CN115424228A - Pavement pit detection method, device, equipment and storage medium - Google Patents

Abstract

The embodiment of the present invention discloses a road surface pothole detection method, device, equipment and storage medium, which can obtain the first fitting curve by fitting the point cloud on a single laser radar scanning line; The cloud performs radial distance screening to obtain the first-level candidate point set; according to the azimuth, the first-level candidate point set is segmented to obtain the second-level candidate point set; the second-level candidate point set is fitted to obtain the second fitting curve, and According to the first fitting curve and the second fitting curve, the second-level candidate point set is screened to obtain the third-level candidate point set; the target point is obtained from the third-level candidate point set, and road potholes are determined according to the target point. Reliable pothole target points are obtained by multi-angle screening of the point cloud on a single lidar scanning line, and road potholes are determined based on the obtained pothole target points, making the pothole detection results more accurate and compatible with single lines And multi-line lidar application scenarios are more extensive.

Description

Road surface pothole detection method, device, equipment and storage medium

technical field

The embodiments of the present invention relate to the technical field of unmanned driving, and in particular to a method, device, equipment and storage medium for detecting road surface potholes.

Background technique

With the rapid development of unmanned driving technology, unmanned vehicles are becoming more and more common in daily life, and whether it is an open road or a closed factory area, potholes on the road will cause vehicle bumps, wheels stuck or even tire blowouts, thus Impact on the operation of unmanned vehicles.

In order to ensure the normal operation of unmanned vehicles, using lidar to detect road potholes is a relatively common detection method at present. And when using lidar for pothole detection, the interval threshold classification method is usually used to project the 3D point cloud acquired by the lidar into a two-dimensional occupancy grid, and then calculate the radial Finally, whether there is a pit between two laser scanning lines is judged by whether the actual obtained radial spacing is greater than the theoretical radial spacing threshold between adjacent scanning lines.

However, if the point on the scan line is not scanned to the theoretical position due to multiple reflections or being blocked by objects, the radial distance between adjacent scan lines will become larger, which will cause false detection based on the detection of the interval threshold classification method, and if there is no When the radar installed on the driver's car is a single-line lidar, the above method cannot be used for pothole detection. Therefore, the existing lidar pothole detection method not only affects the accuracy of pothole detection, but also cannot be applied to single-line lidar application scenarios. limited.

Contents of the invention

Embodiments of the present invention provide a road surface pothole detection method, device, equipment and storage medium, so as to realize accurate detection of road surface potholes.

In the first aspect, an embodiment of the present invention provides a method for detecting road surface potholes, which is applied to unmanned vehicles, including: fitting the point cloud on a single scanning line of the lidar to obtain a first fitting curve; The first fitting curve performs radial distance screening on the point cloud to obtain a first-level candidate point set; obtains the azimuth angle of each point in the first-level candidate point set, and calculates the first-level candidate point set according to the azimuth angle. The point set is screened in segments to obtain a second-level candidate point set; the second-level candidate point set is fitted to obtain a second fitting curve, and according to the first fitting curve and the second fitting curve The second-level candidate point set is screened to obtain a third-level candidate point set; a target point is obtained from the third-level candidate point set, and road potholes are determined according to the target point.

In the second aspect, the embodiment of the present invention provides a road surface pothole detection device, including: a first fitting curve acquisition module, which is used to fit the point cloud on a single scanning line of the lidar to obtain the first fitting curve ;

A first-level candidate point set acquisition module, configured to perform radial distance screening on the point cloud according to the first fitting curve to obtain a first-level candidate point set;

A second-level candidate point set acquisition module, configured to acquire the azimuth of each point in the first-level candidate point set, and perform segmentation screening on the first-level candidate point set according to the azimuth to obtain a second-level candidate point set;

A third-level candidate point set acquisition module, configured to fit the second-level candidate point set to obtain a second fitting curve, and perform the second-level fitting curve according to the first fitting curve and the second fitting curve The set of candidate points is screened to obtain a set of three-level candidate points;

The road surface pothole detection module is used to obtain the target point from the three-level candidate point set, and determine the road surface pothole according to the target point.

In a third aspect, an embodiment of the present invention provides an electronic device, and the electronic device includes:

one or more processors;

storage means for storing one or more programs,

When one or more programs are executed by one or more processors, the one or more processors implement the above method.

In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored, wherein the program implements the method as described above when executed by a processor.

