Method for acquiring vehicle length and vehicle length detection device
By collecting point cloud data of the front and rear of the vehicle in different driving areas and using salient feature points for data registration, the problem of scanning laser rangefinders being unable to obtain the complete length of large vehicles is solved, and low-cost and efficient vehicle length measurement is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- WUHAN WANJI INFORMATION TECH
- Filing Date
- 2022-12-05
- Publication Date
- 2026-06-09
AI Technical Summary
When detecting the length of large vehicles, existing technologies, such as scanning laser rangefinders, struggle to acquire complete length information at once, and multi-sensor combinations are costly.
By collecting point cloud data of the front and rear of the vehicle in different driving areas, data registration is performed using salient feature points, and the overall outline of the vehicle is stitched together to obtain its length.
It achieves low-cost and efficient vehicle length measurement, reduces the installation and performance requirements of the detection device, and reduces the amount of computation.
Smart Images
Figure CN116106922B_ABST
Abstract
Description
Technical Field
[0001] This disclosure generally relates to the field of vehicle inspection technology. More specifically, this disclosure relates to a method for obtaining vehicle length and a vehicle length inspection device. Background Technology
[0002] In vehicle length detection applications based on scanning laser rangefinders, how to economically, quickly, and effectively detect the length of large vehicles has always been a challenge. Due to installation conditions and performance limitations of scanning laser rangefinders, when detecting large vehicles, the rangefinder can often only scan a portion of the vehicle, and the point cloud consists of discrete measurement points. Therefore, it is impossible to obtain complete vehicle length information in a single measurement, necessitating multiple measurements. In existing technologies, point cloud registration is generally used during these multiple measurements. This involves stitching together a complete vehicle point cloud by tracking the vehicle's displacement. However, this method often only scans the vehicle body area. Since the vehicle body is long and has a flat surface, its point cloud exhibits unequal spacing and is approximately linear in shape. The differences between point clouds in adjacent scan frames are also very small. Therefore, it is impossible to stitch together a complete vehicle point cloud based on adjacent frame point cloud registration or feature point matching methods.
[0003] Another existing method can measure vehicle length by using multiple sensors. This method only requires registration of local feature point clouds to reconstruct vehicle displacement, but this multi-sensor approach is more costly. Summary of the Invention
[0004] To address one or more of the technical problems mentioned above, this disclosure provides a method for obtaining vehicle length and a vehicle length detection device.
[0005] In a first aspect, embodiments of this disclosure provide a method for obtaining vehicle length, comprising:
[0006] Collect first point cloud data of the vehicle when it is in a first driving area and second point cloud data when it is in a second driving area; wherein, the first point cloud data is the point cloud data obtained when the front part of the vehicle is in the first driving area, including the point cloud data of the front part of the vehicle, and the second point cloud data is the point cloud data obtained when the rear part of the vehicle is in the second driving area, including the point cloud data of the rear part of the vehicle.
[0007] Point cloud data for determining the overall outline of the vehicle based on the first and second point cloud data; and
[0008] The length of the vehicle is obtained from the point cloud data of the overall outline of the vehicle.
[0009] In one embodiment, the projection of the detection device used to scan the vehicle onto the ground is taken as the origin, wherein the first driving area is a preset area before the front of the vehicle passes the origin, and the second driving area is a preset area after the rear of the vehicle leaves the origin.
[0010] In one embodiment, determining the point cloud data of the overall vehicle outline includes: obtaining point cloud data of a first outline of the vehicle based on the first point cloud data; obtaining point cloud data of a second outline of the vehicle based on the second point cloud data; and determining the point cloud data of the overall vehicle outline based on the point cloud data of the first outline and the point cloud data of the second outline.
[0011] In one embodiment, the first point cloud data includes multiple frames of point cloud data, and obtaining the point cloud data of the first contour includes: determining one or more first feature points on the first contour of the vehicle based on the multiple frames of point cloud data, and the distance between the first feature points and the same reference position at different times, wherein the distance is the distance in the vehicle's driving direction; and fusing the point cloud data at different times in the first point cloud data based on the distance to obtain the point cloud data of the first contour.
