Lane line detection processing method, and related device and system

Abstract

The application discloses a lane line detection processing method and related devices and systems. The method comprises the following steps: acquiring a heading angle of a shape point of a lane line to be detected; determining a heading angle threshold of the lane line based on a road level of a road to which the lane line belongs and road function information of the lane line; and comparing a difference value of the acquired heading angle with the heading angle threshold, so as to determine a non-smooth position of the lane line. The method not only improves the detection efficiency of the lane line, but also avoids the drawbacks of missed detection or insufficient accuracy caused by the inability to accurately judge due to different display scales in the manual detection process, and further improves the smoothness of the lane line of the high-precision map.

Description

Technical Field

[0001] This invention relates to the field of map production, and in particular to a method for detecting and processing lane lines, as well as related devices and systems. Background Technology

[0002] With the development of technology, advanced driver assistance systems (ADAS) and autonomous driving have become hot topics in technological research because they can help drivers drive safely. Currently, one technological path for the implementation of ADAS and autonomous driving relies on "high-definition maps." Compared with ordinary maps, high-definition maps represent the real world in a more refined and accurate way. For example, ordinary maps do not express more detailed information about roads, while high-definition maps use lane lines to represent each lane of the road.

[0003] When high-definition maps serve as the data foundation for advanced driver assistance systems (ADAS) or autonomous driving, they directly impact vehicle control and driving decisions. Therefore, quality inspection of high-definition maps is a crucial technical step in their production process. In particular, lane line quality inspection is currently typically done manually. However, manual inspection suffers from low efficiency and, more importantly, is prone to omissions or insufficient accuracy. Summary of the Invention

[0004] In view of the technical defects and drawbacks existing in the prior art, the present invention provides a lane line detection and processing method, and related apparatus and system to overcome the above problems or at least partially solve the above problems.

[0005] As one aspect of this invention, a lane line detection and processing method is provided, which may include:

[0006] Obtain the heading angle of the shape point of the lane line to be detected;

[0007] Based on the road grade of the road to which the lane line belongs and the road function information of the lane line, the heading angle threshold of the lane line is determined;

[0008] Compare the heading angle difference between two adjacent shape points of the lane line with the heading angle threshold.

[0009] If the difference in heading angle is greater than the heading angle threshold, then the positions of the two adjacent shape points are determined as the non-smooth positions of the lane line.

[0010] Optionally, after determining the heading angle threshold of the lane line, the method further includes: adjusting the heading angle threshold according to the attribute information of the lane line, wherein the attribute information of the lane line includes at least one of the speed limit information of the road segment where the lane line is located and the curvature of the lane line.

[0011] Optionally, after determining the positions of the two adjacent shape points as the non-smooth positions of the lane line, the method further includes: smoothing the non-smooth positions of the lane line.

[0012] As a second aspect of the present invention, a lane line detection and processing device is provided, which may include:

[0013] The heading angle acquisition module is used to acquire the heading angle of the shape points of the lane line to be detected;

[0014] The threshold determination module is used to determine the heading angle threshold of the lane line based on the road level of the road to which the lane line belongs and the road function information of the lane line;

[0015] The comparison module is used to compare the heading angle difference between two adjacent shape points in the lane line shape points with the heading angle threshold.

[0016] The position determination module is used to determine the position of the two adjacent shape points as the non-smooth position of the lane line if the difference in heading angle is greater than the heading angle threshold.

[0017] As a third aspect of the present invention, a lane line detection and processing system is provided, which may include: a server and a terminal device;

[0018] The terminal device is used to collect lane line data, which includes several shape points of the lane lines; the server is equipped with a lane line detection and processing device as described in the first aspect, used to process the collected lane lines.

[0019] As a fourth aspect of the present invention, a map display system is provided, which may include: a server and a terminal device;

[0020] The server is equipped with a lane line detection and processing device as described in the first aspect above, used to smooth the collected lane lines; the terminal device is used to display the smoothed lane lines.

[0021] As a fifth aspect of the present invention, a computer-readable storage medium is provided, wherein computer-executable instructions are stored, which, when executed by a processor, implement the lane line detection processing method as described in the first aspect.

[0022] As a sixth aspect of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the lane line detection processing method as described in the first aspect.

[0023] The embodiments of the present invention achieve at least the following technical effects:

[0024] Based on the road classification and road function information of the lane lines, a heading angle threshold is determined for each lane line. Then, the obtained heading angle difference is compared with the heading angle threshold to identify the unevenness of the lane lines. This method not only improves the detection efficiency of lane lines but also avoids the drawbacks of manual detection, such as missed detections or insufficient accuracy due to inaccurate judgments caused by different display scales, further improving the smoothness of lane lines in high-precision maps.

