Road object height detection method, device, electronic equipment and medium

Abstract

The embodiments of this specification provide a method, apparatus, electronic device, and medium for detecting the height of road objects. A road coordinate system is pre-determined based on the actual road surface plane formed by laser point cloud data of the target road section. Based on this system, the first laser point cloud data of the target road section is converted from the lidar coordinate system to the road coordinate system to obtain second laser point cloud data. This second laser point cloud data is then clustered and segmented to identify the height of the corresponding target object based on each type of point cloud data obtained. This eliminates height detection errors caused by the road surface's inclination relative to the standard ground plane, thereby improving the accuracy of lidar height measurements of road objects.

Description

Technical Field

[0001] The embodiments of this specification relate to the field of intelligent transportation technology, and in particular to a method, device, electronic device, and medium for detecting the height of road objects. Background Art

[0002] Today, damage to road infrastructure and traffic accidents caused by vehicles exceeding height limits remain common. This not only increases the maintenance costs of height-restricted facilities like tunnels and bridges, but also poses a serious threat to the safety of drivers. To minimize the risk of collisions caused by vehicles exceeding height limits, height detection can be performed on roads near the entrances to these facilities, providing early warnings for vehicles exceeding height limits. However, the accuracy of height detection significantly impacts the reliability of these early warnings. Therefore, a more accurate method for detecting the height of road objects is needed. Summary of the Invention

[0003] The embodiments of this specification provide a method, device, electronic device, and medium for detecting the height of road objects.

[0004] In a first aspect, an embodiment of this specification provides a method for detecting the height of a road object, the method comprising:

[0005] Acquire first laser point cloud data of a target road section, wherein a target object is carried on a road surface of the target road section;

[0006] Converting the first laser point cloud data from a laser radar coordinate system to a road surface coordinate system to obtain second laser point cloud data, wherein the road surface coordinate system is determined based on a road surface plane formed by the road surface laser point cloud data of the target road section;

[0007] The second laser point cloud data is clustered and segmented to obtain N types of point cloud data, and the height value of the corresponding target object is obtained based on each type of point cloud data with the road surface plane as a reference, where N is an integer greater than or equal to 1.

[0008] Furthermore, clustering and segmentation processing is performed on the second laser point cloud data to obtain N types of point cloud data, including:

[0009] The second laser point cloud data is clustered based on the x-axis distance and y-axis distance between different points to obtain N types of point cloud data, and in the same type of point cloud data, the x-axis distance between two adjacent points is less than a first preset threshold, and the y-axis distance is less than a second preset threshold, wherein the x-axis direction is the road width direction, and the y-axis direction is the traveling direction of the target road section, and the first preset threshold is different from the second preset threshold.

[0010] Furthermore, in the second laser point cloud data, the laser point cloud density in the x-axis direction is greater than the laser point cloud density in the y-axis direction, and the first preset threshold is less than the second preset threshold.

[0011] Furthermore, converting the first laser point cloud data from the laser radar coordinate system to the road surface coordinate system to obtain second laser point cloud data includes:

[0012] The first laser point cloud data is input into a preconfigured coordinate transformation model to obtain second laser point cloud data in the road surface coordinate system, wherein the coordinate transformation model includes a coordinate rotation matrix, and the coordinate rotation matrix is ​​determined based on the inclination angle of the road surface plane in the lidar coordinate system.

[0013] Furthermore, the coordinate rotation matrix includes one or more combinations of the following rotation matrices:

[0014] A first rotation matrix that rotates the laser point cloud coordinates around the X-axis of the laser radar coordinate system, wherein the first rotation matrix is ​​determined based on the angle between the Y-axis of the laser radar coordinate system and the road surface plane;

[0015] A second rotation matrix that rotates the laser point cloud coordinates around the Y axis of the laser radar coordinate system, wherein the second rotation matrix is ​​determined based on the angle between the X axis of the laser radar coordinate system and the road surface plane;

[0016] A third rotation matrix that rotates the laser point cloud coordinates around the Z axis of the laser radar coordinate system, wherein the third rotation matrix is ​​determined based on the angle between the X axis of the laser radar coordinate system and the reference vertical plane of the road surface plane, wherein the reference vertical plane is the yoz plane in the road surface coordinate system corresponding to the road surface plane, the x-axis direction of the road surface coordinate system is the road surface width direction, the y-axis direction is the traveling direction of the target road section, and the z-axis direction is the direction perpendicular to the road surface plane.

[0017] In a second aspect, an embodiment of this specification provides a method for detecting the height of a road object, the method comprising:

[0018] Acquire first laser point cloud data of the target road section;

[0019] Converting the first laser point cloud data from a laser radar coordinate system to a ground coordinate system to obtain second laser point cloud data;

[0020] performing clustering and segmentation processing on the second laser point cloud data based on x-axis distances and y-axis distances between different points to obtain N types of point cloud data, wherein in the same type of point cloud data, the x-axis distance between two adjacent points is less than a first preset threshold, and the y-axis distance is less than a second preset threshold, wherein the x-axis direction is a road width direction, the y-axis direction is a travel direction of the target road section, N is an integer greater than or equal to 1, and the first preset threshold is different from the second preset threshold;

[0021] Based on the N types of point cloud data, a height value of a vehicle traveling on the target road section is obtained.

