Vehicle restriction detection method and device, equipment and storage medium

Abstract

The invention discloses a vehicle limitation detection method and device, equipment and a storage medium. The method comprises the following steps: determining vehicle point cloud data of each image acquisition device; determining a lane point cloud width, a lane point cloud height and a lane center point cloud coordinate of a target driving vehicle under the current point cloud frame according to the vehicle point cloud data of each image acquisition device; and according to the lane center point cloud coordinate, if it is determined that the vehicle point cloud data under the current point cloud frame meets a preset point cloud receiving ending condition, ending point cloud data acquisition of the target driving vehicle, and when it is determined that the point cloud receiving ending condition is met, ending point cloud data acquisition of the target driving vehicle. The target driving vehicle determines the obtained lane point cloud width, lane point cloud height and lane center point cloud coordinates under at least one point cloud frame; and according to the lane point cloud width, the lane point cloud height and the lane center point cloud coordinate under each point cloud frame, determining a vehicle limitation detection result of the target driving vehicle. According to the embodiment of the invention, accurate detection of vehicle overrun is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle detection, and particularly to a vehicle limit detection method, device, equipment and storage medium. Background Art

[0002] In the case of an increasingly dense road network, the problem of overloading and over-limit transportation of freight vehicles has become one of the major factors endangering road traffic. Therefore, how to quickly judge vehicle over-limit and thus manage vehicle over-limit has become a realistic problem that needs to be solved urgently in the development of intelligent transportation.

[0003] In the process of existing vehicle over-limit detection, edge devices such as vehicle sensing and recognition are usually used to monitor and collect data related to vehicle overloading and over-limit on the road, and detect and judge vehicle over-limit based on the data related to overloading and over-limit; however, the detection accuracy of existing vehicle over-limit detection is relatively low, and there is a high possibility of misjudgment. Summary of the Invention

[0004] The present invention provides a vehicle limit detection method, device, equipment and storage medium to improve the detection accuracy of vehicle over-limit.

[0005] According to one aspect of the present invention, a vehicle limit detection method is provided, and the method includes:

[0006] Obtain vehicle point cloud data of each of the image acquisition devices in the current point cloud frame by performing frame-by-frame point cloud acquisition on a target moving vehicle in the same coordinate system after device calibration by at least one image acquisition device;

[0007] Determine the lane point cloud width, lane point cloud height and lane center point cloud coordinates of the target moving vehicle in the current point cloud frame according to the vehicle point cloud data of each of the image acquisition devices;

[0008] Determine whether the vehicle point cloud data in the current point cloud frame meets a preset point cloud reception end condition according to the lane center point cloud coordinates;

[0009] If so, terminate the acquisition of the point cloud data of the target moving vehicle, and determine the lane point cloud width, lane point cloud height and lane center point cloud coordinates determined by the target moving vehicle in at least one point cloud frame when the point cloud reception end condition is met;

[0010] Determine the vehicle limit detection result of the target moving vehicle according to the lane point cloud width, lane point cloud height and lane center point cloud coordinates in each of the point cloud frames.

[0011] According to another aspect of the present invention, a vehicle limit detection device is provided, and the device includes:

[0012] A vehicle point cloud data acquisition module, configured to acquire vehicle point cloud data of each of the image acquisition devices in the current point cloud frame by performing frame-by-frame point cloud acquisition on a target moving vehicle in the same coordinate system after device calibration by at least one image acquisition device;

[0013] A central point cloud coordinate determination module, configured to determine the lane point cloud width, lane point cloud height, and lane central point cloud coordinate of the target moving vehicle in the current point cloud frame according to the vehicle point cloud data of each of the image acquisition devices;

[0014] An end condition determination module, configured to determine whether the vehicle point cloud data in the current point cloud frame meets a preset point cloud reception end condition according to the lane central point cloud coordinate;

[0015] A lane information determination module, configured to terminate the acquisition of the vehicle point cloud data of the target moving vehicle if the vehicle point cloud data in the current point cloud frame meets the preset point cloud reception end condition, and determine the lane point cloud width, lane point cloud height, and lane central point cloud coordinate determined for the target moving vehicle in at least one point cloud frame when the point cloud reception end condition is met;

[0016] A detection result determination module, configured to determine a vehicle restriction detection result for the target moving vehicle according to the lane point cloud width, lane point cloud height, and lane central point cloud coordinate in each of the point cloud frames.

[0017] According to another aspect of the present invention, there is provided an electronic device, including:

[0018] At least one processor; and

[0019] A memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the vehicle restriction detection method according to any embodiment of the present invention.

[0021] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the vehicle restriction detection method according to any embodiment of the present invention when executed.

[0022] In an embodiment of the present invention, based on the vehicle point cloud data of each image acquisition device, the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle in the current point cloud frame are determined. When it is determined that the vehicle point cloud data in the current point cloud frame meets the preset point cloud reception end condition according to the lane center point cloud coordinates, the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle determined in at least one point cloud frame are determined. According to the lane point cloud width, lane point cloud height, and lane center point cloud coordinates in each point cloud frame, the vehicle restriction detection result for the target moving vehicle is determined. The above technical solution determines whether the vehicle point cloud data meets the preset point cloud reception end condition through the lane center point cloud coordinates, realizes the accurate acquisition of the point cloud data of the target moving vehicle, and determines the vehicle restriction detection result for the target moving vehicle according to the lane point cloud width, lane point cloud height, and lane center point cloud coordinates in each point cloud frame, thereby realizing the accurate detection of the height and width limits of the target moving vehicle.

[0023] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1A is a flowchart of a vehicle restriction detection method provided in Embodiment 1 of the present invention;

[0026] Figure 1B is a schematic diagram of the relative deployment position of an image acquisition device with respect to a road provided in Embodiment 1 of the present invention;

[0027] Figure 2 is a flowchart of a vehicle restriction detection method provided in Embodiment 2 of the present invention;

[0028] Figure 3 is a flowchart of a vehicle restriction detection method provided in Embodiment 3 of the present invention;

[0029] Figure 4 is a schematic structural diagram of a vehicle restriction detection device provided in Embodiment 4 of the present invention;

[0030] Figure 5It is a schematic structural diagram of an electronic device for implementing the vehicle limit detection method according to an embodiment of the present invention. Detailed implementation manners

[0031] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data used may be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0033] Embodiment 1

[0034] Figure 1A It is a flowchart of a vehicle limit detection method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of detecting the height and width limits of a moving vehicle. This method can be executed by a vehicle limit detection device, which can be implemented in the form of hardware and / or software, and the vehicle limit detection device can be configured in an electronic device. As Figure 1A shown, the method includes:

[0035] S110. Obtain the vehicle point cloud data of each image acquisition device in the current point cloud frame by performing frame-by-frame point cloud acquisition on the target moving vehicle in the same coordinate system after the device calibration of at least one image acquisition device.