In the technical solution of the embodiment of the present invention, reliable pothole target points are obtained by multi-angle screening of point clouds on a single laser radar scanning line, and road potholes are determined based on the obtained pothole target points, so that potholes The detection results are more accurate, and it is compatible with single-line and multi-line lidar at the same time, and the application scenarios are more extensive.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and thus It should be regarded as a limitation on the scope, and those skilled in the art can also obtain other related drawings based on these drawings without creative work.

FIG. 1 is a flow chart of a method for detecting road surface potholes provided by Embodiment 1 of the present invention;

Fig. 2 is a distributed schematic diagram of a laser radar harness provided by the present invention;

Fig. 3 is a flow chart of a method for detecting road surface potholes provided by the present invention;

Fig. 4 is a schematic diagram of detection results of a road pothole provided by the present invention;

Fig. 5 is a flow chart of a method for detecting road surface potholes provided by the present invention;

Fig. 6 is a schematic structural view of a road surface pothole detection device provided by the present invention;

Fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.

detailed description

The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, but not to limit the present invention.

In addition, it should be noted that, for the convenience of description, only parts related to the present invention are shown in the drawings but not all content. Before discussing the exemplary embodiments in more detail, it should be mentioned that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although the flowcharts describe various operations (or steps) as sequential processing, many of the operations may be performed in parallel, concurrently, or simultaneously. In addition, the order of operations can be rearranged. The process may be terminated when its operations are complete, but may also have additional steps not included in the figure. The processing may correspond to a method, software implementation, hardware implementation, and the like.

Fig. 1 is a flow chart of a road surface pothole detection method provided by an embodiment of the present invention. This embodiment is applicable to the situation of detecting road surface potholes, and the method can be implemented by the road surface pothole detection device in the embodiment of the present invention. For execution, the device may be implemented in software and/or hardware. As shown in Figure 1, the method specifically includes the following operations:

Step S101 , fitting the point cloud on a single scanning line of the lidar to obtain a first fitting curve.

Optionally, before fitting the point cloud on a single scanning line of the lidar to obtain the first fitting curve, it also includes: obtaining the point cloud on a single scanning line in the lidar coordinate system; Coordinate transformation is performed on the point cloud on a single scanning line to obtain the point cloud on a single scanning line in the vehicle coordinate system. The driving direction is the vertical axis of the horizontal plane, and the direction perpendicular to the horizontal plane is the vertical axis.

Specifically, the unmanned vehicle in this embodiment can be equipped with two 16-line laser radars, which are respectively installed on the left front and right front of the vehicle. The wiring harness distribution of the laser radars is shown in Figure 2. After obtaining the point cloud on a single scanning line in the lidar coordinate system, the point cloud data will be transformed from the lidar coordinate system 1 to the rear axle of the vehicle as the origin, and the right side of the vehicle as the horizontal horizontal axis X, with The driving direction of the vehicle is the vertical axis Y of the horizontal plane, and the vehicle coordinate system is the vertical axis Z perpendicular to the horizontal plane. Moreover, what is specifically acquired in this embodiment is the point cloud on a single scanning line within a certain angle range in front of the vehicle, and the specific value of the angle range is not limited in this embodiment.

Optionally, fitting the point cloud on a single scanning line of the lidar to obtain the first fitting curve includes: obtaining the point cloud on a single scanning line of the lidar; using the RANSAC algorithm to fit the points in the point cloud to obtain the first fitting curve.

It is worth mentioning that after obtaining the point cloud on a single scan line in the vehicle coordinate system, the RANSAC algorithm will be used to fit the points in the point cloud to obtain the first fitting curve. The first fitting curve is specific It can be expressed by the following formula (1):

y=ax ² +bx+c (1)

Among them, when using the RANSAC algorithm to fit the points in the point cloud, the coefficients (a, b, c) in the formula (1) can be obtained specifically, and a is called the first opening of the first fitting curve Spend. The principle of fitting the RANSAC algorithm based on known points is not the focus of this application, so it will not be described in detail in this embodiment.

Step S102, performing radial distance screening on the point cloud according to the first fitting curve to obtain a first-level candidate point set.

Optionally, perform radial distance screening on the point cloud according to the first fitting curve to obtain a set of first-level candidate points, including: obtaining the radial distance between the point cloud midpoint and the first fitting curve, and the vertical distance between the point cloud midpoint Vertical height: Points whose radial distance is greater than the distance threshold and whose vertical height is less than the height threshold are used as a set of first-level candidate points.