[0022] In a third aspect, an embodiment of this specification provides a road object height detection device, the device comprising:

[0023] a data acquisition module, configured to acquire first laser point cloud data of a target road section, wherein a target object is carried on the road surface of the target road section;

[0024] a coordinate conversion module, configured to convert the first laser point cloud data from a laser radar coordinate system to a ground coordinate system to obtain second laser point cloud data, wherein the road surface coordinate system is determined based on a road surface plane formed by the road surface laser point cloud data of the target road section;

[0025] The height detection module is used to cluster and segment the second laser point cloud data to obtain N types of point cloud data, and obtain the height value of the corresponding target object based on each type of point cloud data with the road surface plane as a reference, where N is an integer greater than or equal to 1.

[0026] In a fourth aspect, an embodiment of this specification provides a road surface object height detection device, the device comprising:

[0027] An acquisition module, used to acquire first laser point cloud data of a target road section;

[0028] a conversion module, configured to convert the first laser point cloud data from a laser radar coordinate system to a road surface coordinate system to obtain second laser point cloud data;

[0029] a cluster segmentation module, configured to perform cluster segmentation processing on the second laser point cloud data based on x-axis distances and y-axis distances between different points, to obtain N types of point cloud data, wherein in the same type of point cloud data, the x-axis distance between two adjacent points is less than a first preset threshold, and the y-axis distance is less than a second preset threshold, wherein the x-axis direction is the road width direction, the y-axis direction is the travel direction of the target road section, N is an integer greater than or equal to 1, and the first preset threshold is different from the second preset threshold;

[0030] The vehicle height determination module is used to obtain the vehicle height value of the vehicle traveling on the target road section based on the N types of point cloud data.

[0031] In a fifth aspect, an embodiment of this specification provides an electronic device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the road object height detection method provided in the first or second aspect above are implemented.

[0032] In a sixth aspect, an embodiment of this specification provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the road surface object height detection method provided in the first or second aspect above.

[0033] One embodiment of this specification provides a method for detecting the height of road objects. A road coordinate system is first determined based on the actual road surface plane formed by laser point cloud data of a target road section. Based on this, the first laser point cloud data of the target road section is converted from the lidar coordinate system to the road coordinate system to obtain second laser point cloud data. This second laser point cloud data is then clustered and segmented to identify the height of the corresponding target object based on each type of point cloud data. This process calibrates the lidar coordinate system using the actual road surface plane as a reference plane, eliminating height detection errors caused by the road surface's inclination relative to a standard ground plane and improving the accuracy of lidar height measurements of road objects. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A schematic diagram of a laser radar height measurement scenario provided in an embodiment of this specification;

[0035] Figure 2 A flowchart of a method for detecting the height of road objects provided in the first aspect of the embodiment of this specification;

[0036] Figure 3 A flowchart of a method for detecting the height of road objects provided in accordance with the second aspect of the present disclosure;

[0037] Figure 4 A module block diagram of a road object height detection device provided in the third aspect of the embodiments of this specification;

[0038] Figure 5 A module block diagram of a road object height detection device provided in the fourth aspect of the embodiment of this specification;

[0039] Figure 6 This is a structural diagram of an electronic device provided in the fifth aspect of the embodiments of this specification. DETAILED DESCRIPTION

[0040] Figure 1 A schematic diagram of an exemplary laser radar altimetry scenario is shown in FIG. Figure 1 As shown, a laser radar 110 can be mounted on a bracket 101 provided on the road to collect laser point cloud data on a target road section, thereby detecting the height of objects 120, such as vehicles and pedestrians, carried on the road surface, i.e., the road surface 100, in the target road section. For example, the laser radar 110 can be a 16-line laser radar to achieve detection of long-distance areas.

[0041] The specific installation location of the LiDAR 110 can be determined based on the actual scenario. For example, in one scenario, the LiDAR 110 can be installed approximately 7 meters above the road surface 100. The radar's transmitting surface is tilted downward in the Y-axis direction, with a depression angle θ between 15 and 20 degrees. The intersection of the radar's transmitting centerline and the road surface 100 is approximately 20 meters from the radar's projection on the road surface 100.

[0042] When in use, the laser radar 110 can send the collected laser point cloud data of the target road section to the control device, and the control device executes the road object height detection method provided in the embodiment of this specification to realize the height detection of road objects in the target road section.

[0043] Taking the vehicle overheight warning scenario as an example, the road object that the laser radar 110 needs to detect can be a vehicle traveling on the target road section. After obtaining the vehicle height detection result, it can further determine whether the vehicle is overheight based on the detected height value and the height limit value of the height limit facility ahead, thereby issuing an early warning to the overheight vehicle when the vehicle is overheight.