[0036] Among them, the image acquisition device can be an acquisition device used to detect vehicles driving on the road. For example, the image acquisition device can be a single-line lidar sensor, which has high resolution and strong anti-interference ability. The image acquisition device can be deployed above the road surface vertically to perform high-precision model scanning on the driving vehicle and obtain the point cloud information of the vehicle. Among them, the target driving vehicle can be a driving vehicle that is driving on the lane line and appears within the acquisition range of the image acquisition device and for which vehicle limit detection is to be performed.

[0037] Among them, the number of image acquisition devices deployed above the road surface vertically can be at least one, and specifically, single-device or multi-device deployment can be performed according to the road width and the number of roads. Generally, for the sake of comprehensiveness of the vehicle point cloud data of the road driving vehicles obtained, the number of deployed image acquisition devices is multiple. Exemplarily, a schematic diagram of the relative position of the image acquisition device with respect to the road is as Figure 1B shown. Taking two roads with three road lines as an example, corresponding image acquisition devices are deployed above each road line vertically, and the acquisition ranges of the respective image acquisition devices can be the same or different.

[0038] It should be noted that if there are multiple image acquisition devices, device calibration needs to be performed on each image acquisition device to ensure that each image acquisition device belongs to the same coordinate system, and obtaining point cloud data in the same coordinate system facilitates subsequent point cloud fusion of the point cloud data obtained by each image acquisition device. It can be understood that the acquisition method of the image acquisition device for the driving vehicle in the lane is frame-by-frame acquisition. Specifically, based on the acquisition frequency, when the image acquisition device detects that there is a driving vehicle on the lane within the acquisition range, it performs frame-by-frame acquisition on the driving vehicle until the driving vehicle exits the lane within the acquisition range, and obtains at least one frame of point cloud data corresponding to the acquired driving vehicle.

[0039] Exemplarily, device calibration is performed on each image acquisition device in advance so that the point cloud data acquired by each image acquisition device belongs to the same coordinate system. When each image acquisition device detects that there is a target driving vehicle on the lane within the acquisition range, it performs frame-by-frame point cloud acquisition on the target driving vehicle, and obtains at least one frame of vehicle point cloud data of the target driving vehicle acquired by each image acquisition device. It can be understood that since the point cloud data is a frame-by-frame acquisition process, therefore, for each frame of point cloud data acquired, the vehicle point cloud data of each image acquisition device in the current point cloud frame can be obtained.

[0040] S120. According to the vehicle point cloud data of each image acquisition device, determine the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target driving vehicle in the current point cloud frame.

[0041] Exemplarily, for the vehicle point cloud data of each image acquisition device in the current point cloud frame, the point cloud data of each vehicle is fused, and based on the fused vehicle point cloud data, the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle in the current point cloud frame are determined. The lane point cloud width, lane point cloud height, and lane center point cloud coordinates are obtained by performing contour extraction on the fused vehicle point cloud data. It can be understood that since the process of acquiring point cloud data of the lane moving vehicle by the image acquisition device is the extraction of point cloud data of the moving vehicles on each lane, therefore, the lane point cloud width extracted by performing contour extraction on the point cloud data can represent the vehicle width; the lane point cloud height extracted by performing contour extraction on the point cloud data can represent the vehicle height; the lane center point cloud coordinates can be the coordinates of the center point cloud obtained after point cloud data fusion, which can represent the vehicle center position coordinates.

[0042] It should be noted that since there may be vehicle point cloud data on at least one lane within the acquisition range of the image acquisition device, there may be a situation where there are vehicle point cloud data of multiple vehicles in the acquired vehicle point cloud data. For example, the vehicle point cloud data acquired by any image acquisition device may include the complete vehicle point cloud data of moving vehicle A and partial vehicle point cloud data of moving vehicle B. Therefore, in order to distinguish the vehicle point cloud data of different vehicles, a clustering method can be used to classify the vehicle point cloud data of different vehicles.

[0043] In an alternative embodiment, determining the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle in the current point cloud frame based on the vehicle point cloud data of each image acquisition device includes: obtaining the fused point cloud data in the current point cloud frame based on the vehicle point cloud data of each image acquisition device; performing point cloud clustering processing on the fused point cloud data in the current point cloud frame to obtain the target point cloud class information of the target moving vehicle; and determining the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle in the current point cloud frame based on the point cloud data in the target point cloud class information.

[0044] Exemplarily, the vehicle point cloud data of each image acquisition device in the current point cloud frame is fused to obtain the fused point cloud data in the current point cloud frame. Optionally, only the point cloud data within the ROI (Region Of Interest) area of the lane line can be retained, and the other point cloud data outside the ROI area is removed. Optionally, the point cloud data with a Z-axis height less than a preset height threshold within the ROI area can also be filtered to obtain the filtered fused point cloud data. Herein, the preset height threshold can be preset by those skilled in the relevant art. For example, the preset height threshold can be 0.2 cm.

[0045] Exemplarily, based on a preset density clustering algorithm, clustering processing can be performed on the fused point cloud data for point cloud filtering to obtain point cloud class information under at least one point cloud class. Different point cloud classes correspond to different driving vehicles, and each point cloud class information includes the clustered vehicle point cloud data of the corresponding driving vehicle.

[0046] Among them, the density clustering algorithm can be DBSCAN (Density-Based Spatial Clustering of Applications with Noise, a representative density-based clustering algorithm). It should be noted that to further ensure the accuracy of the clustering result of the fused point cloud data, during the process of clustering using the clustering algorithm, the lane line scenario can be fused to improve the DBSCAN algorithm model. Specifically, since this scenario clusters the vehicle point cloud data of the lane line, the point cloud data is concentrated in the quadrilateral area range. The DBSCAN algorithm clusters the data by comparing data based on a three-dimensional spherical structure container. Then, the three-dimensional spherical structure in the DBSCAN algorithm can be improved to a rectangular structure, and based on actual requirements, the side lengths of the rectangular structure can be set within a reasonable length range. For example, the side length of the rectangular structure in the X direction can be set to 0.8 m, and the side length in the Z direction can be set to 1.2 m. Among them, the X direction is the direction perpendicular to the lane line on the plane, and the Z direction is the direction perpendicular to the lane line plane.