[0025] Optionally, the heading angle threshold can be adjusted based on the speed limit information of the road to which the lane line belongs and / or the curvature of the lane line to further improve the judgment accuracy, thereby making the lane lines of the high-precision map produced more consistent with the lane lines on the actual road.

[0026] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures described in the written description, claims, and drawings.

[0027] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0028] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0029] Figure 1 A flowchart of the lane line detection and processing method provided in an embodiment of the present invention;

[0030] Figure 2 A schematic diagram illustrating the selection of shape points representing the shape of a lane line on a lane line, provided in an embodiment of the present invention;

[0031] Figure 3 This is a schematic diagram of a heading angle measurement method provided in an embodiment of the present invention;

[0032] Figure 4 A flowchart illustrating the implementation of step S20 in an embodiment of the present invention;

[0033] Figure 5 This is a schematic diagram of the lane line detection and processing device provided in an embodiment of the present invention;

[0034] Figure 6 A flowchart of the second lane line detection and processing method provided in the embodiments of the present invention;

[0035] Figure 7 This is a schematic diagram of the structure of the second lane line detection and processing device provided in an embodiment of the present invention;

[0036] Figure 8 A flowchart of the third lane line detection and processing method provided in the embodiments of the present invention;

[0037] Figure 9 A flowchart of the first smoothing method provided in the embodiments of the present invention;

[0038] Figure 10 A schematic diagram of curvature calculation provided for an embodiment of the present invention;

[0039] Figure 11 This is a schematic diagram illustrating a smoothing process for non-smooth positions provided in an embodiment of the present invention;

[0040] Figure 12 A flowchart of another smoothing method provided in an embodiment of the present invention;

[0041] Figure 13 This is a schematic diagram illustrating another method for smoothing non-smooth positions provided in an embodiment of the present invention;

[0042] Figure 14 This is a schematic diagram of the structure of the third lane line detection and processing device provided in an embodiment of the present invention;

[0043] Figure 15 A flowchart of the fourth lane line detection and processing method provided in the embodiments of the present invention;

[0044] Figure 16 This is a schematic diagram of the fourth lane line detection and processing device provided in an embodiment of the present invention;

[0045] Figure 17 This is a schematic diagram of the structure of a lane line detection and processing system provided in an embodiment of the present invention;

[0046] Figure 18 This is a schematic diagram of the structure of a map display system provided in an embodiment of the present invention. Detailed Implementation

[0047] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0048] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0049] Example 1

[0050] This invention provides a lane line detection and processing method, which can be used to detect and process uneven lane line locations, such as... Figure 1 As shown, the following steps may be included:

[0051] Step S11: Obtain the heading angle of the shape point of the lane line to be detected.

[0052] In this embodiment of the invention, the shape points on the lane lines are points used to create high-precision map lane lines. The shape points can accurately represent the shape of the continuously extending lane lines. During the high-precision map creation process, a high-precision data acquisition vehicle is needed to collect laser point clouds for creating the high-precision map. The collected lane line data includes several shape points of the lane lines. The position coordinates of the shape points can be obtained from the point cloud data, and the heading angle of the shape points can be obtained from the position coordinates.

[0053] Step S12: Determine the heading angle threshold of the lane line based on the road level of the road to which the lane line belongs and the road function information of the lane line.

[0054] Because different road grades and lane markings have different road function information, the heading angle thresholds for lane markings vary during road construction. Therefore, the heading angle thresholds for lane markings can be determined based on the road grade of the road to which the lane marking belongs and the road function information of the lane marking.

[0055] It should be noted that the execution order of steps S11 and S12 in the embodiments of the present invention is not important. Step S11 can be executed first and then step S12, or step S12 can be executed first and then step S11, or steps S11 and S12 can be executed simultaneously. The embodiments of the present invention do not impose specific limitations on this.

[0056] Step S13: Compare the heading angle difference between two adjacent shape points in the lane line shape points with the heading angle threshold.

[0057] To avoid unevenness in lane lines in high-precision maps generated from point cloud data, which would cause the lane lines to mismatch their actual shape, this invention addresses this issue. The inventors have discovered that unevenness can be located by comparing the difference in heading angles between shape points that accurately represent the lane line shape with a heading angle threshold for the lane line. This method is not only efficient but also easy to implement.

[0058] Step S14: If the heading angle difference is greater than the heading angle threshold, then the positions of the two adjacent shape points are determined as the non-smooth positions of the lane line.

[0059] The lane line detection and processing method provided in this embodiment of the invention not only improves the detection efficiency of lane lines, but also avoids the drawbacks of missed detection or insufficient accuracy caused by the inability to make accurate judgments due to different display scales during manual detection, and further improves the smoothness of lane lines in high-precision maps.

[0060] The following is a detailed description of each step in the embodiments of the present invention:

[0061] In step S11 above, the heading angle of the shape point of the lane line to be detected is obtained.

