of the calculated lane line is verified based on the relationship between the current point and the target matching point. This application, by setting a confidence region, prioritizes selecting the coordinate point with the shortest distance to the vertical reference line as the matching point. This matching point has a higher correlation with the current point than other coordinate points, thus better reflecting the calculation effect of the calculated lane line.
[0077] Corresponding to the aforementioned application function implementation method embodiments, this application also provides a lane line accuracy verification device, electronic device, and corresponding embodiments.
[0078] Figure 11 This is a schematic diagram of the lane line accuracy verification device shown in an embodiment of this application. See also... Figure 11 This application provides a lane line accuracy verification device, which specifically includes: a first processing module 111, a second processing module 112, a third processing module 113, a fourth processing module 114, and a fifth processing module 115, wherein:
[0079] The first processing module 111 is used to obtain the actual lane line and the calculated lane line of the lane line to be verified, and to determine the direction of the lane line based on the actual lane line.
[0080] The second processing module 112 is used to select any coordinate point on the actual lane line as the current point, take the current point as the center point, and construct a confidence region according to the accuracy requirements of the calculated lane line, wherein the vertical reference line of the confidence region is perpendicular to the direction of the lane line.
[0081] The third processing module 113 is used to determine the coordinate points on the solved lane line within the confidence area as the points to be matched;
[0082] The fourth processing module 114 is used to select the point to be matched that has the shortest distance from the vertical reference line as the target matching point.
[0083] The fifth processing module 115 is used to verify the calculation accuracy of the calculated lane line based on the relationship between the current point and the target matching point.
[0084] Preferably, the fourth processing module 114 is specifically used for:
[0085] Obtain the coordinates of each point to be matched, and calculate the distance from each point to be matched to the vertical reference line to obtain the first distance corresponding to each point to be matched;
[0086] The point to be matched corresponding to the shortest first distance is determined as the target matching point.
[0087] Preferably, if there are multiple matching points corresponding to the shortest first distance, and the matching points are on the vertical reference line, then the fourth processing module 114 is further configured to:
[0088] Calculate the distance from each point to be matched to the center point to obtain the second distance for each point to be matched.
[0089] The point to be matched corresponding to the shortest second distance is determined as the target matching point.
[0090] Preferably, if there are multiple matching points corresponding to the shortest first distance, and the matching points are not on the vertical reference line, then the fourth processing module 114 is further configured to:
[0091] Calculate the distance from each point to be matched to the parallel reference line of the confidence region to obtain the third distance corresponding to each point to be matched.
[0092] The point to be matched corresponding to the shortest third distance is determined as the target matching point.
[0093] Preferably, if there are multiple matching points corresponding to the shortest first distance, and the matching points are not on the vertical reference line, then the fourth processing module 114 is further configured to:
[0094] Obtain the coordinates of the current point and calculate the distance between each point to be matched and the current point to obtain the fourth distance corresponding to each point to be matched;
[0095] The point to be matched corresponding to the shortest fourth distance is determined as the target matching point.
[0096] Furthermore, after obtaining the target matching point corresponding to each coordinate point on the actual lane line, the fifth processing module 115 is specifically used for:
[0097] Obtain the first coordinate of each coordinate point and the second coordinate of the target matching point corresponding to that coordinate point;
[0098] Multiple offset distances are obtained based on each first coordinate and its corresponding second coordinate;
[0099] The accuracy of the calculated lane lines is verified based on multiple offset distances and the accuracy requirements of the calculated lane lines.
[0100] Preferably, the fifth processing module 115 is further configured to:
[0101] The verification range is determined based on the accuracy requirements of the calculated lane lines.
[0102] The accuracy of the lane line calculation is calculated based on the number of offset distances that fall within the verification range.