[0047] Exemplarily, according to the point cloud data in the target point cloud class information, the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target driving vehicle in the current point cloud frame can be determined. Specifically, contour extraction can be performed on the point cloud data of the target point cloud class information, and based on the contour extraction result, the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target driving vehicle in the current point cloud frame can be obtained. Among them, the lane center point cloud coordinates are the coordinates of the center point cloud in the point cloud data of the target point cloud class information. The lane point cloud width is used to represent the vehicle width of the target driving vehicle on the lane, and the lane point cloud height is used to represent the vehicle width of the target driving vehicle on the lane.

[0048] It can be understood that if at least two point cloud classes are obtained by clustering, the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the driving vehicles corresponding to each point cloud class in the current point cloud frame can be determined respectively.

[0049] In this alternative embodiment, by integrating the actual lane road scenario, the clustering method is optimized and improved, and based on the improved clustering algorithm, point cloud clustering processing is performed on the fused point cloud data in the current point cloud frame to obtain the target point cloud class information of the target driving vehicle, achieving accurate determination of the target point cloud class information of the target driving vehicle, thereby improving the determination accuracy of the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target driving vehicle in the current point cloud frame.

[0050] S130. Determine whether the vehicle point cloud data in the current point cloud frame meets a preset point cloud reception end condition according to the lane center point cloud coordinates.

[0051] Exemplarily, according to the lane center point cloud coordinates, it can be determined whether the current lane line to which the target driving vehicle belongs in the current point cloud frame and the historical lane line to which the target driving vehicle belonged in the previous point cloud frame are the same lane line; if so, it is determined that the vehicle point cloud data in the current point cloud frame does not meet the preset point cloud reception end condition; if not, it is determined that the vehicle point cloud data in the current point cloud frame meets the preset point cloud reception end condition.

[0052] Optionally, it can also be determined whether the point cloud reception end condition is met according to the number of frames of the current point cloud frame. Exemplarily, if the number of frames of the current point cloud frame reaches a preset frame number threshold, it is determined that the point cloud reception end condition is met, and then the image acquisition device is controlled not to perform vehicle point cloud acquisition on the target driving vehicle anymore; if the number of frames of the current point cloud frame does not reach the preset frame number threshold, it is determined that the point cloud reception end condition is not met, and then the image acquisition device is controlled to continue performing the next frame of vehicle point cloud acquisition on the target driving vehicle.

[0053] S140. If so, terminate the acquisition of the point cloud data of the target driving vehicle, and determine the lane point cloud width, lane point cloud height, and lane center point cloud coordinates determined for the target driving vehicle in at least one point cloud frame when the point cloud reception end condition is met.

[0054] Exemplarily, when it is determined that the target driving vehicle meets the preset point cloud reception end condition, the acquisition of the point cloud data of the target driving vehicle is terminated, and the lane point cloud width, lane point cloud height, and lane center point cloud coordinates determined for the target driving vehicle in each point cloud frame when the point cloud reception end condition is met are determined. For example, if the current point cloud frame is the 15th frame, that is, when it is determined that the target driving vehicle meets the point cloud reception end condition at the 15th frame, the lane point cloud width, lane point cloud height, and lane center point cloud coordinates determined for the target driving vehicle in the previous 14 frames are obtained, so as to obtain the lane point cloud width, lane point cloud height, and lane center point cloud coordinates determined for the target driving vehicle in each of the 15 frames.

[0055] S150. Determine the vehicle limit detection result for the target moving vehicle according to the lane point cloud width, lane point cloud height, and lane center point cloud coordinates in each point cloud frame.

[0056] Exemplarily, the target lane line to which the target moving vehicle belongs can be determined according to the lane center point cloud coordinates; according to the lane point cloud width and lane point cloud height in each point cloud frame, based on the lane line height and width limits of the target lane line, the vehicle limit detection result for the target moving vehicle can be determined.

[0057] Specifically, the lane point cloud width in each point cloud frame can be respectively compared with the lane line width threshold of the target lane line to obtain the vehicle width limit result of the target moving vehicle in each point cloud frame. For example, if the lane point cloud width in a preset number of point cloud frames is not greater than the lane line width threshold, it can be determined that the vehicle width detection of the target moving vehicle passes. Among them, the preset number of point cloud frames can be preset by those skilled in the art according to the number of point cloud frames generated when the target moving vehicle meets the point cloud reception end condition. For example, if the number of point cloud frames corresponding to the target moving vehicle is 20 frames, the preset number of point cloud frames can be set to 16 frames, that is, 80% of the number of point cloud frames corresponding to the target moving vehicle. The method for detecting the limit of the lane line height of the target moving vehicle is the same, and this embodiment will not elaborate on this.

[0058] Exemplarily, if the detections of the vehicle height limit and vehicle width limit for the target driving lane line both pass, it can be considered that the vehicle limit detection result for the target moving vehicle passes; if any one of the detections of the vehicle height limit and vehicle width limit for the target driving lane line fails, it can be considered that the vehicle limit detection result for the target moving vehicle fails.

[0059] In the embodiment of the present invention, according to the vehicle point cloud data of each image acquisition device, the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle in the current point cloud frame are determined, and according to the lane center point cloud coordinates, when it is determined that the vehicle point cloud data in the current point cloud frame meets the preset point cloud reception end condition, the lane point cloud width, lane point cloud height, and lane center point cloud coordinates determined for the target moving vehicle in at least one point cloud frame are determined. According to the lane point cloud width, lane point cloud height, and lane center point cloud coordinates in each point cloud frame, the vehicle limit detection result for the target moving vehicle is determined. The above technical solution judges whether the vehicle point cloud data meets the preset point cloud reception end condition through the lane center point cloud coordinates, realizes the accurate acquisition of the point cloud data of the target moving vehicle, and determines the vehicle limit detection result for the target moving vehicle according to the lane point cloud width, lane point cloud height, and lane center point cloud coordinates in each point cloud frame, realizing the accurate detection of the height and width limits of the target moving vehicle.