[0044] Of course, in addition to being used in vehicle overheight warning scenarios, the road object height detection method provided in this embodiment can also be used in other application scenarios. For example, it can also be used to identify the height of road obstacles in unmanned driving scenarios. This embodiment does not limit this.

[0045] In order to better understand the technical solutions provided by the embodiments of this specification, the technical solutions of the embodiments of this specification are described in detail below through the accompanying drawings and specific embodiments. It should be understood that the embodiments of this specification and the specific features in the embodiments are detailed descriptions of the technical solutions of the embodiments of this specification, rather than limitations on the technical solutions of this specification. In the absence of conflict, the embodiments of this specification and the technical features in the embodiments can be combined with each other.

[0046] First, as Figure 2 As shown, the road object height detection method provided in the embodiment of this specification includes at least the following steps S101 to S103.

[0047] Step S101 : obtaining first laser point cloud data of a target road section, wherein a target object is carried on the road surface of the target road section.

[0048] The target road section is the road section where the height measurement of road objects is required, and is also the road section covered by the field of view of the laser radar. The target object is a road object that requires height detection. For example, the target object can be a vehicle traveling on the target road section, which is determined according to the actual application scenario. After the laser radar is installed at the detection point on the road, the first laser point cloud data of the target road section can be collected. It is understandable that the first laser point cloud data includes the point cloud data of the target object carried on the road surface within the field of view of the laser radar, as well as the point cloud data of the road surface that is not blocked by the target object.

[0049] Step S102 : converting the first laser point cloud data from the laser radar coordinate system to the road surface coordinate system to obtain second laser point cloud data, wherein the road surface coordinate system is determined based on the road surface plane formed by the road surface laser point cloud data of the target road section.

[0050] It should be noted that the first laser point cloud data collected in step S101 is the point cloud coordinates in the laser radar coordinate system. Generally speaking, the laser radar coordinate system is constructed with the front of the transmitting surface as the positive direction of the Y axis, the right side as the positive direction of the X axis, and the top as the positive direction of the Z axis. After the laser radar is installed in the road scene, the direction of each coordinate axis in the laser radar coordinate system is determined, such as Figure 1 As shown in the figure, in this scenario, due to the LiDAR installation angle θ, the Y axis in the LiDAR coordinate system is tilted downward toward the road surface. Therefore, before performing height detection, the LiDAR coordinate system must be calibrated to determine the height of the target object relative to a reference plane.

[0051] During the research process, the inventors found that most roads are not standard ground planes. For example, there is a slight slope in the extension direction, or the road itself is tilted in the left and right directions due to drainage issues when it was built. If the standard ground plane is used as the calibration reference for the coordinate system, the error in the height detection results of road objects will increase, especially for long-distance measurement, which is more affected by the degree of road inclination. The longer the distance, the greater the height error. Therefore, this embodiment uses the road plane of the actual scene as the reference plane to calibrate the lidar coordinate system, so that the XOY plane of the calibrated lidar coordinate system is parallel to the road plane, and the Z axis is perpendicular to the road plane. In other words, the first laser point cloud data is converted from the lidar coordinate system to the road coordinate system. This can eliminate the error in height detection caused by the inclination of the road itself relative to the standard ground plane, which is conducive to improving the accuracy of lidar height measurement of road objects.

[0052] Of course, before executing the coordinate conversion in step S102, it is necessary to first obtain the road surface laser point cloud data of the target road section, and then determine the road surface plane based on the road surface laser point cloud data. In this way, the coordinate conversion model is determined based on the posture, i.e., the inclination, of the road surface plane in the LiDAR coordinate system and the position of the LiDAR coordinate system relative to the road surface plane. It should be noted that the inclination of the road surface plane in the LiDAR coordinate system is affected by both the installation posture of the LiDAR in the road scene and the inclination of the road surface itself relative to the standard ground plane.

[0053] Specifically, the road surface laser point cloud data of the target road section can be obtained by filtering the first laser point cloud data obtained in step S101, or can be separately collected and filtered using the same laser radar before executing steps S101 to S103. It should be noted that when the road surface returns a small number of laser point clouds, the road surface plane can be determined by combining the laser point clouds returned by reference objects on both sides of the road, such as guardrails.

[0054] Furthermore, based on the determined coordinate conversion model, the first laser point cloud data collected during the use of the laser radar can be converted from the laser radar coordinate system to the road surface coordinate system. Specifically, the first laser point cloud data can be input into the pre-configured coordinate conversion model to obtain the second laser point cloud data in the road surface coordinate system, that is, the coordinate system calibration of the laser point cloud data. For example, the x-axis direction of the road surface coordinate system can be the width of the road surface, the y-axis direction can be the direction of travel of the target road section, and the positive z-axis direction can be the direction perpendicular to the road surface plane and upward.