[0103] This application provides a lane line accuracy verification device. A first processing module, after acquiring the actual lane line and the calculated lane line to be verified, determines the lane line direction based on the actual lane line. Then, a second processing module selects any coordinate point on the actual lane line as the current point, and constructs a confidence region based on the accuracy requirements of the calculated lane line, with the current point as the center point. The vertical reference line of this confidence region is perpendicular to the lane line direction. Next, a third processing module determines the coordinate points on the calculated lane line within the confidence region as matching points. A fourth processing module selects the matching point with the shortest distance to the vertical reference line as the target matching point. Finally, a fifth processing module verifies the calculation accuracy of the calculated lane line based on the relationship between the current point and the target matching point. This application, by setting a confidence region and prioritizing the selection of the coordinate point with the shortest distance to the vertical reference line as the matching point, ensures that this matching point has a higher correlation with the current point compared to other coordinate points, thus better reflecting the calculation effect of the calculated lane line.
[0104] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated further here.
[0105] Figure 12This is a schematic diagram of the structure of an electronic device shown in an embodiment of this application.
[0106] See Figure 12 The electronic device 1200 includes a memory 1210 and a processor 1220.
[0107] The processor 1220 can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.
[0108] Memory 1210 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. ROM may store static data or instructions required by processor 1220 or other modules of the computer. Permanent storage devices may be read-write storage devices. Permanent storage devices may be non-volatile storage devices that retain stored instructions and data even when the computer is powered off. In some embodiments, permanent storage devices use mass storage devices (e.g., magnetic or optical disks, flash memory) as permanent storage devices. In other embodiments, permanent storage devices may be removable storage devices (e.g., floppy disks, optical drives). System memory may be a read-write storage device or a volatile read-write storage device, such as dynamic random access memory. System memory may store some or all of the instructions and data required by the processor during operation. Furthermore, memory 1210 may include any combination of computer-readable storage media, including various types of semiconductor memory chips (DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, memory 1210 may include a removable storage device that is readable and / or writable, such as a laser disc (CD), a read-only digital versatile optical disc (e.g., DVD-ROM, dual-layer DVD-ROM), a read-only Blu-ray disc, an ultra-high density optical disc, a flash memory card (e.g., SD card, mini SD card, Micro-SD card, etc.), a magnetic floppy disk, etc. Computer-readable storage media do not contain carrier waves or transient electronic signals transmitted wirelessly or via wired connections.
[0109] The memory 1210 stores executable code, which, when processed by the processor 1220, can cause the processor 1220 to execute part or all of the methods described above.
[0110] The solution of this application has been described in detail above with reference to the accompanying drawings. In the above embodiments, the descriptions of each embodiment have different emphases; parts not described in detail in a certain embodiment can be referred to in the relevant descriptions of other embodiments. Those skilled in the art should also understand that the actions and modules involved in the specification are not necessarily essential to this application. Furthermore, it is understood that the steps in the method of this application embodiment can be adjusted, combined, and deleted according to actual needs, and the modules in the device of this application embodiment can be combined, divided, and deleted according to actual needs.
[0111] Furthermore, the method according to this application can also be implemented as a computer program or computer program product, which includes computer program code instructions for performing some or all of the steps in the method described above.
[0112] Alternatively, this application may be implemented as a non-transitory machine-readable storage medium (or computer-readable storage medium, or machine-readable storage medium) storing executable code (or computer program, or computer instruction code) that, when executed by a processor of an electronic device (or electronic device, server, etc.), causes the processor to perform some or all of the steps of the methods described above according to this application.
[0113] Those skilled in the art will also understand that the various exemplary logic blocks, modules, circuits, and algorithm steps described in connection with the present application can be implemented as electronic hardware, computer software, or a combination of both.
[0114] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems and methods according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.
[0115] The various embodiments of this application have been described above. These descriptions are exemplary and not exhaustive, nor are they limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical application, or improvement of the technology in the market, or to enable others skilled in the art to understand the embodiments disclosed herein.