[0060] It should be noted that, to ensure that the point cloud data collected by each image acquisition device belongs to the same coordinate system, facilitating the data fusion of the vehicle point cloud data of each image acquisition device, each image acquisition device can be pre-calibrated.

[0061] In an alternative embodiment, the ground point cloud data scanned by each image acquisition device in a preset coordinate system is obtained; the projected point cloud data of the ground point cloud data of each image acquisition device on a preset plane is determined; and each image acquisition device is calibrated according to the projected point cloud data of each image acquisition device, so that the point cloud data scanned by each image acquisition device is located in the same coordinate system.

[0062] Among them, the preset coordinate system can be preset by those skilled in the relevant art. For example, the positive front axis of the preset coordinate system is the positive Y-axis, the right axis (the axis perpendicular to the lane line on the lane line plane) is the positive X-axis, and the positive upper axis (the axis perpendicular to the lane line plane) is the positive Z-axis. The preset plane can be preset by those skilled in the relevant art according to the acquisition range of the image acquisition device. For example, for a single-line lidar device, its corresponding preset plane is the XZ plane.

[0063] Among them, the ground point cloud data is the point cloud data collected by the image acquisition device in the preset coordinate system; the projected point cloud data is the point cloud data after the ground point cloud data is projected onto the preset plane. Optionally, during the process of determining the projected point cloud data, the invalid point cloud outside the road can be filtered to achieve the purpose of removing noise interference.

[0064] Exemplarily, the calibration of each image acquisition device can be achieved by fitting the point cloud data of the projected point cloud data of each image acquisition device.

[0065] It should be noted that, to further improve the calibration accuracy of the calibration between each image acquisition device, the calibration of the device can also be performed by combining the rotation matrix and displacement matrix of the image acquisition device during the point cloud data fitting process.

[0066] In an alternative embodiment, calibrating each image acquisition device according to the projected point cloud data of each image acquisition device includes: respectively performing point cloud fitting on each projected point cloud data to obtain the road section straight line equations corresponding to each image acquisition device; determining the rotation matrix and displacement matrix corresponding to each image acquisition device according to the road section straight line equations; and calibrating each image acquisition device according to the rotation matrix and displacement matrix corresponding to each image acquisition device.

[0067] Exemplarily, the least squares fitting method can be adopted to perform point cloud fitting on each projection point cloud data respectively, so as to obtain the road section straight line equations corresponding to each image acquisition device. Among them, the equation expression form of the road section straight line equation obtained by least squares fitting can be as follows:

[0068] Y = KX + B;

[0069] Among them, K and B are constant terms, and (X, Y) are the coordinates of the projection point cloud.

[0070] Exemplarily, according to the road section straight line equations, the rotation matrix and displacement matrix corresponding to each image acquisition device are determined respectively. Among them, the rotation matrix M can be constructed by K and the displacement B in the Z direction. Specifically, the determination method of the rotation matrix M can be as follows:

[0071]

[0072] Among them, M is the rotation matrix, Roll is the angle between the ground and the X-axis direction. Among them, the determination method of Roll is as follows:

[0073]

[0074] Exemplarily, the determination method of the displacement matrix T can be as follows:

[0075]

[0076] Exemplarily, according to the rotation matrix and displacement matrix corresponding to each image acquisition device respectively, the device calibration of each image acquisition device is performed. Specifically, the point cloud where the ground coincides with the X-axis can be obtained by multiplying the rotation matrix M and the displacement matrix T, so that the point cloud data between each image acquisition device can completely coincide.

[0077] The technical solution of this alternative embodiment realizes the device calibration of each image acquisition device by performing point cloud fitting on each projection point cloud data respectively to obtain the road section straight line equations corresponding to each image acquisition device, determining the rotation matrix and displacement matrix corresponding to each image acquisition device according to the road section straight line equations, and performing device calibration on each image acquisition device according to the rotation matrix and displacement matrix corresponding to each image acquisition device; during the calibration process, the fitting relationship of each image acquisition device is fully considered, and the rotation matrix and displacement matrix of the image acquisition device are combined, which improves the calibration accuracy of the device calibration of each image acquisition device.

[0078] Embodiment 2

[0079] Figure 2The flowchart of a vehicle limit detection method provided in the second embodiment of the present invention. This embodiment is optimized and improved based on the above technical solutions.

[0080] Further, the step of "determining whether the vehicle point cloud data in the current point cloud frame meets the preset point cloud reception end condition according to the lane center point cloud coordinates" is refined to "determining the target lane line corresponding to the target driving vehicle in the current point cloud frame based on the preset lane line width range threshold according to the lane center point cloud coordinates; if the current point cloud frame is not the first point cloud frame, determining the historical lane line of the target driving vehicle in the historical point cloud frame; the historical point cloud frame is adjacent to the current point cloud frame and is before the current point cloud frame; determining whether the vehicle point cloud data in the current point cloud frame meets the preset point cloud data reception end condition according to the target lane line and the historical lane line." to improve the judgment method for the point cloud reception end condition.

[0081] Further, the step of "determining the vehicle limit detection result for the target driving vehicle according to the lane point cloud width, lane point cloud height, and lane center point cloud coordinates in each point cloud frame" is refined to "determining the target lane line corresponding to the target driving vehicle in the current point cloud frame based on the preset lane line width range threshold according to the lane center point cloud coordinates; determining whether the target driving vehicle exceeds the width limit based on the width range threshold of the target lane line according to the lane point cloud width, and obtaining the width limit detection result; and determining whether the target driving vehicle exceeds the height limit based on the height range threshold of the target lane line according to the lane point cloud height, and obtaining the height limit detection result; generating a vehicle limit detection result including the width limit detection result and the height limit detection result." to improve the determination method for the vehicle limit detection result. It should be noted that for the parts not detailed in the embodiments of the present invention, reference can be made to the descriptions of other embodiments.

[0082] As Figure 2 shown, the method includes the following specific steps:

[0083] S210. Obtain the vehicle point cloud data of each of the image acquisition devices in the current point cloud frame by performing frame-by-frame point cloud acquisition on the target driving vehicle in the same coordinate system after device calibration of at least one image acquisition device.