Specifically, when the first fitting curve is obtained, the radial distance and vertical height between the point cloud midpoint and the first fitting curve will be calculated, for example, point A exists in the point cloud, and point A is at the vehicle coordinate The coordinates in the system are (x1, y1, z1), and the abscissa of point A is substituted into the first fitting curve to obtain the point (x1, y2) on the first curve, then the diameter between point A and the first fitting curve The vertical distance d=y1-y2, and the vertical height of point A refers to the value z1 of point A on the vertical axis in the vehicle coordinate system. Of course, in this embodiment, point A is taken as an example for illustration, and the way to obtain the radial distance and vertical height of other points in the point cloud is roughly the same, and will not be repeated in this embodiment.

It should be noted that in this embodiment, the points in the point cloud can be screened according to the radial distance and vertical height of the point. For example, the distance threshold is 0.1m, and the height threshold is 0.2m. When the radial distance is greater than 0.1m and the vertical height is less than 0.2m, then the point is reserved, and all the retained points constitute a first-level candidate point set. Therefore, in this embodiment, the points in the point cloud are initially screened according to the radial distance and vertical height to obtain the first-level candidate point set. For example, when the radial distance d=0.15m of point A is determined, the vertical If the height is 0.1m, it can be determined that point A belongs to the first-level candidate point set.

Step S103, obtaining the azimuth angle of each point in the first-level candidate point set, and performing segmentation screening on the first-level candidate point set according to the azimuth angle to obtain a second-level candidate point set.

Optionally, according to the azimuth, the first-level candidate point set is segmented and screened to obtain the second-level candidate point set, including: determining the continuity of each point in the first-level candidate point set according to the azimuth, and obtaining points according to the continuous points. segment candidate point set; obtain the relevant parameters of each segment candidate point set, wherein the relevant parameters include the total value of the continuous azimuth angle, the total number of points, and the maximum value of the point’s horizontal coordinate difference; The segment candidate point set is retained to obtain the second-level candidate point set.

Specifically, after obtaining the first-level candidate point set, the azimuth angle of each point in the first-level candidate point set will also be obtained. Specifically, the Y-axis positive direction is 0 degrees, and the X-axis positive direction is rotated counterclockwise. With 1 degree as the minimum unit, the origin is used as the starting point to obtain the ray formed by the origin and each point, and the angle between the ray and the Y axis is obtained, and the determined angle is used as the azimuth of each point. After obtaining the azimuth angle of each point in the first-level candidate point set, the continuity of each point in the first-level candidate point set is determined according to the azimuth angle, and the segmented candidate point set is obtained according to the continuous points.

For example, the set of first-level candidate points includes {A B C D E F G H I J K L M N}, and the corresponding azimuth angles are {1 2 3 4 5 6 9 10 11 12 13 14 19 20} degrees, and the minimum unit is 1 degree, so that The azimuth angle difference between point F and point G is 3 degrees, so it is disconnected, and the azimuth angle between point K and point L is 5 degrees, so it is disconnected, so that three segment candidate point sets {A B C D E F}, {G H I J K L} and {M N}. Of course, this embodiment is only for illustration, and does not limit the number of points in the first-level candidate point set.

It should be noted that in this embodiment, after the segment candidate point set is obtained, the relevant parameters of each segment candidate point set will also be obtained, and the relevant parameters specifically include the total value of the continuous azimuth angle, the total number of points, and the number of points. The maximum value of the horizontal coordinate difference, for example, for the segment candidate point set {ABCDEF}, the total value of the corresponding continuous azimuth angle is 5 degrees, the total number of points is 6, and the segment candidate point set is on the horizontal axis The point corresponding to the minimum value is point A, and the coordinate value of the horizontal axis is x _A = 0.1, and the point corresponding to the maximum value on the horizontal axis of the horizontal plane is point D, and the coordinate value of the horizontal axis is x _D = 1.3, so the segment candidate point set The maximum value of the horizontal coordinate difference of the midpoint is △x=1.2; for the segment candidate point set {GHIJKL}, the total value of the corresponding continuous azimuth angles is 5 degrees, the total number of points is 6, and the horizontal coordinate difference of the points is the largest Value △x=1; for the segmentation candidate point set {MN}, the total value of the corresponding continuous azimuth angle is 1 degree, the total number of points is 2, and the maximum value of horizontal coordinate difference △x=0.5.