[0055] In an optional embodiment, the coordinate transformation model includes a coordinate rotation matrix, which is used to transform the pose of the coordinate system of the point cloud coordinates to be consistent with the road coordinate system. The coordinate system pose transformation of the point cloud coordinates can be achieved by rotating the point cloud coordinates about the coordinate axes of the lidar coordinate system, using a right-handed coordinate system with the counterclockwise direction around each axis as the positive direction. It can be understood that each dimension of rotation can be represented by the product of a vector and a rotation matrix. If rotation about three coordinate axes is required, it is represented by the product of three rotation matrices.

[0056] Specifically, the coordinate rotation matrix may include one or more combinations of the following three rotation matrices, which may be determined based on the needs of the actual scenario. When multiple rotation matrices are included, the multiple rotation matrices included may be multiplied to obtain the coordinate rotation matrix.

[0057] The first type is to rotate the laser point cloud coordinates around the X-axis of the laser radar coordinate system. For example, you can first obtain the angle between the Y-axis of the laser radar coordinate system and the road surface as the first rotation angle, and then determine the first rotation matrix based on the first rotation angle. For example, you can input the first rotation angle into the following formula (1) to obtain the corresponding first rotation matrix. In formula (1), R X (α) represents the first rotation matrix, and α represents the first rotation angle.

[0058]

[0059] For example, if the LiDAR is installed tilted downward directly in front of the radar, the road surface plane presented in the collected road laser point cloud data is tilted upward in the Y-axis direction, that is, there is an angle between the road surface plane and the Y-axis of the LiDAR coordinate system. In this case, it is necessary to rotate the point cloud data around the X-axis of the LiDAR coordinate system to rotate the road surface plane presented in the road point cloud data to be parallel to the Y-axis.

[0060] The second type is to rotate the laser point cloud coordinates around the Y axis of the laser radar coordinate system. For example, you can first obtain the angle between the X axis of the laser radar coordinate system and the road surface as the second rotation angle, and then determine the second rotation matrix based on the second rotation angle. For example, you can input the second rotation angle into the following formula (2) to obtain the corresponding second rotation matrix. In formula (2), R Y (β) represents the second rotation matrix, and β represents the second rotation angle.

[0061]

[0062] For example, if the road surface is tilted widthwise relative to the standard ground plane, there may be an angle between the road surface plane and the X-axis of the LiDAR coordinate system. In this case, the point cloud data needs to be rotated around the Y-axis of the LiDAR coordinate system to rotate the road surface plane represented by the road point cloud data to be roughly parallel to the X-axis.

[0063] The third type is a third rotation matrix that rotates the laser point cloud coordinates around the Z axis of the laser radar coordinate system. For example, you can first obtain the angle between the X axis of the laser radar coordinate system and the reference vertical plane of the road surface plane as the third rotation angle, and then determine the third rotation matrix based on the third rotation angle. Among them, the reference vertical plane is the yoz plane in the road surface coordinate system corresponding to the road surface plane. For example, the third rotation angle can be input into the following formula (3) to obtain the corresponding third rotation matrix. In formula (3), R Z (γ) represents the third rotation matrix, and γ represents the third rotation angle.

[0064]

[0065] In an optional implementation, the coordinate rotation matrix may be assumed to include the first rotation matrix, the second rotation matrix, and the third rotation matrix, that is, the coordinate rotation matrix M may be determined by the following formula (4).

[0066] M=R X (α)R Y (β)R Z (γ) (4)

[0067] It is understood that if the coordinate transformation of the actual road scene does not require rotation around one of the axes, the corresponding rotation angle obtained is zero. For example, assuming the third rotation angle obtained is zero, the elements on the main diagonal of the determined third rotation matrix are 1, and the remaining elements are 0. In this case, multiplying the point coordinates by the third rotation matrix will not change the coordinate values.

[0068] Of course, in other implementations, the coordinate rotation matrix can also be determined based on the installation posture of the laser radar and the road inclination in the actual road scene. For example, if a road scene only needs to rotate around the X axis and around the Y axis to achieve coordinate transformation, the coordinate rotation matrix is: R X (α)R Y When using it, there is no need to obtain the third rotation angle. After obtaining the first rotation angle and the second rotation angle, the coordinate rotation matrix can be determined.

[0069] In the coordinate transformation model, the coordinates of the first laser point cloud data are multiplied by the coordinate rotation matrix to achieve the posture transformation of the coordinate system, so that the directions of the three axes x, y, and z of the converted coordinate system are consistent with those of the road coordinate system.

[0070] Furthermore, in addition to the coordinate rotation matrix, the coordinate transformation model also includes a coordinate translation matrix. The coordinate translation matrix is ​​determined based on the position of the origin of the laser radar coordinate system relative to the road surface plane. In the coordinate transformation model, after completing the above-mentioned coordinate rotation, the rotated point cloud coordinates are translated by the coordinate translation matrix so that the origin of the rotated coordinate system is located on the road surface plane, and the point cloud coordinates converted to the road surface coordinate system can be obtained. For example, the coordinate transformation model can be shown as the following formula (5), where (x0, y0, z0) represents the point coordinates before conversion, (x1, y1, z1) represents the point coordinates after conversion, M represents the coordinate rotation matrix, and P represents the coordinate translation matrix. In actual application, the point cloud coordinates in the first laser radar data are input into formula (5) to obtain the second laser point cloud data.