[0084] S220. Determine the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target driving vehicle in the current point cloud frame according to the vehicle point cloud data of each image acquisition device.

[0085] S230. Determine the target lane line corresponding to the target driving vehicle in the current point cloud frame based on the preset lane line width range threshold according to the lane center point cloud coordinates.

[0086] Among them, the lane line width range thresholds corresponding to different lanes are different. For example, the lane line width range threshold of lane line A is (CarRoadweidth0, CarRoadweidth1], and the lane line width range threshold of lane line B is (CarRoadweidth1, CarRoadweidth2].

[0087] Exemplarily, based on the lane line center point cloud coordinates and the lane line width range thresholds corresponding to different lanes respectively, the target lane line width range threshold into which the lane center point cloud coordinates fall can be determined; the target lane line corresponding to the target lane line width range threshold is used as the target lane line corresponding to the target driving vehicle in the current point cloud frame.

[0088] S240. If the current point cloud frame is a non-first frame point cloud frame, determine the historical lane line of the target driving vehicle in the historical point cloud frame; the historical point cloud frame is adjacent to the current point cloud frame and is before the current point cloud frame.

[0089] Exemplarily, if the current point cloud frame is a non-first frame point cloud frame, determine the historical lane line of the target driving vehicle in the historical point cloud frame. Among them, the historical point cloud frame is a frame adjacent to the current point cloud frame and before the current point cloud frame. For example, if the current point cloud frame is the 13th frame, the historical point cloud frame corresponding to the current point cloud frame is the 12th frame. It should be noted that if the current point cloud frame is the first frame point cloud frame, there is no historical point cloud frame, and there is no need to determine the historical lane line of the target driving vehicle in the historical point cloud frame.

[0090] S250. According to the target lane line and the historical lane line, determine whether the vehicle point cloud data in the current point cloud frame meets the preset point cloud data reception end condition.

[0091] Exemplarily, if the target lane line and the historical lane line are the same, determine that the vehicle point cloud data in the current point cloud frame does not meet the preset point cloud data reception end condition; if the target lane line and the historical lane line are different, determine that the vehicle point cloud data in the current point cloud frame meets the preset point cloud data reception end condition.

[0092] S260. If so, terminate the acquisition of the point cloud data of the target driving vehicle, and determine the lane point cloud width, lane point cloud height, and lane center point cloud coordinates determined for the target driving vehicle in at least one point cloud frame when the point cloud reception end condition is met.

[0093] S270. According to the lane point cloud width, based on the width range threshold of the target lane line, determine whether the target driving vehicle is over-width, and obtain the over-width detection result.

[0094] Exemplarily, based on the lane point cloud widths obtained from each point cloud frame, the average width is determined, and it is determined whether the average width is within the width range threshold of the target lane line. If so, it is determined that the width of the target driving vehicle is over-limit; if not, it is determined that the width of the target driving vehicle is not over-limit. The width range threshold of the target lane line can be preset by those skilled in the art according to actual needs.

[0095] S280. Based on the height range threshold of the target lane line according to the lane point cloud height, determine whether the target driving vehicle is over-height, and obtain the over-height detection result.

[0096] Exemplarily, based on the lane point cloud heights obtained from each point cloud frame, the average height is determined, and it is determined whether the average height is within the height range threshold of the target lane line. If so, it is determined that the target driving vehicle is over-height; if not, it is determined that the target driving vehicle is not over-height. The height range threshold of the target lane line can be preset by those skilled in the art according to actual needs.

[0097] S290. Generate a vehicle restriction detection result including the over-width detection result and the over-height detection result.

[0098] Exemplarily, the over-width detection result and the over-height detection result can be used as the vehicle restriction detection result. Specifically, if any of the over-width detection result or the over-height detection result fails, it is determined that the vehicle restriction detection result fails; if both the over-width detection result and the over-height detection result pass, it is determined that the vehicle restriction detection result passes.

[0099] The technical solution of this embodiment determines the target lane line corresponding to the target driving vehicle in the current point cloud frame based on the preset lane line width range threshold according to the lane center point cloud coordinates. If the current point cloud frame is not the first frame point cloud frame, the historical lane line of the target driving vehicle in the historical point cloud frame is determined. According to the target lane line and the historical lane line, it is determined whether the vehicle point cloud data in the current point cloud frame meets the preset point cloud data reception end condition, further realizing an accurate judgment of the point cloud data reception end condition; by determining whether the target driving vehicle is over-width based on the width range threshold of the target lane line according to the lane point cloud width, the over-width detection result is obtained, improving the determination accuracy of the over-width detection result of the target driving vehicle; and, by determining whether the target driving vehicle is over-height based on the height range threshold of the target lane line according to the lane point cloud height, the over-height detection result is obtained, improving the determination accuracy of the over-width detection result of the target driving vehicle, thereby improving the determination accuracy of the vehicle restriction detection result of the target driving vehicle.

[0100] It should be noted that, for further analysis of the target moving vehicle with height exceeding the limit and / or width exceeding the limit, after determining the vehicle limit detection result of the target moving vehicle, it is also possible to further obtain, analyze, and process the detailed relevant vehicle information or driving information of the target moving vehicle.

[0101] In an alternative embodiment, after determining the vehicle limit detection result of the target moving vehicle, it further includes: if the vehicle limit detection result is that the vehicle has an excessive height and / or an excessive width, determining the condition end time when the point cloud reception end condition is met; obtaining at least one candidate vehicle image associated with the target moving vehicle; the candidate vehicle image includes a shooting timestamp; according to the condition end time and the shooting timestamps of each candidate vehicle image, selecting the target vehicle image from each candidate vehicle image, and reporting the target vehicle image for image for detecting result analysis based on the target vehicle image and the vehicle limit detection result.

[0102] Exemplarily, if the vehicle limit detection result is that the vehicle has an excessive height and / or an excessive width, determining the condition end time when the point cloud reception end condition is met, and obtaining at least one candidate vehicle image associated with the target moving vehicle. Among them, the candidate vehicle image can be captured by a capture camera deployed in the vertical direction of the lane line. It should be noted that the capture camera can continuously capture the moving vehicles within the capture range area, and the vehicle images of the captured moving vehicles have shooting timestamp information. Specifically, according to the condition end time, at least one vehicle image captured within the condition end time range can be obtained, and candidate vehicle images related to the target moving vehicle can be selected from the at least one vehicle image.