It should be noted that after obtaining the set of segment candidate points and the corresponding relevant parameters, the set of segment candidate points whose relevant parameters meet the preset conditions will be reserved. The preset conditions can specifically refer to the continuous azimuth angle The total value must be greater than 2 and less than 10, the total number of points must be greater than 5 and less than 100, and the maximum value of the point’s horizontal coordinate difference must be less than 2, so that the set of segment candidate points that meet the above preset conditions can be obtained as {A B C D E F} and {G H I J K L }, so that {A B C D E F} and {G H I J K L} that meet the preset conditions are used as the second-level candidate point set. Of course, the specific number of the second-level candidate point set is not limited in this embodiment.

Step S104, fitting the second-level candidate point set to obtain a second fitting curve, and filtering the second-level candidate point set according to the first fitting curve and the second fitting curve to obtain a third-level candidate point set.

Optionally, according to the first fitting curve and the second fitting curve, the second-level candidate point set is screened to obtain the third-level candidate point set, including: obtaining the first opening of the first fitting curve and the second-level candidate point set The second degree of opening of the corresponding second fitting curve; a set of secondary candidate points whose second degree of opening is within a specified range and smaller than a specified multiple of the first degree of opening is used as a set of third-level candidate points.

Specifically, after obtaining the second-level candidate point set, the RANSAC algorithm will be used again to fit the points in the second-level candidate point set to obtain the second fitting curve, so each second-level candidate point set corresponds to a second The second fitting curve, for example, the second fitting curve obtained by fitting the secondary candidate point set {A B C D E F} can be specifically expressed by the following formula (2):

y＝ex ² +fx+g (2)

Among them, when the RANSAC algorithm is used to fit the points in the second-level candidate point set, the coefficients (e, f, g) in the formula (2) can be obtained specifically, and e is called the second fitting curve. Two degrees of opening.

It should be noted that when the second opening is within the specified range and is smaller than the specified multiple of the first opening, the second-level candidate point set is regarded as the third-level candidate point set, that is, the second opening of the third-level candidate point set needs to be Satisfy the following formula (3)

Among them, k is the specified multiple, e _min is the minimum opening value, and e _max is the maximum opening value.

For example, when k=5, e _min =-20, e _max =-0.1, that is, the second opening value satisfies e<5a, and -20<e<-0.1, then it is determined that the secondary candidate point set {ABCDEF } As a set of three-level candidate points, of course, in this real-time method, only the specified range and the specified multiple are given as examples, and the specific values are not limited. The determination method for the second-level candidate point set {G HI JKL} is roughly the same, and will not be repeated in this embodiment, so that the third-level candidate point set that meets the conditions is determined to be {ABCDEF} by screening according to the opening degree.

Step S105, obtaining target points from the three-level candidate point set, and determining road surface potholes according to the target points.

Optionally, the target point is obtained from the third-level candidate point set, and the road surface pothole is determined according to the target point, including: obtaining a predetermined ground equation, and determining the target point below the ground in the third-level candidate point set according to the ground equation ; Obtain the average distance from the target point to the ground; when the average distance is greater than the depth threshold, cluster the target points to obtain clusters; obtain the associated information of the clusters, and determine the potholes on the road according to the associated information, where , the association information includes the coverage of the cluster and the center position of the cluster.

Specifically, after screening the point cloud on a single scanning line of the lidar according to the three angles of radial distance, continuous azimuth and opening degree, a qualified three-level candidate point set is obtained. Since the three-level candidate point set The points in are related to the potholes on the ground, so the potholes on the road surface can be obtained by detecting according to the three-level candidate point set.

In the technical solution of the embodiment of the present invention, reliable pothole target points are obtained by multi-angle screening of point clouds on a single laser radar scanning line, and road potholes are determined based on the obtained pothole target points, so that potholes The detection results are more accurate, and it is compatible with single-line and multi-line lidar at the same time, and the application scenarios are more extensive.

Fig. 3 is the flow chart of the method for detecting road surface potholes provided by the embodiment of the present invention. This embodiment is based on the above-mentioned embodiment, specifically for the above-mentioned step S105 to obtain the target point from the three-level candidate point set, and determine according to the target point Potholes on the road surface are described in detail, and the method steps specifically include the following operations:

Step S201, obtaining a predetermined ground equation, and determining a target point below the ground in the third-level candidate point set according to the ground equation.