[0071] (x1,y1,z1) T =M*(x0,y0,z0) T +P (5)

[0072] After the coordinate conversion is completed, it can be considered that the road surface point cloud data in the second laser point cloud data is located on the xoy plane of the road surface coordinate system. Further, step S103 can be executed to perform height detection.

[0073] Step S103: cluster and segment the second laser point cloud data to obtain N types of point cloud data, and obtain the height value of the corresponding target object based on each type of point cloud data with the road surface as the reference, where N is an integer greater than or equal to 1.

[0074] Considering that the second laser point cloud data contains point cloud data other than the target object within the field of view of the laser radar, in order to reduce the computational complexity of clustering and improve the accuracy of the clustering results, the detection interval can be determined in advance based on the field of view of the laser radar, the road width, the height of the target object, and the effective road section length in the actual application scenario, including the detection interval in the x-axis direction, the detection interval in the y-axis direction, and the detection interval in the z-axis direction. For example, when the target object is a vehicle traveling on the target road section, the above-mentioned detection area can be determined based on factors such as the lane area to be detected and the height range of the vehicle. In step S103, the point cloud data outside the detection interval in the second laser point cloud data is first eliminated, and then the second laser point cloud data is clustered and segmented to identify the target object.

[0075] In an optional embodiment, the second laser point cloud data can be clustered based on the x-axis distance and y-axis distance between different points to obtain N types of point cloud data, where the x-axis distance between two adjacent points is less than a first preset threshold, and the y-axis distance is less than a second preset threshold. It should be noted that, in this article, the adjacent point of a point refers to another point that is closest to the point.

[0076] The first preset threshold value is different from the second preset threshold value and can be set based on the needs of the actual application scenario and multiple experiments. For example, if the laser point cloud density in the x-axis direction of the second laser point cloud data is greater than the laser point cloud density in the y-axis direction, then the first preset threshold value is less than the second preset threshold value.

[0077] It should be noted that the angular resolution of the multi-line laser radar is different in the x-axis direction and the y-axis direction. At the same distance, the density of the point cloud in the x-axis direction and the density in the y-axis direction show a large gap, resulting in inconsistent distances between adjacent points on the x-axis and y-axis in the coordinate system. If the traditional clustering method based on Euclidean distance is adopted, that is, the straight-line distance between points is used as the clustering threshold, there will be a problem that the x-axis threshold is appropriate but the y-axis threshold is too small, or the y-axis threshold is appropriate but the x-axis threshold is too large, resulting in large errors in the clustering results. Therefore, this embodiment can effectively improve the accuracy of the clustering results by clustering point cloud data using different distance thresholds in the x-axis and y-axis directions.

[0078] Taking the target object as a vehicle traveling on the target road section as an example, the width of the vehicle is smaller than the lane width, and the length and height of different vehicles vary greatly. During the clustering segmentation process, using different distance thresholds in the x-axis and y-axis directions is conducive to more accurately segmenting the point clouds corresponding to various types of vehicles, thereby improving the accuracy of vehicle height detection results.

[0079] Specifically, there are many ways to perform clustering and segmentation based on distance. For example, you can traverse each point in the second laser point cloud data. If no class has been created when traversing to the current point, create a new class and add the current point to the new class point cloud. If a class has been created, traverse the created class, obtain the x-axis distance and y-axis distance between the current point and each point in the current class, and if there is at least one point in the current class whose x-axis distance to the current point is less than the first preset threshold, and the y-axis distance is less than the second preset threshold, then add the current point to the current class. If there is no point in the created class whose x-axis distance to the current point is less than the first preset threshold, and the y-axis distance is less than the second preset threshold, then create a new class and add the current point to the new class point cloud. And so on, until all points in the second laser point cloud data are traversed, N types of point cloud data can be obtained.

[0080] Each type of point cloud data corresponds to a target object. For example, the target object can be a vehicle traveling on the target road segment. Since the coordinate system calibration in step S102 has already positioned the road surface point cloud on the xoy plane of the road surface coordinate system, the height of the top of the corresponding target object from the road surface can be determined by comparing the z-axis coordinate values ​​of each point in the same type of point cloud data. For example, the maximum z-axis coordinate value in the same type of point cloud data can be used as the height of the corresponding target object.