[0103] Exemplarily, according to the shooting timestamps of each candidate vehicle image, selecting the candidate vehicle image whose shooting timestamp is close to the condition end time from each candidate vehicle image as the target vehicle image, and reporting the target vehicle image for image for detecting result analysis based on the target vehicle image and the vehicle limit detection result. Specifically, it can be reporting the target vehicle image to the vehicle command center, and this embodiment does not limit this.

[0104] In the technical solution of this alternative embodiment, when it is determined that the vehicle limit detection result is that the vehicle is over-height and / or over-width, the condition end time when the point cloud reception end condition is satisfied is obtained, and at least one candidate vehicle image associated with the target driving vehicle is obtained. According to the condition end time and the shooting timestamps of the candidate vehicle images, the target vehicle image is selected from the candidate vehicle images, and the target vehicle image is reported for image analysis based on the target vehicle image and the vehicle limit detection result, realizing the post-processing of the relevant vehicle information of the target driving vehicle with a failed vehicle limit detection result, providing basic theoretical data for the subsequent optimization of vehicle limit detection, and retaining data of the over-height and over-width target driving vehicles for the driver of the target driving vehicle to view.

[0105] Embodiment III

[0106] Figure 3 The flowchart of a vehicle limit detection method provided by Embodiment III of the present invention is shown. Based on the above embodiments, this embodiment provides a preferred example.

[0107] As Figure 3 shown, the method includes the following specific steps:

[0108] S301. Obtain the vehicle point cloud data of each image acquisition device in the current point cloud frame by performing frame-by-frame point cloud acquisition on the target driving vehicle in the same coordinate system after device calibration of at least one image acquisition device.

[0109] Among them, the device calibration method between at least one image acquisition device is as follows:

[0110] Obtain the ground point cloud data scanned by each image acquisition device in the preset coordinate system; determine the projected point cloud data of the ground point cloud data of each image acquisition device on the preset plane; perform point cloud fitting on each projected point cloud data respectively to obtain the road section straight line equations corresponding to each image acquisition device; determine the rotation matrix and displacement matrix corresponding to each image acquisition device according to the road section straight line equations; perform device calibration on each image acquisition device according to the rotation matrix and displacement matrix corresponding to each image acquisition device respectively, so that the point cloud data scanned by each image acquisition device is located in the same coordinate system.

[0111] S302. Obtain the fused point cloud data in the current point cloud frame according to the vehicle point cloud data of each image acquisition device.

[0112] S303. Perform point cloud clustering processing on the fused point cloud data in the current point cloud frame to obtain the target point cloud class information of the target driving vehicle.

[0113] S304. Determine the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle in the current point cloud frame based on the point cloud data in the target point cloud class information.

[0114] S305. Determine the target lane line corresponding to the target moving vehicle in the current point cloud frame based on the lane center point cloud coordinates and the preset lane line width range threshold.

[0115] S306. If the current point cloud frame is not the first point cloud frame, determine the historical lane line of the target moving vehicle in the historical point cloud frame; the historical point cloud frame is adjacent to the current point cloud frame and is before the current point cloud frame.

[0116] S307. Determine whether the vehicle point cloud data in the current point cloud frame meets the preset point cloud data reception end condition based on the target lane line and the historical lane line.

[0117] S308. If so, terminate the acquisition of the point cloud data of the target moving vehicle, and determine the lane point cloud width, lane point cloud height, and lane center point cloud coordinates determined for the target moving vehicle in at least one point cloud frame when the point cloud reception end condition is met.

[0118] S309. Determine whether the target moving vehicle is over-width based on the lane point cloud width and the width range threshold of the target lane line, and obtain the over-width detection result.

[0119] S310. Determine whether the target moving vehicle is over-height based on the lane point cloud height and the height range threshold of the target lane line, and obtain the over-height detection result.

[0120] S311. Generate a vehicle restriction detection result including the over-width detection result and the over-height detection result.

[0121] Exemplarily, after determining the vehicle restriction detection result for the target moving vehicle, it further includes: if the vehicle restriction detection result is that the vehicle is over-height and / or over-width, determine the end time of the condition when the point cloud reception end condition is met; obtain at least one candidate vehicle image associated with the target moving vehicle; the candidate vehicle image includes a shooting timestamp; according to the end time of the condition and the shooting timestamps of each candidate vehicle image, select the target vehicle image from each candidate vehicle image, and report the target vehicle image for detecting result analysis based on the target vehicle image and the vehicle restriction detection result.

[0122] Example 4

[0123] Figure 4Schematic diagram of a vehicle limit detection device provided in Embodiment 4 of the present invention. A vehicle limit detection device provided in an embodiment of the present invention is applicable to the situation of detecting the height and width limits of a moving vehicle. The vehicle limit detection device can be implemented in the form of hardware and / or software, such as Figure 4 As shown, the device specifically includes: a vehicle point cloud data acquisition module 401, a center point cloud coordinate determination module 402, an end condition judgment module 403, a lane information determination module 404, and a detection result determination module 405. Among them,

[0124] The vehicle point cloud data acquisition module 401 is configured to acquire vehicle point cloud data of each image acquisition device in the current point cloud frame by performing frame-by-frame point cloud acquisition on a target moving vehicle in the same coordinate system after device calibration by at least one image acquisition device;

[0125] The center point cloud coordinate determination module 402 is configured to determine the lane point cloud width, lane point cloud height, and lane center point cloud coordinate of the target moving vehicle in the current point cloud frame according to the vehicle point cloud data of each image acquisition device;

[0126] The end condition judgment module 403 is configured to determine whether the vehicle point cloud data in the current point cloud frame meets a preset point cloud reception end condition according to the lane center point cloud coordinate;

[0127] The lane information determination module 404 is configured to, if the vehicle point cloud data in the current point cloud frame meets the preset point cloud reception end condition, terminate the acquisition of the vehicle point cloud data of the target moving vehicle, and determine the lane point cloud width, lane point cloud height, and lane center point cloud coordinate determined by the target moving vehicle in at least one point cloud frame when the point cloud reception end condition is met;

[0128] The detection result determination module 405 is configured to determine a vehicle limit detection result for the target moving vehicle according to the lane point cloud width, lane point cloud height, and lane center point cloud coordinate in each point cloud frame.