Claims
1. A method for verifying lane line accuracy, characterized in that, include: Obtain the actual lane line and the calculated lane line of the lane line to be verified, and determine the direction of the lane line based on the actual lane line; Select any coordinate point on the actual lane line as the current point, and use the current point as the center point to construct a confidence region according to the accuracy requirements of the calculated lane line. The vertical reference line of the confidence region is perpendicular to the direction of the lane line and passes through the current point. The coordinates of the solved lane line within the confidence region are determined as the points to be matched; The point to be matched that has the shortest distance from the vertical reference line is taken as the target matching point; The accuracy of the lane line calculation is verified based on the relationship between the current point and the target matching point.
2. The lane line accuracy verification method according to claim 1, characterized in that, The step of selecting the target matching point as the point with the shortest distance from the vertical reference line includes: Obtain the coordinates of each point to be matched, and calculate the distance from each point to be matched to the vertical reference line to obtain the first distance corresponding to each point to be matched; The point to be matched corresponding to the shortest first distance is determined as the target matching point.
3. The lane line accuracy verification method according to claim 2, characterized in that, If there are multiple points to be matched corresponding to the shortest first distance, and the points to be matched are on the vertical reference line, then the method further includes: Calculate the distance from each point to be matched to the center point to obtain the second distance for each point to be matched. The point to be matched corresponding to the shortest second distance is determined as the target matching point.
4. The lane line accuracy verification method according to claim 2, characterized in that, If there are multiple points to be matched corresponding to the shortest first distance, and the points to be matched are not on the vertical reference line, then the method further includes: Calculate the distance from each point to be matched to the parallel reference line of the confidence region to obtain the third distance corresponding to each point to be matched; the parallel reference line is parallel to the direction of the lane line and passes through the current point. The point to be matched corresponding to the shortest third distance is determined as the target matching point.
5. The lane line accuracy verification method according to claim 2, characterized in that, If there are multiple points to be matched corresponding to the shortest first distance, and the points to be matched are not on the vertical reference line, then the method further includes: Obtain the coordinates of the current point and calculate the distance between each point to be matched and the current point to obtain the fourth distance corresponding to each point to be matched; The point to be matched corresponding to the shortest fourth distance is determined as the target matching point.
6. The lane line accuracy verification method according to any one of claims 1-5, characterized in that, After obtaining the target matching point corresponding to each coordinate point on the actual lane line, the step of verifying the calculation accuracy of the lane line based on the relationship between the current point and the target matching point includes: Obtain the first coordinate of each coordinate point and the second coordinate of the target matching point corresponding to that coordinate point; Multiple offset distances are obtained based on each first coordinate and its corresponding second coordinate; The accuracy of the calculated lane lines is verified based on multiple offset distances and the accuracy requirements of the calculated lane lines.
7. The lane line accuracy verification method according to claim 6, characterized in that, The process of verifying the accuracy of the calculated lane lines based on multiple offset distances and the accuracy requirements of the calculated lane lines includes: The verification range is determined based on the accuracy requirements of the calculated lane lines. The accuracy of the lane line calculation is calculated based on the number of offset distances that fall within the verification range.
8. A lane line accuracy verification device, characterized in that, include: The first processing module is used to obtain the actual lane line and the calculated lane line of the lane line to be verified, and to determine the direction of the lane line based on the actual lane line. The second processing module is used to select any coordinate point on the actual lane line as the current point, and use the current point as the center point to construct a confidence region according to the accuracy requirements of the calculated lane line. The vertical reference line of the confidence region is perpendicular to the direction of the lane line and passes through the current point. The third processing module is used to determine the coordinate points on the solved lane line within the confidence area as the points to be matched; The fourth processing module is used to select the point to be matched that has the shortest distance from the vertical reference line as the target matching point. The fifth processing module is used to verify the calculation accuracy of the calculated lane lines based on the relationship between the current point and the target matching point.
9. An electronic device, characterized in that, include: processor; as well as A memory having executable code stored thereon, which, when executed by the processor, causes the processor to perform the lane line accuracy verification method as described in any one of claims 1-7.
10. A non-transitory machine-readable storage medium having executable code stored thereon, which, when executed by a processor of an electronic device, causes the processor to perform the lane line accuracy verification method as described in any one of claims 1-7.