[0081] In a second aspect, the embodiments of this specification also provide a method for detecting the height of road objects, which is used to detect the height of vehicles traveling on a target road section from a long distance. Figure 3 As shown, the method may include the following steps:

[0082] Step S201, obtaining first laser point cloud data of a target road section;

[0083] Step S202, converting the first laser point cloud data from the laser radar coordinate system to the ground coordinate system to obtain second laser point cloud data;

[0084] Step S203: performing cluster segmentation processing on the second laser point cloud data based on the x-axis distances and y-axis distances between different points to obtain N types of point cloud data, wherein in the same type of point cloud data, the x-axis distance between two adjacent points is less than a first preset threshold, and the y-axis distance is less than a second preset threshold, wherein the x-axis direction is the road width direction, the y-axis direction is the travel direction of the target road section, N is an integer greater than or equal to 1, and the first preset threshold is different from the second preset threshold;

[0085] Step S204: obtaining a vehicle height value traveling on the target road section based on the N types of point cloud data.

[0086] It should be noted that the specific implementation process and technical effects achieved by the above-mentioned steps S201 to S204 can be referred to the relevant description of the method embodiment provided in the first aspect above, and will not be repeated here. In specific implementation, the ground coordinate system in step S202 can be determined based on the road surface plane formed by the road surface laser point cloud data of the target road section, or it can also be determined based on a standard ground plane, which is not limited in this embodiment.

[0087] In the third aspect, based on the same inventive concept as the road object height detection method provided in the embodiment of the first aspect, the embodiment of this specification also provides a road object height detection device. Figure 4 As shown, the road surface object height detection device 40 includes:

[0088] The data acquisition module 401 is configured to acquire first laser point cloud data of a target road section, wherein a target object is carried on the road surface of the target road section;

[0089] A coordinate conversion module 402 is configured to convert the first laser point cloud data from a laser radar coordinate system to a road surface coordinate system to obtain second laser point cloud data, wherein the road surface coordinate system is determined based on a road surface plane formed by the road surface laser point cloud data of the target road section;

[0090] The height detection module 403 is used to cluster and segment the second laser point cloud data to obtain N types of point cloud data, and obtain the height value of the corresponding target object based on each type of point cloud data with the road surface plane as the reference, where N is an integer greater than or equal to 1.

[0091] In an optional embodiment, the above-mentioned height detection module 403 is used to: cluster the second laser point cloud data based on the x-axis distance and y-axis distance between different points to obtain N types of point cloud data, and in the same type of point cloud data, the x-axis distance between two adjacent points is less than a first preset threshold, and the y-axis distance is less than a second preset threshold, wherein the x-axis direction is the road width direction, and the y-axis direction is the traveling direction of the target road section, and the first preset threshold is different from the second preset threshold.

[0092] In an optional embodiment, the laser point cloud density in the x-axis direction in the second laser point cloud data is greater than the laser point cloud density in the y-axis direction, and the first preset threshold is less than the second preset threshold.

[0093] In an optional implementation, the coordinate conversion module 402 is used to:

[0094] The first laser point cloud data is input into a preconfigured coordinate transformation model to obtain second laser point cloud data in the road surface coordinate system, wherein the coordinate transformation model includes a coordinate rotation matrix, and the coordinate rotation matrix is ​​determined based on the inclination angle of the road surface plane in the lidar coordinate system.

[0095] In an optional embodiment, the coordinate rotation matrix includes: a first rotation matrix that rotates the laser point cloud coordinates around the X-axis of the laser radar coordinate system, and the first rotation matrix is ​​determined based on the angle between the Y-axis of the laser radar coordinate system and the road surface plane.

[0096] In an optional embodiment, the coordinate rotation matrix includes: a second rotation matrix that rotates the laser point cloud coordinates around the Y axis of the laser radar coordinate system, and the second rotation matrix is ​​determined based on the angle between the X axis of the laser radar coordinate system and the road surface plane.

[0097] In an optional embodiment, the coordinate rotation matrix includes: a third rotation matrix that rotates the laser point cloud coordinates around the Z axis of the laser radar coordinate system, and the third rotation matrix is ​​determined based on the angle between the X axis of the laser radar coordinate system and the reference vertical plane of the road surface plane, wherein the reference vertical plane is the yoz plane in the road surface coordinate system corresponding to the road surface plane, the x-axis direction of the road surface coordinate system is the road surface width direction, the y-axis direction is the traveling direction of the target road section, and the z-axis direction is the direction perpendicular to the road surface plane.

[0098] It should be noted that the road object height detection device 40 provided in the embodiment of this specification, wherein the specific manner in which each module performs operations has been described in detail in the method embodiment provided in the above-mentioned first aspect, and the specific implementation process can refer to the method embodiment provided in the above-mentioned first aspect, and will not be elaborated on here.