[0062] The heading angle refers to the angle between the vehicle speed and the Earth's North Pole. In this embodiment of the invention, it means taking the next shape point after the current shape point and sequentially calculating the angle between the line connecting the current shape point and the next shape point and true north. During the acquisition of these shape points, more shape points can be selected where the lane line shape changes significantly, and fewer shape points can be selected where the lane line shape changes little. For example, refer to... Figure 2 The diagram shows a schematic of an actual lane line to be detected. Shape points representing the lane line shape are selected on the middle lane line. To better represent the changes in the lane line shape, more shape points are selected at the turning points of the lane line shape, and fewer shape points are selected at the straight points of the lane line.

[0063] Specifically, a high-precision data acquisition vehicle can be used to collect lane line data, which includes several shape points of the lane lines; alternatively, a high-precision data acquisition vehicle can be used to collect road point cloud data, and then geometric object access functions can be used to perform coordinate transformation to select shape points. Geometric object sets are one of the most widely used object sets in Geographic Information System (GIS) platforms, including various object categories and data structure classes. They enable operations such as feature symbolization and feature annotation of geometric objects containing geometric shapes, facilitating the creation, deletion, editing, and other analytical processing of geographic information, thereby converting road data into coordinate data. Since the coordinate information of shape points can be obtained from point cloud data, the heading angle of the shape points can be obtained from the coordinate information.

[0064] In a specific embodiment, the implementation of step S11 may include the following steps: obtaining the position coordinates of shape points on the lane line to be detected and their adjacent shape points; obtaining the line connecting adjacent shape points based on the obtained position coordinates; and determining the angle between the line connecting adjacent shape points and the due north direction as the heading angle of the shape point.

[0065] For example, refer to Figure 3 As shown, three shape points on a lane line are N, N+1, and N+2, where shape point N and its adjacent shape points N+1 and N+2 are ordered sequentially according to the lane's travel direction. In this embodiment, the angle between the line connecting shape points N and N+1 and due north is θ, where θ is the heading angle of shape point N; similarly, the angle between the line connecting shape points N+1 and N+2 and due north is α, where α is the heading angle of shape point N+1. Of course, in a lane line, the heading angle of the last shape point can be the same as that of the second-to-last shape point; this embodiment of the invention does not impose a specific limitation on this.

[0066] In step S12 above, the heading angle threshold of the lane line is determined based on the road level of the road to which the lane line belongs and the road function information of the lane line.

[0067] The road classification of lane markings is based on the nature of the road, which can be categorized as highway, urban expressway, or ordinary road, among others. Generally, highways have a larger radius of curvature than urban expressways and ordinary roads. For example, highways have a radius of curvature of at least 100m, urban expressways at least 50m, and ordinary roads at least 15m.

[0068] The road function information refers to the functional division of roads during application, which can specifically include main roads, ramps, acceleration and deceleration lanes, etc. For example, according to domestic lane standards, domestic lanes are arranged from left to right according to the direction of travel, and the left lane line belongs to the right lane. Because the functions of the lanes are different, the heading angle thresholds of the left and right lane lines are different.

[0069] This invention determines the heading angle threshold for lane lines based on the road classification and road function information of the road to which the lane lines belong. Specifically, refer to... Figure 4 As shown, the following steps may be included:

[0070] Step S121: Determine the standard threshold value of the heading angle of the road based on the road grade of the road to which the lane line belongs and the road function information of the lane line.

[0071] In this step, the standard threshold for the heading angle of the aforementioned road can be determined directly based on the road grade of the road to which the lane line belongs and the road function information of the lane line. Alternatively, it can be determined based on the road curvature radius threshold determined by the road grade of the road to which the lane line belongs and the road function information of the lane line.

[0072] The radius of curvature is the reciprocal of the curvature. The curvature of a plane curve is the rate of rotation of the tangent angle about a point on the curve with respect to the arc length, indicating the degree to which the curve deviates from a straight line. For a curve, it is equal to the radius of the arc closest to that point. The larger the radius of the circle, the smaller the curvature, and the closer it is to a straight line.

[0073] For example, a standard threshold for the heading angle of a road is determined based on a radius of curvature threshold and a preset distance dividing the lane lines. This can be achieved using the following formula 1:

[0074]

[0075] Where R is the radius of curvature threshold and L is the preset average point distance.

[0076] The average point distance refers to the average straight-line distance between each adjacent shape point.

[0077] The preset average point distance in this embodiment of the invention can be set based on experience. After obtaining the radius of curvature threshold of a curve, the length of the curve can be calculated based on the circumference, and the preset average point distance of the shape points on the curve is also known. By calculation, the number of parts into which the curve is divided can be determined, thereby obtaining the angle threshold of the angle change between adjacent shape points.