Specifically, in this embodiment, the ground equation determined in advance in the vehicle coordinate system will be obtained, and the ground equation is shown in the following formula (4):

mx+ny+oz+p=0 (4)

Among them, after the ground equation is obtained, the target point located below the ground in the third-level candidate point set will be determined according to the ground equation, and the target point can be specifically determined by the following formula (5):

After calculating the d _A value of point A in the third-level candidate point set {ABCDEF} according to formula (5), if the value of d _A *o is less than 0, it can be determined that point A is located below the ground. Similarly, for the third-level candidate point set The points in are calculated using the above respectively. If it is determined that each point satisfies the above formula (5), it can be determined that the points ABCDEF in the third-level candidate point set are all located below the ground, and point ABCDEF is used as the target point.

Step S202, obtaining the average distance from the target point to the ground.

Among them, after the target point is determined, the average distance from all target points to the ground will be obtained, for example, the target point AB C D E F, the distance to the ground is |d1|, |d2|, |d3|, |d4|, |d5| and |d6|, then the average distance D=(|d1|+|d2|+|d3|+|d4|+|d5|+|d6|)/6 can be determined. Of course, this embodiment is only for illustration, and does not limit the specific number of target points.

Step S203, when the average distance is greater than the depth threshold, cluster the target points to obtain clusters.

Among them, after obtaining the average distance, it will be judged whether the average distance D is greater than the depth threshold. Specifically, K-Means clustering, mean shift clustering, or density-based clustering can be used for clustering. This embodiment does not limit the specific methods used for clustering target points, and about clustering The specific principle of the class is not the focus of this application, so it will not be repeated in this embodiment.

Step S204, acquiring associated information of the clusters, and determining road surface potholes according to the associated information.

Specifically, in this embodiment, after the clustering is performed, associated information corresponding to each cluster is also obtained, wherein the associated information includes the coverage of the cluster and the center position of the cluster. The position of the road pothole in the vehicle coordinate system is determined according to the center position of the cluster, and the size of the road pothole is determined according to the coverage. As shown in FIG. 4 , it is a schematic diagram of detection results of road potholes obtained in this embodiment, and the determined road potholes are marked in the form of dotted boxes in FIG. 4 .

In the technical solution of the embodiment of the present invention, reliable pothole target points are obtained by multi-angle screening of point clouds on a single laser radar scanning line, and road potholes are determined based on the obtained pothole target points, so that potholes The detection results are more accurate, and it is compatible with single-line and multi-line lidar at the same time, and the application scenarios are more extensive. And specifically, according to the three-level candidate points, the target points located below the ground are concentrated, and the road surface potholes are obtained through clustering operations, so that the determined road surface potholes are more accurate.

Fig. 5 is a flow chart of the road surface pothole detection method provided by the embodiment of the present invention. This embodiment is based on the above-mentioned embodiment, and specifically obtains the target point from the three-level candidate point set, and determines the road surface pothole according to the target point Afterwards, the road surface pothole detection results are verified, and the method steps specifically include the following operations:

Step S301, fitting the point cloud on a single scanning line of the lidar to obtain a first fitting curve.

Optionally, before fitting the point cloud on a single scanning line of the lidar to obtain the first fitting curve, it also includes: obtaining the point cloud on a single scanning line in the lidar coordinate system; Coordinate transformation is performed on the point cloud on a single scanning line to obtain the point cloud on a single scanning line in the vehicle coordinate system. The driving direction is the vertical axis of the horizontal plane, and the direction perpendicular to the horizontal plane is the vertical axis.

Step S302, performing radial distance screening on the point cloud according to the first fitting curve to obtain a first-level candidate point set.

Optionally, perform radial distance screening on the point cloud according to the first fitting curve to obtain a set of first-level candidate points, including: obtaining the radial distance between the point cloud midpoint and the first fitting curve, and the vertical distance between the point cloud midpoint Vertical height: Points whose radial distance is greater than the distance threshold and whose vertical height is less than the height threshold are used as a set of first-level candidate points.

Step S303, obtaining the azimuth angle of each point in the first-level candidate point set, and performing segmentation screening on the first-level candidate point set according to the azimuth angle to obtain the second-level candidate point set.

Optionally, according to the azimuth, the first-level candidate point set is segmented and screened to obtain the second-level candidate point set, including: determining the continuity of each point in the first-level candidate point set according to the azimuth, and obtaining points according to the continuous points. segment candidate point set; obtain the relevant parameters of each segment candidate point set, wherein the relevant parameters include the total value of the continuous azimuth angle, the total number of points, and the maximum value of the point’s horizontal coordinate difference; The segment candidate point set is retained to obtain the second-level candidate point set.