[0099] In the fourth aspect, based on the same inventive concept as the road object height detection method provided in the embodiment of the second aspect, the embodiment of this specification also provides a road object height detection device. Figure 5 As shown, the road surface object height detection device 50 includes:

[0100] An acquisition module 501 is used to acquire first laser point cloud data of a target road section;

[0101] A conversion module 502 is configured to convert the first laser point cloud data from a laser radar coordinate system to a ground coordinate system to obtain second laser point cloud data;

[0102] a cluster segmentation module 503 configured to perform cluster segmentation processing on the second laser point cloud data based on x-axis distances and y-axis distances between different points, to obtain N types of point cloud data, wherein in the same type of point cloud data, the x-axis distance between two adjacent points is less than a first preset threshold, and the y-axis distance is less than a second preset threshold, wherein the x-axis direction is the road width direction, the y-axis direction is the travel direction of the target road section, N is an integer greater than or equal to 1, and the first preset threshold is different from the second preset threshold;

[0103] The vehicle height determination module 504 is configured to obtain a vehicle height value traveling on the target road section based on the N types of point cloud data.

[0104] It should be noted that the road object height detection device 50 provided in the embodiment of this specification, wherein the specific manner in which each module performs operations has been described in detail in the method embodiment provided in the above-mentioned first aspect, and the specific implementation process can refer to the method embodiment provided in the above-mentioned first aspect, and will not be elaborated here.

[0105] In a fifth aspect, based on the same inventive concept as the road object height detection method provided in the above embodiment, the embodiment of this specification also provides an electronic device. Figure 6 As shown, the electronic device includes a memory 604, one or more processors 602, and a computer program stored in the memory 604 and executable on the processors 602. When the processors 602 execute the program, the steps of any of the embodiments of the road object height detection method provided in the first or second aspects above are implemented. For example, the electronic device can be an edge computing device, a personal computer, a tablet computer, a server, or other device with data processing capabilities.

[0106] Among them, Figure 6 In the embodiment of the present invention, a bus architecture (represented by bus 600) is shown. Bus 600 may include any number of interconnected buses and bridges, and bus 600 links together various circuits including one or more processors represented by processor 602 and memory represented by memory 604. Bus 600 may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. Bus interface 605 provides an interface between bus 600 and receiver 601 and transmitter 603. Receiver 601 and transmitter 603 may be the same component, namely a transceiver, which provides a unit for communicating with various other devices over a transmission medium. Processor 602 is responsible for managing bus 600 and general processing, while memory 604 may be used to store data used by processor 602 when performing operations.

[0107] It is understandable that Figure 6 The structure shown is for illustration only. The electronic device provided in the embodiments of this specification may also include Figure 6 More or fewer components than shown, or with Figure 6 Different configurations shown. Figure 6 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0108] In the sixth aspect, based on the same inventive concept as the road object height detection method provided in the aforementioned embodiment, the embodiment of this specification also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by the processor, it implements the steps of any embodiment of the road object height detection method provided in the first or second aspect above.

[0109] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0110] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that performs the functions specified in one or more boxes.

[0111] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0113] Although the preferred embodiments of this specification have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of this specification.

[0114] Obviously, those skilled in the art may make various changes and modifications to this specification without departing from the spirit and scope of this specification. Thus, if such changes and modifications fall within the scope of the claims of this specification and their equivalents, this specification is intended to include such changes and modifications.

Claims

1. A method for detecting the height of road objects, characterized in that: The method comprises: Acquire first laser point cloud data of a target road section, wherein a target object is carried on the road surface of the target road section, the first laser point cloud data including point cloud data of the target object carried on the road surface of the target road section within a laser radar field of view and point cloud data of the road surface not blocked by the target object, the laser radar being a multi-line laser radar, and the target object including a vehicle traveling on the target road section; Converting the first laser point cloud data from a laser radar coordinate system to a road surface coordinate system to obtain second laser point cloud data, wherein the road surface coordinate system is determined based on a road surface plane formed by the road surface laser point cloud data of the target road section; Performing clustering and segmentation processing on the second laser point cloud data to obtain N types of point cloud data, and obtaining a height value of a corresponding target object based on each type of point cloud data with the road surface plane as a reference, where N is an integer greater than or equal to 1; wherein, clustering and segmenting the second laser point cloud data to obtain N types of point cloud data includes: clustering the second laser point cloud data based on the x-axis distance and the y-axis distance between different points to obtain N types of point cloud data, and in the same type of point cloud data, the x-axis distance between two adjacent points is less than a first preset threshold, and the y-axis distance is less than a second preset threshold, wherein the x-axis direction is the road width direction, the y-axis direction is the traveling direction of the target road section, and the first preset threshold is different from the second preset threshold; when the laser point cloud density in the x-axis direction in the second laser point cloud data is greater than the laser point cloud density in the y-axis direction, the first preset threshold is less than the second preset threshold.

2. The method according to claim 1, characterized in that Converting the first laser point cloud data from the laser radar coordinate system to a road surface coordinate system to obtain second laser point cloud data includes: The first laser point cloud data is input into a preconfigured coordinate transformation model to obtain second laser point cloud data in the road surface coordinate system, wherein the coordinate transformation model includes a coordinate rotation matrix, and the coordinate rotation matrix is ​​determined based on the inclination angle of the road surface plane in the lidar coordinate system.