[0078] Step S122: Adjust the standard threshold of the heading angle based on the average point distance of the shape points of the lane line to obtain the heading angle threshold of the lane line. This can be achieved using the following formula 2:

[0079]

[0080] Where R is the radius of curvature threshold and l is the average point distance.

[0081] It should be noted that the average point distance of l in step S122 is determined based on the actual situation of the shape points of the lane line to be detected obtained in step S11. After the length of the lane line to be detected and the number of shape points are determined, the average point distance of the shape points of the lane line to be detected can be calculated. Therefore, in this embodiment, step S12 needs to be executed after step S11.

[0082] For example, if the radius of curvature threshold of the lane line is 25m, then the minimum perimeter of the curve is 50π. If the average distance between the points of the above shape is calculated to be 1.09m, then the minimum circumference is divided into 50π / 1.09≈144.11 segments. The angle threshold is 360° / 144.11≈2.498°. Therefore, the maximum heading angle threshold between adjacent shape points can be 2.498° or 2.5°.

[0083] In step S13 above, the difference in heading angle between two adjacent shape points of the lane line is compared with the heading angle threshold.

[0084] For example, the difference between the heading angles of shape point N and shape point N+1 obtained in step S11 is |θ-α|. The absolute value between them is taken as the difference and compared with the heading angle threshold of the lane line determined in step S12.

[0085] In step S14 above, if the difference in heading angle is greater than the heading angle threshold, then the positions of the two adjacent shape points are determined as the non-smooth positions.

[0086] If the heading angle difference |θ-α| in step S13 is greater than the above angle threshold, for example, greater than the maximum angle threshold of 2.5° in step S12, then the positions of shape point N and shape point N+1 are determined as unsmooth positions, and the above unsmooth positions need to be smoothed; if it is less than or equal to the maximum angle threshold of 2.5° in step S12, then the positions of shape point N and shape point N+1 are determined as smooth positions, and the above smooth positions do not need to be smoothed.

[0087] This invention determines the heading angle threshold of lane lines based on the road grade and road function information of the road to which the lane lines belong. Then, it compares the obtained heading angle difference with the heading angle threshold to determine the non-smooth locations of the lane lines. This method not only improves the detection efficiency of lane lines but also avoids the drawbacks of manual detection, such as missed detections or insufficient accuracy due to inaccurate judgment caused by different display scales, further improving the smoothness of lane lines in high-precision maps.

[0088] Based on the same inventive concept, embodiments of the present invention provide a lane line detection and processing device, referring to... Figure 5 As shown, it may include: a heading angle acquisition module 11, a threshold determination module 12, a comparison module 13, and a position determination module 14, and its working principle is as follows:

[0089] The heading angle acquisition module 11 acquires the heading angle of the shape point of the lane line to be detected. Specifically, the heading angle acquisition module 11 acquires the position coordinates of the shape point on the lane line to be detected and its adjacent shape points; based on the acquired position coordinates, it obtains the line connecting the adjacent shape points, and determines the angle between the line connecting the adjacent shape points and the due north direction as the heading angle of the shape point.

[0090] The threshold determination module 12 determines the heading angle threshold of the lane line based on the road grade of the road to which the lane line belongs and the road function information of the lane line. Specifically, the threshold determination module 12 determines the standard threshold of the heading angle of the road according to the road grade of the road to which the lane line belongs and the road function information of the lane line; the threshold determination module 12 adjusts the standard threshold of the heading angle according to the average point distance of the shape points of the lane line to obtain the heading angle threshold of the lane line.

[0091] The comparison module 13 compares the difference in heading angle between two adjacent shape points of the lane line with the heading angle threshold. If the difference in heading angle is greater than the heading angle threshold, the position determination module 14 determines the position of the two adjacent shape points as the non-smooth position of the lane line.

[0092] For the technical effects and other specific descriptions of this embodiment, please refer to the relevant content of the above method, which will not be repeated here.

[0093] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the aforementioned lane line detection and processing method. A computer device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the aforementioned lane line detection and processing method. For some technical effects and other specific descriptions of the embodiments of the present invention, please refer to the relevant content of the above methods, which will not be repeated here.

[0094] Example 2

[0095] This invention provides another method for detecting and processing lane lines, referring to... Figure 6 As shown, the following steps may be included:

[0096] Step S21: Obtain the heading angle of the shape point of the lane line to be detected.

[0097] Step S22: Determine the heading angle threshold of the lane line based on the road level of the road to which the lane line belongs and the road function information of the lane line.

[0098] Step S23: Adjust the heading angle threshold according to the lane line attribute information. The lane line attribute information includes at least one of the following: the speed limit information of the road segment where the lane line is located, and the curvature of the lane line.

[0099] Step S24: Compare the heading angle difference between two adjacent shape points in the lane line shape points with the heading angle threshold.

[0100] Step S25: If the heading angle difference is greater than the heading angle threshold, then the positions of the two adjacent shape points are determined as the non-smooth positions of the lane line.