Step S304, fitting the second-level candidate point set to obtain a second fitting curve, and filtering the second-level candidate point set according to the first fitting curve and the second fitting curve to obtain a third-level candidate point set.

Optionally, according to the first fitting curve and the second fitting curve, the second-level candidate point set is screened to obtain the third-level candidate point set, including: obtaining the first opening of the first fitting curve and the second-level candidate point set The second degree of opening of the corresponding second fitting curve; a set of secondary candidate points whose second degree of opening is within a specified range and smaller than a specified multiple of the first degree of opening is used as a set of third-level candidate points.

Step S305, obtaining target points from the three-level candidate point set, and determining road surface potholes according to the target points.

Optionally, the target point is obtained from the third-level candidate point set, and the road surface pothole is determined according to the target point, including: obtaining a predetermined ground equation, and determining the target point below the ground in the third-level candidate point set according to the ground equation ; Obtain the average distance from the target point to the ground; when the average distance is greater than the depth threshold, cluster the target points to obtain clusters; obtain the associated information of the clusters, and determine the potholes on the road according to the associated information, where , the association information includes the coverage of the cluster and the center position of the cluster.

Step S306, verifying the detection result of road surface potholes.

Specifically, after the road surface potholes are determined according to the target points in this embodiment, the road surface pothole detection results will also be verified, specifically, the actual road surface potholes within the road surface detection range are obtained, and the actual road surface potholes are compared with Comparing the obtained road potholes, if the difference exceeds 10%, it is determined that the road pothole detection is invalid, and an alarm message will be issued to prompt the user to optimize or adjust the equipment to further ensure that the detection is invalid. Accuracy of road pothole detection.

In the technical solution of the embodiment of the present invention, reliable pothole target points are obtained by multi-angle screening of point clouds on a single laser radar scanning line, and road potholes are determined based on the obtained pothole target points, so that potholes The detection results are more accurate, and it is compatible with single-line and multi-line lidar at the same time, and the application scenarios are more extensive. By verifying the detection results of road potholes, when the detection is invalid, an alarm message is sent to prompt the user to optimize or adjust the equipment to further ensure the accuracy of road pothole detection.

6 is a schematic structural diagram of a road surface pothole detection device provided by an embodiment of the present invention, the device includes: a first fitting curve acquisition module 410, a first-level candidate point set acquisition module 420, a second-level candidate point set acquisition module 430, three Level candidate point set acquisition module 440 and road pothole detection module 450.

The first fitting curve acquisition module 410 is used to fit the point cloud on a single scanning line of the laser radar to obtain the first fitting curve;

The first-level candidate point set acquisition module 420 is used to perform radial distance screening on the point cloud according to the first fitting curve to obtain the first-level candidate point set;

The second-level candidate point set acquisition module 430 is used to obtain the azimuth angle of each point in the first-level candidate point set, and perform segmentation screening on the first-level candidate point set according to the azimuth to obtain the second-level candidate point set;

The third-level candidate point set acquisition module 440 is used to fit the second-level candidate point set to obtain the second fitting curve, and filter the second-level candidate point set according to the first fitting curve and the second fitting curve to obtain the third-level candidate point set. Level candidate point set;

The road pothole detection module 450 is configured to obtain target points from the three-level candidate point set, and determine road potholes according to the target points.

Optionally, the device also includes a coordinate transformation module, which is used to obtain the point cloud on a single scanning line in the lidar coordinate system;

Carry out coordinate transformation on the point cloud on a single scanning line in the lidar coordinate system to obtain the point cloud on a single scanning line in the vehicle coordinate system, where the vehicle coordinate system is centered on the rear axle of the vehicle and centered on the right side of the vehicle. The transverse axis of the horizontal plane takes the driving direction of the vehicle as the vertical axis of the horizontal plane, and takes the direction perpendicular to the horizontal plane as the vertical axis.

Optionally, the first fitting curve acquisition module is used to acquire the point cloud on a single scanning line of the lidar;

A RANSAC algorithm is used to fit the points in the point cloud to obtain a first fitting curve.

Optionally, the first-level candidate point set acquisition module is used to obtain the radial distance between the point cloud midpoint and the first fitting curve, and the vertical height of the point cloud midpoint;

The points whose radial distance of the points in the point cloud are greater than the distance threshold and whose vertical height is less than the height threshold are used as a set of first-level candidate points.