[0129] In an embodiment of the present invention, based on the vehicle point cloud data of each image acquisition device, the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle in the current point cloud frame are determined. When it is determined that the vehicle point cloud data in the current point cloud frame meets a preset point cloud reception end condition according to the lane center point cloud coordinates, the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle determined in at least one point cloud frame are determined. According to the lane point cloud width, lane point cloud height, and lane center point cloud coordinates in each point cloud frame, the vehicle restriction detection result for the target moving vehicle is determined. Through the lane center point cloud coordinates, the above technical solution determines whether the vehicle point cloud data meets the preset point cloud reception end condition, realizes the accurate acquisition of the point cloud data of the target moving vehicle, and determines the vehicle restriction detection result for the target moving vehicle according to the lane point cloud width, lane point cloud height, and lane center point cloud coordinates in each point cloud frame, thereby realizing the accurate detection of the height and width limits of the target moving vehicle.

[0130] Optionally, the center point cloud coordinate determination module 402 includes:

[0131] The fused point cloud data determination unit is configured to obtain the fused point cloud data in the current point cloud frame according to the vehicle point cloud data of each image acquisition device;

[0132] The target point cloud information determination unit is configured to perform point cloud clustering processing on the fused point cloud data in the current point cloud frame to obtain the target point cloud class information of the target moving vehicle;

[0133] The center point cloud coordinate determination unit is configured to determine the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle in the current point cloud frame according to the point cloud data in the target point cloud class information.

[0134] Optionally, the end condition judgment module 403 includes:

[0135] The first target lane line determination unit is configured to determine the target lane line corresponding to the target moving vehicle in the current point cloud frame based on a preset lane line width range threshold according to the lane center point cloud coordinates;

[0136] The historical lane line determination unit is configured to, if the current point cloud frame is not the first point cloud frame, determine the historical lane line of the target moving vehicle in the historical point cloud frame; the historical point cloud frame is adjacent to the current point cloud frame and is before the current point cloud frame;

[0137] The end condition judgment unit is configured to determine whether the vehicle point cloud data in the current point cloud frame meets the preset point cloud data reception end condition according to the target lane line and the historical lane line.

[0138] Optionally, the detection result determination module 405 includes:

[0139] A second target lane line determination unit, configured to determine a target lane line corresponding to a target driving vehicle in the current point cloud frame based on the lane center point cloud coordinates and a preset lane line width range threshold;

[0140] A width detection result determination unit, configured to determine whether the width of the target driving vehicle exceeds the limit based on the lane point cloud width and the width range threshold of the target lane line, and obtain a width over-limit detection result; and

[0141] A height detection result determination unit, configured to determine whether the height of the target driving vehicle exceeds the limit based on the lane point cloud height and the height range threshold of the target lane line, and obtain a height over-limit detection result;

[0142] A detection result determination unit, configured to generate a vehicle limit detection result including the width over-limit detection result and the height over-limit detection result.

[0143] Optionally, the device further includes:

[0144] A condition end time judgment module, configured to determine a condition end time when the point cloud reception end condition is met after determining the vehicle limit detection result of the target driving vehicle, if the vehicle limit detection result is that the vehicle height exceeds the limit and / or the vehicle width exceeds the limit;

[0145] A candidate vehicle image acquisition module, configured to acquire at least one candidate vehicle image associated with the target driving vehicle; the candidate vehicle image includes a shooting timestamp;

[0146] A target vehicle image selection module, configured to select a target vehicle image from each of the candidate vehicle images according to the condition end time and the shooting timestamps of each candidate vehicle image, and report the target vehicle image for detecting result analysis based on the target vehicle image and the vehicle limit detection result.

[0147] Optionally, the device further includes: a device calibration module; the device calibration module is used to perform device calibration between at least one image acquisition device;

[0148] The device calibration module includes:

[0149] A ground point cloud data acquisition unit, configured to acquire ground point cloud data scanned by each of the image acquisition devices in a preset coordinate system;

[0150] A projection point cloud data acquisition unit for determining the projection point cloud data of the ground point cloud data of each of the image acquisition devices on a preset plane;

[0151] A device calibration unit for calibrating each of the image acquisition devices according to the projection point cloud data of each of the image acquisition devices, so that the point cloud data scanned by each of the image acquisition devices is in the same coordinate system.

[0152] Optionally, the device calibration unit includes:

[0153] A point cloud fitting sub-unit for respectively performing point cloud fitting on the projection point cloud data of each to obtain the road section straight line equations corresponding to each of the image acquisition devices;

[0154] A matrix determination sub-unit for determining the rotation matrix and displacement matrix corresponding to each of the image acquisition devices according to the road section straight line equation;

[0155] A device calibration sub-unit for calibrating each of the image acquisition devices according to the rotation matrix and displacement matrix corresponding to each of the image acquisition devices.

[0156] The vehicle limit detection device provided by the embodiments of the present invention can execute the vehicle limit detection method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0157] Embodiment Five

[0158] Figure 5 FIG. shows a schematic structural diagram of an electronic device 50 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present invention described herein and / or claimed.

[0159] As Figure 5As shown, the electronic device 50 includes at least one processor 51 and a memory communicatively connected to the at least one processor 51, such as a read-only memory (ROM) 52, a random access memory (RAM) 53, etc. The memory stores a computer program executable by the at least one processor. The processor 51 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 52 or the computer program loaded from the storage unit 58 into the random access memory (RAM) 53. In the RAM 53, various programs and data required for the operation of the electronic device 50 can also be stored. The processor 51, the ROM 52, and the RAM 53 are connected to each other via a bus 54. An input / output (I / O) interface 55 is also connected to the bus 54.

[0160] Multiple components in the electronic device 50 are connected to the I / O interface 55, including: an input unit 56, such as a keyboard, a mouse, etc.; an output unit 57, such as various types of displays, speakers, etc.; a storage unit 58, such as a magnetic disk, an optical disc, etc.; and a communication unit 59, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 59 allows the electronic device 50 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0161] The processor 51 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 51 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 51 executes the various methods and processes described above, such as the vehicle limit detection method.