[0101] The steps S21, S22, S24 and S25 in the embodiments of the present invention are the same as steps S11, S12, S13 and S14 in Embodiment 1. Specific examples, beneficial effects and other specific descriptions can be found in the relevant content of Embodiment 1 above, and will not be repeated here.

[0102] It should be noted that after step S22 in the embodiment of the present invention, step S23 needs to be executed, that is: the heading angle threshold is adjusted according to the attribute information of the lane line.

[0103] The attribute information of the lane line includes at least one of the following: the speed limit information of the road segment where the lane line is located and the curvature of the lane line.

[0104] For example, the heading angle thresholds for lane markings differ between sections of a highway with a speed limit of 80 km / h and those with a speed limit of 120 km / h. This is because higher speeds require a larger turning radius, resulting in a higher heading angle threshold. Similarly, the curvature of lane markings also affects the heading angle threshold. For instance, on a relatively straight highway, the heading angle threshold is lower, while on highway sections with curves, the threshold is higher due to the varying curvature.

[0105] In this embodiment of the invention, the heading angle threshold is adjusted by using the speed limit information of the road to which the lane line belongs and / or the curvature of the lane line, thereby further improving the judgment accuracy and making the lane lines of the high-precision map produced more consistent with the lane lines on the actual road.

[0106] Based on the same inventive concept, embodiments of the present invention also provide another lane line detection and processing device, referring to... Figure 7 As shown, it may include: a heading angle acquisition module 21, a threshold determination module 22, a threshold adjustment module 23, a comparison module 24, and a position determination module 25, and its working principle is as follows:

[0107] The heading angle acquisition module 21, threshold determination module 22, comparison module 24 and position determination module 25 have the same functions and effects as the heading angle acquisition module 11, threshold determination module 12, comparison module 13 and position determination module 14 in Embodiment 1, and will not be described again here.

[0108] It should be noted that, compared with Embodiment 1 above, a threshold adjustment module 23 is added. The threshold adjustment module 23 adjusts the heading angle threshold according to the attribute information of the lane line. The attribute information of the lane line includes at least one of the speed limit information of the road segment where the lane line is located and the curvature of the lane line.

[0109] For details regarding the technical effects and other specific descriptions of the device in this embodiment, please refer to the relevant content of the above method, which will not be repeated here.

[0110] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the aforementioned lane line detection and processing method. A computer device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the aforementioned lane line detection and processing method. For some technical effects and other specific descriptions of the embodiments of the present invention, please refer to the relevant content of the above methods, which will not be repeated here.

[0111] Example 3

[0112] This invention provides a third method for detecting and processing lane lines, referring to... Figure 8 As shown, the following steps may be included:

[0113] Step S31: Obtain the heading angle of the shape point of the lane line to be detected.

[0114] Step S32: Determine the heading angle threshold of the lane line based on the road level of the road to which the lane line belongs and the road function information of the lane line.

[0115] Step S33: Compare the heading angle difference between two adjacent shape points in the lane line shape points with the heading angle threshold.

[0116] Step S34: If the heading angle difference is greater than the heading angle threshold, then the positions of the two adjacent shape points are determined as the non-smooth positions of the lane line.

[0117] Step S35: Smooth the uneven parts of the lane lines.

[0118] In this embodiment of the invention, steps S31, S32, S33 and S34 are the same as steps S11, S12, S13 and S14 in embodiment 1, respectively. For specific examples, beneficial effects and other specific descriptions, please refer to the relevant content of embodiment 1 above, which will not be repeated here.

[0119] Compared with Embodiment 1, this embodiment of the invention adds step S35, namely: smoothing the unsmooth positions of the lane lines.

[0120] Specifically, step S35 above can be implemented in the following two ways:

[0121] <Method 1>

[0122] The implementation of method 1 in this embodiment of the invention is as follows: Figure 9 As shown, the following steps may be included:

[0123] Step S3511: Obtain the position and curvature of several shape points adjacent to the non-smooth position.

[0124] The curvature of each shape point on the lane line can be obtained by taking the coordinates of the shape point and the two adjacent shape points. Therefore, the radius of curvature of the curve at the shape point can be obtained by taking the reciprocal.

[0125] For example, refer to Figure 10As shown in the figure, there are three shape points on the lane line, namely N, N-1, and N+1. Using the coordinates of these three shape points, X1, Y1, X2, and Y2 can be calculated. Then, using these values, the curvature of the curve where shape point N is located can be calculated. The curvature of shape point N can be obtained using the following formula 3:

[0126]

[0127] The curvature of the curve containing all shape points can be calculated using the above formula. After calculating the curvature of the lane lines, the curvature of the curves containing all the shape points can be denoised. This embodiment of the invention uses existing denoising methods to eliminate the noise, such as three-standard-deviation denoising or binning denoising; this embodiment does not specifically limit the method.