Optionally, the second-level candidate point set acquisition module is used to determine the continuity of each point in the first-level candidate point set according to the azimuth, and obtain the segmented candidate point set according to the continuous points;

Obtain the relevant parameters of each segment candidate point set, wherein the relevant parameters include the total value of the continuous azimuth angle, the total number of points, and the maximum value of the horizontal coordinate difference of the points;

The set of segmented candidate points whose relevant parameters meet the preset conditions are retained to obtain a set of secondary candidate points.

Optionally, the third-level candidate point set acquisition module is used to acquire the first opening degree of the first fitting curve and the second opening degree of the second fitting curve corresponding to the second-level candidate point set;

The second-level candidate point set whose second opening degree is within the specified range and smaller than the specified multiple of the first opening degree is used as the third-level candidate point set.

Optionally, the road surface pothole detection module is used to obtain a predetermined ground equation, and determine the target point located below the ground in the third-level candidate point set according to the ground equation;

Obtain the average distance from the target point to the ground;

When the average distance is greater than the depth threshold, the target points are clustered to obtain clusters;

Obtain the association information of the clusters, and determine the potholes on the road according to the association information, wherein the association information includes the coverage of the clusters and the center position of the clusters.

The above-mentioned device can execute the method for detecting road surface potholes provided by any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method. For technical details not exhaustively described in this embodiment, refer to the method provided in any embodiment of the present invention.

FIG. 7 shows a schematic structural diagram of an electronic device 10 that can be used to implement an embodiment of the present invention. Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers. Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (eg, helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the inventions described and/or claimed herein.

As shown in FIG. 7 , the electronic device 10 includes at least one processor 11, and a memory connected in communication with the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores There is a computer program executable by at least one processor, and the processor 11 can operate according to a computer program stored in a read-only memory (ROM) 12 or loaded from a storage unit 18 into a random access memory (RAM) 13. Various appropriate actions and processes are performed. In the RAM 13, various programs and data necessary for the operation of the electronic device 10 are also stored. The processor 11 , ROM 12 , and RAM 13 are connected to each other through a bus 14 . An input/output (I/O) interface 15 is also connected to the bus 14 .

Multiple components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices through a computer network such as the Internet and/or various telecommunication networks.

Processor 11 may be various general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing units (CPUs), graphics processing units (GPUs), various dedicated artificial intelligence (AI) computing chips, various processors that run machine learning model algorithms, digital signal processing processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes various methods and processes described above, such as a road surface pothole detection method.

In some embodiments, the road surface pothole detection method can be implemented as a computer program, which is tangibly embodied in a computer-readable storage medium, such as the storage unit 18 . In some embodiments, part or all of the computer program may be loaded and/or installed on the electronic device 10 via the ROM 12 and/or the communication unit 19 . When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the method for detecting road surface potholes described above can be executed. Alternatively, in other embodiments, the processor 11 may be configured in any other appropriate way (for example, by means of firmware) to execute the method for detecting road surface potholes.

Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips Implemented in a system of systems (SOC), load programmable logic device (CPLD), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include being implemented in one or more computer programs executable and/or interpreted on a programmable system including at least one programmable processor, the programmable processor Can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.

Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus, so that the computer program causes the functions/operations specified in the flowcharts and/or block diagrams to be implemented when executed by the processor. A computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of the present invention, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus or device. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. More specific examples of machine-readable storage media would include one or more wire-based electrical connections, portable computer discs, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, compact disk read only memory (CD-ROM), optical storage, magnetic storage, or any suitable combination of the foregoing.

In order to provide interaction with the user, the systems and techniques described herein can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display)) for displaying information to the user. monitor); and a keyboard and pointing device (eg, a mouse or a trackball) through which the user can provide input to the electronic device. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.

The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system. The components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

A computing system can include clients and servers. Clients and servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also known as a cloud computing server or a cloud host. It is a host product in the cloud computing service system to solve the problems of difficult management and weak business expansion in traditional physical hosts and VPS services. defect.

It should be understood that steps may be reordered, added or deleted using the various forms of flow shown above. For example, each step described in the present invention may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution of the present invention can be achieved, there is no limitation herein.