3. The method according to claim 2, characterized in that The coordinate rotation matrix includes one or more combinations of the following rotation matrices: A first rotation matrix that rotates the laser point cloud coordinates around the X-axis of the laser radar coordinate system, wherein the first rotation matrix is ​​determined based on the angle between the Y-axis of the laser radar coordinate system and the road surface plane; A second rotation matrix that rotates the laser point cloud coordinates around the Y axis of the laser radar coordinate system, wherein the second rotation matrix is ​​determined based on the angle between the X axis of the laser radar coordinate system and the road surface plane; A third rotation matrix that rotates the laser point cloud coordinates around the Z axis of the laser radar coordinate system, wherein the third rotation matrix is ​​determined based on the angle between the X axis of the laser radar coordinate system and the reference vertical plane of the road surface plane, wherein the reference vertical plane is the yoz plane in the road surface coordinate system corresponding to the road surface plane, the x-axis direction of the road surface coordinate system is the road surface width direction, the y-axis direction is the traveling direction of the target road section, and the z-axis direction is the direction perpendicular to the road surface plane.

4. A method for detecting the height of road objects, characterized in that: The method comprises: Acquire first laser point cloud data of a target road section, the first laser point cloud data including point cloud data of vehicles traveling on the target road section within a field of view of a laser radar and point cloud data of a road surface not blocked by the vehicles, wherein the laser radar is a multi-line laser radar; Converting the first laser point cloud data from a laser radar coordinate system to a ground coordinate system to obtain second laser point cloud data; Performing clustering and segmentation processing on the second laser point cloud data based on x-axis distances and y-axis distances between different points to obtain N types of point cloud data, wherein in the same type of point cloud data, the x-axis distance between two adjacent points is less than a first preset threshold, and the y-axis distance is less than a second preset threshold, wherein the x-axis direction is a road width direction, the y-axis direction is a travel direction of the target road section, N is an integer greater than or equal to 1, and the first preset threshold is different from the second preset threshold; and when, in the second laser point cloud data, the laser point cloud density in the x-axis direction is greater than the laser point cloud density in the y-axis direction, the first preset threshold is less than the second preset threshold; Based on the N types of point cloud data, a height value of a vehicle traveling on the target road section is obtained.

5. A road object height detection device, characterized in that: The device comprises: a data acquisition module, configured to acquire first laser point cloud data of a target road section, wherein a target object is carried on the road surface of the target road section, the first laser point cloud data including point cloud data of the target object carried on the road surface of the target road section within a field of view of a laser radar and point cloud data of the road surface not obscured by the target object, the laser radar being a multi-line laser radar, and the target object including a vehicle traveling on the target road section; a coordinate conversion module, configured to convert the first laser point cloud data from a laser radar coordinate system to a road surface coordinate system to obtain second laser point cloud data, wherein the road surface coordinate system is determined based on a road surface plane formed by the road surface laser point cloud data of the target road section; a height detection module, configured to perform clustering and segmentation processing on the second laser point cloud data to obtain N types of point cloud data, and obtain a height value of a corresponding target object based on each type of point cloud data with the road surface as a reference, where N is an integer greater than or equal to 1; In which, the height detection module is used to: cluster the second laser point cloud data based on the x-axis distance and y-axis distance between different points to obtain N types of point cloud data, and in the same type of point cloud data, the x-axis distance between two adjacent points is less than a first preset threshold, and the y-axis distance is less than a second preset threshold, wherein the x-axis direction is the road width direction, and the y-axis direction is the traveling direction of the target road section, and the first preset threshold is different from the second preset threshold; when the laser point cloud density in the x-axis direction in the second laser point cloud data is greater than the laser point cloud density in the y-axis direction, the first preset threshold is less than the second preset threshold.

6. A road object height detection device, characterized in that: The device comprises: an acquisition module, configured to acquire first laser point cloud data of a target road section, wherein the first laser point cloud data includes point cloud data of vehicles traveling on the target road section within a field of view of a laser radar and point cloud data of a road surface not blocked by the vehicles, wherein the laser radar is a multi-line laser radar; a conversion module, configured to convert the first laser point cloud data from a laser radar coordinate system to a ground coordinate system to obtain second laser point cloud data; a cluster segmentation module, configured to perform cluster segmentation processing on the second laser point cloud data based on x-axis distances and y-axis distances between different points, to obtain N types of point cloud data, wherein in the same type of point cloud data, the x-axis distance between two adjacent points is less than a first preset threshold, and the y-axis distance is less than a second preset threshold, wherein the x-axis direction is a road width direction, the y-axis direction is a travel direction of the target road section, N is an integer greater than or equal to 1, and the first preset threshold is different from the second preset threshold; and when the laser point cloud density in the x-axis direction is greater than the laser point cloud density in the y-axis direction in the second laser point cloud data, the first preset threshold is less than the second preset threshold; The vehicle height determination module is used to obtain the vehicle height value traveling on the target road section based on the N types of point cloud data.

7. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the steps of the method according to any one of claims 1 to 4 are implemented when the processor executes the program.

8. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.

Images