[0128] Step S3512: Construct a fitting curve based on the position and curvature of the obtained shape points.

[0129] The fitted curve refers to a curve drawn based on given discrete data points. Specifically, it is formed by establishing data relationships (mathematical models), finding a series of tiny straight line segments, connecting these interpolation points to form a curve, and thus creating a smooth fitted curve.

[0130] For example, refer to Figure 11 As shown, the positions of shape points N-1, N, and N+1 are the non-smooth positions determined in Example 3. The shape points are connected by straight lines, as shown by the double-point discontinuous line in the figure. This non-smooth position needs to be smoothed. Based on the curvature of shape points N-2, N-3, N+2, N+3, and N+4 before and after this non-smooth position determined in step S3511, a fitting curve is constructed according to the determined curvature and the coordinates of several shape points before and after it, as shown in the figure. Figure 11 As shown in the figure, the smooth solid line is the constructed fitting curve.

[0131] Step S3513: Map the shape points at the non-smooth position onto the fitted curve, and form a smoothed lane line by using the mapped shape points and several adjacent shape points.

[0132] This step involves mapping and projecting the shape points at the non-smooth locations onto the fitted curve constructed in step S3512, obtaining the positions of the projected points as new shape points.

[0133] Also refer to Figure 11As shown, the positions of shape points N-1, N, and N+1 mapped onto the fitted curve are indicated by the black triangles in the figure. These are used as new shape points. The shape points at the smoothed positions are connected to the new shape points mapped onto the fitted curve at the non-smoothed positions to form smooth lane lines. It should be noted that the final lane lines are formed by connecting line segments, not the fitted curve (or the smooth curve) shown in the figure. This is because in the process of creating high-precision maps, the lane lines between shape points are vector data, and only vector straight lines (line segments) can be used to represent lane lines in high-precision maps. Therefore, the smooth lane lines formed by connecting all shape points with line segments are the lane lines obtained in this embodiment of the invention. In this embodiment, the double-point discontinuous dashed lines are the actual lane lines. It is necessary to reconnect the new shape points obtained at shape points N-1, N, and N+1 to form the final smooth lane lines, achieving the smoothing effect.

[0134] <Method 2>

[0135] The implementation of this method 2 in this embodiment of the invention refers to... Figure 12 As shown, the following steps may be included:

[0136] Step S3521: Determine the shape points that need to be deleted at the non-smooth positions and delete them.

[0137] Reference Figure 13 As shown, through the above step S34, the position between shape point N-1, shape point N', and shape point N+1 can be determined as the non-smooth position in this embodiment. By comparing shape points N-1, N', and N+1 at the non-smooth position, as well as shape points N-2, N-3, N+2, N+3, and N+4 before and after the non-smooth position, it can be seen that shape point N' has the largest change in heading angle. Therefore, shape point N' can be directly deleted, and then shape points N-1 and N+1 can be directly connected to form a smooth lane line.

[0138] Step S3522: Obtain the position and curvature of several shape points adjacent to the non-smooth position.

[0139] Step S3523: Construct a fitting curve based on the position and curvature of the obtained shape points.

[0140] Step S3524: Smoothed lane lines obtained from the constructed fitted curve.

[0141] The specific implementations of steps S3522, S3523, and S3524 in Method 2 can be referred to steps S3511, S3512, and S3513 above, and will not be repeated here. It should be noted that in Method 2, the mapping step in step S3513 is no longer executed, and it is replaced by deleting shape point N'.

[0142] This invention constructs a fitted curve by calculating the curvature of several shape points before and after an unsmooth position. Then, the shape points at the unsmooth position are mapped onto the fitted curve as new shape points, or shape points with significant changes in heading angle are directly deleted. Finally, the shape points are connected sequentially to form a smooth curve. This method rapidly processes unsmooth positions on lane lines by quickly determining the changes in heading angle and projecting them onto the fitted curve, thus generating smooth lane lines. Compared to manual detection and comparison, this method generates smooth lane lines more conveniently and quickly, saving significant resource costs and improving the efficiency of high-precision map production.

[0143] Based on the same inventive concept, embodiments of the present invention also provide a third lane line detection and processing device, referring to... Figure 14 As shown, it may include: a heading angle acquisition module 31, a threshold determination module 32, a comparison module 33, a position determination module 34, and a smoothing processing module 35, and its working principle is as follows:

[0144] The heading angle acquisition module 31, threshold determination module 32, comparison module 33, and position determination module 34 have the same functions and effects as the heading angle acquisition module 11, threshold determination module 12, comparison module 13, and position determination module 14 in Embodiment 1, and will not be described again here.