The above specific implementation methods do not constitute a limitation to the protection scope of the present invention. It should be apparent to those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made depending on design requirements and other factors. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. A road surface pothole detection method, applied to unmanned vehicles, is characterized in that, comprising: Fitting the point cloud on a single scanning line of the lidar to obtain the first fitting curve; performing radial distance screening on the point cloud according to the first fitting curve to obtain a set of first-level candidate points; Obtain the azimuth angle of each point in the first-level candidate point set, and perform segmentation screening on the first-level candidate point set according to the azimuth angle to obtain a second-level candidate point set; Fitting the second-level candidate point set to obtain a second fitting curve, and filtering the second-level candidate point set according to the first fitting curve and the second fitting curve to obtain a third-level candidate point gather; A target point is acquired from the three-level candidate point set, and road potholes are determined according to the target point. 2. The method according to claim 1, wherein, before the point cloud on a single scanning line of the lidar is fitted to obtain the first fitting curve, it also includes: Obtain the point cloud on a single scan line in the lidar coordinate system; Coordinate transformation is performed on the point cloud on a single scan line in the lidar coordinate system to obtain the point cloud on a single scan line in the vehicle coordinate system, wherein the vehicle coordinate system takes the rear axle of the vehicle as its original center, and The right side of the vehicle is the horizontal axis, the vehicle driving direction is the horizontal axis, and the direction perpendicular to the horizontal plane is the vertical axis. 3. The method according to claim 2, wherein said fitting the point cloud on a single scanning line of the lidar to obtain the first fitting curve comprises: Obtain a point cloud on a single scanning line of the lidar; The RANSAC algorithm is used to fit the points in the point cloud to obtain the first fitting curve. 4. The method according to claim 3, wherein said carrying out radial distance screening to said point cloud according to said first fitting curve to obtain a first-level candidate point set comprises: Obtain the radial distance between the point cloud midpoint and the first fitting curve, and the vertical height of the point cloud midpoint; Taking the points whose radial distance is greater than a distance threshold and whose vertical height is less than a height threshold among points in the point cloud as the first-level candidate point set. 5. method according to claim 2, is characterized in that, described according to described azimuth to described first-level candidate point set and carry out segmentation screening and obtain secondary candidate point set, comprising: determining the continuity of each point in the first-level candidate point set according to the azimuth angle, and obtaining a segmentation candidate point set according to the continuous points; Obtain relevant parameters of each of the segmented candidate point sets, wherein the relevant parameters include the total value of continuous azimuth angles, the total number of points, and the maximum value of the horizontal coordinate difference of points; The set of segment candidate points whose relevant parameters meet the preset conditions are retained, and the set of secondary candidate points is obtained. 6. method according to claim 1, is characterized in that, described according to described first fitting curve and described second fitting curve to described secondary candidate point set is screened and obtains tertiary candidate point set, include: Acquiring a first opening of the first fitting curve and a second opening of a second fitting curve corresponding to the set of secondary candidate points; The second-level candidate point set whose second opening degree is within a specified range and smaller than a specified multiple of the first opening degree is used as the third-level candidate point set. 7. The method according to claim 1, wherein said acquiring target points from said three-level candidate point set, and determining road surface potholes according to said target points, comprises: Obtaining a predetermined ground equation, and determining a target point located below the ground in the third-level candidate point set according to the ground equation; Obtain the average distance from the target point to the ground; When the average value of the distance is greater than the depth threshold, the target points are clustered to obtain a cluster; Acquiring association information of the clusters, and determining the road surface potholes according to the association information, wherein the association information includes the coverage of the clusters and the center position of the clusters. 8. A road surface pothole detection device, characterized in that it comprises: The first fitting curve acquisition module is used to fit the point cloud on the single scanning line of the lidar to obtain the first fitting curve; A first-level candidate point set acquisition module, configured to perform radial distance screening on the point cloud according to the first fitting curve to obtain a first-level candidate point set; A second-level candidate point set acquisition module, configured to acquire the azimuth of each point in the first-level candidate point set, and perform segmentation screening on the first-level candidate point set according to the azimuth to obtain a second-level candidate point set; A third-level candidate point set acquisition module, configured to fit the second-level candidate point set to obtain a second fitting curve, and perform the second-level fitting curve according to the first fitting curve and the second fitting curve The set of candidate points is screened to obtain a set of three-level candidate points; The road surface pothole detection module is used to obtain the target point from the three-level candidate point set, and determine the road surface pothole according to the target point. 9. An electronic device, characterized in that the electronic device comprises: one or more processors; storage means for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors are made to implement the method according to any one of claims 1-7. 10. A computer-readable storage medium, on which a computer program is stored, wherein, when the program is executed by a processor, the method according to any one of claims 1-7 is implemented.

Images