[0162] In some embodiments, the vehicle limit detection method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 58. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 50 via the ROM 52 and / or the communication unit 59. When the computer program is loaded into the RAM 53 and executed by the processor 51, one or more steps of the vehicle limit detection method described above can be executed. Alternatively, in other embodiments, the processor 51 can be configured to execute the vehicle limit detection method by any other appropriate means (e.g., by means of firmware).

[0163] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0164] The computer programs for implementing the methods of the present invention can 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, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer programs can be executed 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.

[0165] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can 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, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0166] To provide interaction with a 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) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., 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 input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0167] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0168] The computing system can include a client and a server. The client and the server are generally far from each other and usually interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0169] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0170] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A vehicle restriction detection method, characterized in that, comprising: Obtaining vehicle point cloud data of each of the image acquisition devices in the current point cloud frame by performing frame-by-frame point cloud acquisition on a target moving vehicle in the same coordinate system after device calibration by at least one image acquisition device; Determining the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle in the current point cloud frame according to the vehicle point cloud data of each of the image acquisition devices; Determining whether the vehicle point cloud data in the current point cloud frame meets a preset point cloud reception end condition according to the lane center point cloud coordinates; If so, terminating the acquisition of the point cloud data of the target moving vehicle, and determining the lane point cloud width, lane point cloud height, and lane center point cloud coordinates determined for the target moving vehicle in at least one point cloud frame when the point cloud reception end condition is met; Determining a vehicle restriction detection result for the target moving vehicle according to the lane point cloud width, lane point cloud height, and lane center point cloud coordinates in each of the point cloud frames.

2. The method according to claim 1, characterized in that, The step of determining the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle in the current point cloud frame according to the vehicle point cloud data of each of the image acquisition devices includes: Obtaining fused point cloud data in the current point cloud frame according to the vehicle point cloud data of each of the image acquisition devices; Performing point cloud clustering processing on the fused point cloud data in the current point cloud frame to obtain target point cloud class information of the target moving vehicle; Determining the lane point cloud width, lane point cloud height, and lane center point cloud coordinates of the target moving vehicle in the current point cloud frame according to the point cloud data in the target point cloud class information.

3. The method according to claim 1, characterized in that, The step of determining whether the vehicle point cloud data in the current point cloud frame meets a preset point cloud reception end condition according to the lane center point cloud coordinates includes: Determining a target lane line corresponding to the target moving vehicle in the current point cloud frame based on a preset lane line width range threshold according to the lane center point cloud coordinates; If the current point cloud frame is not the first frame of the point cloud frame, determining a historical lane line of the target moving vehicle in the historical point cloud frame; the historical point cloud frame is adjacent to the current point cloud frame and is before the current point cloud frame; Determining whether the vehicle point cloud data in the current point cloud frame meets a preset point cloud data reception end condition according to the target lane line and the historical lane line.

4. The method according to claim 1, characterized in that, The step of determining a vehicle restriction detection result for the target moving vehicle according to the lane point cloud width, lane point cloud height, and lane center point cloud coordinates in each of the point cloud frames includes: Determining a target lane line corresponding to the target moving vehicle in the current point cloud frame based on a preset lane line width range threshold according to the lane center point cloud coordinates; Based on the width range threshold of the target lane line, determine whether the target moving vehicle is over-width according to the width of the lane point cloud, and obtain the over-width detection result; and, Based on the height range threshold of the target lane line, determine whether the target moving vehicle is over-height according to the height of the lane point cloud, and obtain the over-height detection result; Generate a vehicle restriction detection result including the over-width detection result and the over-height detection result.

5. The method according to claim 1, wherein, after determining the vehicle restriction detection result of the target moving vehicle, the method further includes: if the vehicle restriction detection result is that the vehicle is over-height and / or over-width, determine the condition end time when the point cloud reception end condition is satisfied; Obtain at least one candidate vehicle image associated with the target moving vehicle; the candidate vehicle image includes a shooting timestamp; According to the condition end time and the shooting timestamps of the candidate vehicle images, select a target vehicle image from the candidate vehicle images, and report the target vehicle image for detecting result analysis according to the target vehicle image and the vehicle restriction detection result.

6. The method according to any one of claims 1-5, wherein, The device calibration method between at least one image acquisition device is as follows: Obtain the ground point cloud data scanned by each image acquisition device in a preset coordinate system; Determine the projected point cloud data of the ground point cloud data of each image acquisition device on a preset plane; According to the projected point cloud data of each image acquisition device, perform device calibration on each image acquisition device so that the point cloud data scanned by each image acquisition device is in the same coordinate system.

7. The method according to claim 6, wherein, The performing device calibration on each image acquisition device according to the projected point cloud data of each image acquisition device includes: Perform point cloud fitting on each of the projected point cloud data respectively to obtain the road section straight line equations corresponding to each image acquisition device; According to the road section straight line equations, determine the rotation matrix and displacement matrix corresponding to each image acquisition device respectively; According to the rotation matrix and displacement matrix corresponding to each image acquisition device respectively, perform device calibration on each image acquisition device.

8. A vehicle restriction detection device, wherein, comprising: A vehicle point cloud data acquisition module, configured to acquire the vehicle point cloud data of each image acquisition device in the current point cloud frame by performing frame-by-frame point cloud acquisition on a target moving vehicle in the same coordinate system after device calibration by at least one image acquisition device; A central point cloud coordinate determination module, configured to determine the lane point cloud width, lane point cloud height and lane central point cloud coordinate of the target moving vehicle in the current point cloud frame according to the vehicle point cloud data of each image acquisition device; An end condition judgment module, configured to determine whether the vehicle point cloud data in the current point cloud frame satisfies a preset point cloud reception end condition according to the lane central point cloud coordinate; A lane information determination module, configured to terminate the acquisition of the point cloud data of the target moving vehicle if the vehicle point cloud data in the current point cloud frame satisfies a preset point cloud reception end condition, and determine the lane point cloud width, lane point cloud height, and lane center point cloud coordinates determined for the target moving vehicle in at least one point cloud frame when the point cloud reception end condition is satisfied; A detection result determination module, configured to determine a vehicle limit detection result for the target moving vehicle according to the lane point cloud width, lane point cloud height, and lane center point cloud coordinates in each of the point cloud frames.

9. An electronic device, characterized in that, the electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the vehicle limit detection method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, the computer-readable storage medium stores computer instructions for causing a processor to implement the vehicle limit detection method according to any one of claims 1-7 when executed.

Images