[0145] It should be noted that, compared with Embodiment 1 above, a smoothing module 35 is added. The smoothing module 35 smooths the unsmooth positions of the lane line. Specifically, the smoothing module 35 obtains the positions and curvatures of several adjacent shape points before and after the unsmooth position, and constructs a fitting curve based on the obtained positions and curvatures of the shape points; maps the shape points at the unsmooth position onto the fitting curve, and forms a smoothed lane line through the mapped shape points and several adjacent shape points. Alternatively, the smoothing module 35 determines the shape points that need to be deleted at the unsmooth position and deletes them; obtains the positions and curvatures of several adjacent shape points before and after the unsmooth position, and constructs a fitting curve based on the obtained positions and curvatures of the shape points, and obtains a smoothed lane line based on the constructed fitting curve.

[0146] For details regarding the technical effects and other specific descriptions of the device in this embodiment, please refer to the relevant content of the above method, which will not be repeated here.

[0147] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the aforementioned lane line detection and processing method. A computer device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the aforementioned lane line detection and processing method. For some technical effects and other specific descriptions of the embodiments of the present invention, please refer to the relevant content of the above methods, which will not be repeated here.

[0148] Example 4

[0149] This invention provides a fourth method for detecting and processing lane lines, referring to... Figure 15 As shown, the following steps may be included:

[0150] Step S41: Obtain the heading angle of the shape point of the lane line to be detected.

[0151] Step S42: Determine the heading angle threshold of the lane line based on the road level of the road to which the lane line belongs and the road function information of the lane line.

[0152] Step S43: Adjust the heading angle threshold according to the lane line attribute information. The lane line attribute information includes at least one of the following: the speed limit information of the road segment where the lane line is located and the curvature of the lane line.

[0153] Step S44: Compare the heading angle difference between two adjacent shape points in the lane line shape points with the heading angle threshold.

[0154] Step S45: If the heading angle difference is greater than the heading angle threshold, then the positions of the two adjacent shape points are determined as the non-smooth positions of the lane line.

[0155] Step S46: Smooth the uneven parts of the lane lines.

[0156] In this embodiment of the invention, steps S41, S42, S43, S44 and S45 are the same as steps S21, S22, S23, S24 and S25 in embodiment 2, respectively. Step S46 is the same as step S35 in embodiment 3. Specific examples, beneficial effects and other specific descriptions can be found in the relevant content of embodiments 2 and 3 above, and will not be repeated here.

[0157] This invention adjusts the heading angle threshold by using the speed limit information of the road to which the lane line belongs and / or the curvature of the lane line, further improving the judgment accuracy and making the lane lines on the high-precision map more consistent with the lane lines on the actual road. Furthermore, a fitting curve is constructed by calculating the curvature of several shape points before and after the unsmooth position. Then, the shape points at the unsmooth position are mapped onto the fitting curve as new shape points, or shape points with large changes in heading angle are directly deleted. Finally, the shape points are connected sequentially to form a smooth curve. This method quickly processes the unsmooth positions on the lane line by rapidly judging the changes in heading angle and projecting the fitting curve, thereby generating smooth lane lines. Compared with manual detection and comparison, it is more convenient and faster to generate smooth lane lines, saving significant resource costs and improving the efficiency of high-precision map production.

[0158] Based on the same inventive concept, this invention also provides a fourth lane line detection and processing device, referring to... Figure 16 As shown, it may include: a heading angle acquisition module 41, a threshold determination module 42, a threshold adjustment module 43, a comparison module 44, a position determination module 45, and a smoothing processing module 46, and its working principle is as follows:

[0159] The heading angle acquisition module 41, threshold determination module 42, comparison module 44, and position determination module 45 have the same functions and effects as the heading angle acquisition module 11, threshold determination module 12, comparison module 13, and position determination module 14 in Embodiment 1, respectively. The threshold adjustment module 43 has the same functions and effects as the threshold adjustment module 23 in Embodiment 2. The smoothing processing module 46 has the same functions and effects as the smoothing processing module 35 in Embodiment 3. The embodiments of the present invention will not be described again here.

[0160] For details regarding the technical effects and other specific descriptions of the device in this embodiment, please refer to the relevant content of the above method, which will not be repeated here.

[0161] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the aforementioned lane line detection and processing method. A computer device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the program, implements the aforementioned lane line detection and processing method. For some technical effects and other specific descriptions of the embodiments of the present invention, please refer to the relevant content of the above methods, which will not be repeated here.

[0162] Example 5

[0163] This invention provides a lane line detection and processing system, referring to... Figure 17As shown, it may include: a server 51 and a terminal device 52. The terminal device 52 is used to collect lane line data, which includes a number of shape points of the lane lines. The server 51 is equipped with a lane line detection and processing device as shown in Embodiments 1 to 4, which is used to process the collected lane lines.

[0164] This invention determines the heading angle threshold of lane lines based on the road grade and road function information of the road to which the lane lines belong. Then, it compares the obtained heading angle difference with the heading angle threshold to determine the non-smooth locations of the lane lines. This method not only improves the detection efficiency of lane lines but also avoids the drawbacks of manual detection, such as missed detections or insufficient accuracy due to inaccurate judgment caused by different display scales, further improving the smoothness of lane lines in high-precision maps.

[0165] Optionally, the heading angle threshold can be adjusted based on the speed limit information of the road to which the lane line belongs and / or the curvature of the lane line to further improve the judgment accuracy, thereby making the lane lines of the high-precision map produced more consistent with the lane lines on the actual road.

[0166] Example 6

[0167] This invention provides a map display system, referring to... Figure 18 As shown, it may include: a server 61 and a terminal device 62. The server 61 is equipped with a lane line detection and processing device as shown in Embodiments 1 to 4, which is used to smooth the collected lane lines; the terminal device 62 is used to display the smoothed lane lines.

[0168] The embodiments of the present invention not only improve the detection efficiency of lane lines, but also avoid the drawbacks of missed detection or insufficient accuracy caused by the inaccurate judgment due to different display scales during manual detection. Furthermore, it improves the smoothness of lane lines in high-precision maps. By displaying the smoothed lane lines, the lane lines in the high-precision maps produced are more consistent with the lane lines on the actual roads, further improving the user experience.

[0169] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0170] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0171] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0172] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0173] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting and processing lane lines, comprising: Obtain the heading angle of the shape point of the lane line to be detected; Based on the road grade of the road to which the lane line belongs and the road function information of the lane line, the standard threshold for the heading angle of the road is determined; the standard threshold for the heading angle is adjusted according to the average point distance of the shape points of the lane line to obtain the heading angle threshold of the lane line. Compare the heading angle difference between two adjacent shape points of the lane line with the heading angle threshold. If the difference in heading angle is greater than the heading angle threshold, then the positions of the two adjacent shape points are determined as the non-smooth positions of the lane line.

2. The method according to claim 1, further comprising, after determining the heading angle threshold of the lane line: The heading angle threshold is adjusted based on the attribute information of the lane line, which includes at least one of the following: speed limit information of the road segment where the lane line is located and the curvature of the lane line.

3. The method according to claim 1, further comprising, after determining the positions of the two adjacent shape points as the non-smooth positions of the lane line: The uneven parts of the lane lines are smoothed.

4. The method according to claim 3, wherein smoothing the uneven areas of the lane lines comprises: Obtain the positions and curvatures of several adjacent shape points before and after the non-smooth position, and construct a fitting curve based on the obtained positions and curvatures of the shape points; The shape points at the non-smooth locations are mapped onto the fitted curve, and the smoothed lane lines are formed by the mapped shape points and several adjacent shape points.

5. The method according to claim 3, wherein smoothing the non-smooth position comprises: Identify and delete the shape points that need to be deleted at the non-smooth locations; The positions and curvatures of several adjacent shape points before and after the non-smooth position are obtained, and a fitting curve is constructed based on the obtained position and curvature of the shape points. The smoothed lane line is obtained based on the constructed fitting curve.

6. The method according to any one of claims 1 to 5, wherein obtaining the heading angle of the shape point of the lane line to be detected includes: Obtain the position coordinates of shape points on the lane line to be detected and their adjacent shape points; Based on the obtained position coordinates, the line connecting adjacent shape points is obtained, and the angle between the line connecting adjacent shape points and the due north direction is determined as the heading angle of the shape point.

7. A lane marking detection and processing device, comprising: The heading angle acquisition module is used to acquire the heading angle of the shape points of the lane line to be detected; The threshold determination module is used to determine the standard threshold of the heading angle of the road based on the road level of the road to which the lane line belongs and the road function information of the lane line; and to adjust the standard threshold of the heading angle according to the average point distance of the shape points of the lane line to obtain the heading angle threshold of the lane line. The comparison module is used to compare the heading angle difference between two adjacent shape points in the lane line shape points with the heading angle threshold. The position determination module is used to determine the position of the two adjacent shape points as the non-smooth position of the lane line if the difference in heading angle is greater than the heading angle threshold.

8. The apparatus according to claim 7, further comprising: A smoothing module is used to smooth out the non-smooth parts of the lane lines.

9. A lane line detection and processing system, comprising: Servers and terminal devices; The terminal device is used to collect lane line data, which includes several shape points of the lane lines. The server is equipped with a lane line detection and processing device as described in claim 7 or 8, used to process the collected lane lines.

10. A map display system, comprising: Servers and terminal devices; The server is equipped with the lane line detection and processing device as described in claim 8, which is used to smooth the collected lane lines. The terminal device is used to display the smoothed lane lines.

11. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the lane line detection processing method as described in any one of claims 1 to 6.

12. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the lane line detection processing method as described in any one of claims 1 to 6.

Images