[0012] In one embodiment, the first feature point is a point determined based on each frame of point cloud data whose distance from the detection device used to scan the vehicle meets a preset condition, wherein the distance is the distance in the vehicle's direction of travel.
[0013] In one embodiment, determining the point cloud data of the overall vehicle contour includes: determining one or more second feature points on the vehicle based on the point cloud data of the first contour and the point cloud data of the second contour, and the position difference of the second feature points at different times, wherein the position difference is the position difference in the vehicle's driving direction; and fusing the point cloud data of the first contour and the point cloud data of the second contour based on the position difference to obtain the point cloud data of the overall vehicle contour.
[0014] In one embodiment, determining the position difference of the second feature point at different times based on the point cloud data of the first contour and the point cloud data of the second contour includes: performing curve fitting based on the point cloud data of the first contour and the point cloud data of the second contour to obtain the contour curve of the first rear portion of the vehicle and the contour curve of the second rear portion; determining the point cloud data at the tangent point between the contour curve of the first rear portion and the first straight line and the point cloud data at the tangent point between the contour curve of the second rear portion and the second straight line, wherein the first straight line and the second straight line are parallel lines; and determining the position difference of the second feature point on the vehicle at different times based on the point cloud data at the tangent point between the contour curve of the first rear portion and the first straight line and the point cloud data at the tangent point between the contour curve of the second rear portion and the second straight line.
[0015] In one embodiment, after determining the point cloud data at the tangent point of the contour curve of the first rear portion of the vehicle and the first straight line, and the point cloud data at the tangent point of the contour curve of the second rear portion of the vehicle and the second straight line, and before determining the position difference of the second feature point on the vehicle at different times, the method further includes: determining the position difference of the tangent points of the contour curve of the first rear portion of the vehicle and the first straight line and the tangent points of the contour curve of the second rear portion of the vehicle and the second straight line in a preset direction based on the point cloud data at the tangent points of the contour curve of the first rear portion of the vehicle and the first straight line and the tangent points of the contour curve of the second rear portion of the vehicle and the second straight line, wherein the preset direction is a non-vehicle driving direction; and in response to the position difference being less than or equal to a preset difference, using the tangent points of the contour curve of the first rear portion of the vehicle and the first straight line and the tangent points of the contour curve of the second rear portion of the vehicle and the second straight line as the second feature point on the vehicle, so as to calculate the position difference of each of the one or more second feature points on the vehicle at different times.
[0016] In one embodiment, obtaining the length of the vehicle based on point cloud data of the overall vehicle outline includes: determining the point cloud data of the two points furthest apart in the driving direction based on the point cloud data of the overall vehicle outline; and calculating the length of the vehicle based on the point cloud data of the two furthest points.
[0017] In a second aspect, this disclosure also provides a vehicle length detection device, comprising: a detection device disposed above a lane, its scanning surface being perpendicular to the ground and parallel to the vehicle's direction of travel, configured to: scan the vehicle when the front portion of the vehicle is located within a first driving area to obtain first point cloud data, wherein the first point cloud data includes point cloud data of the front portion; and scan the vehicle when the rear portion of the vehicle is located within a second driving area to obtain second point cloud data, wherein the second point cloud data includes point cloud data of the rear portion; and a data processing unit electrically connected to the detection device, configured to: determine point cloud data of the overall outline of the vehicle based on the first point cloud data and the second point cloud data; and obtain the length of the vehicle based on the point cloud data of the overall outline of the vehicle.
[0018] Based on the foregoing description of the present disclosure, those skilled in the art will understand that the scheme described in the above embodiments can utilize salient feature points of the front and rear of the vehicle within different driving areas for data registration, thereby allowing for the measurement of vehicle length based on the overall vehicle profile obtained through registration. This characteristic makes the installation and performance requirements of the detection device low, and since only a single detection device is needed to acquire point cloud data, the overall equipment cost is low. Furthermore, compared to previous point cloud registration methods based on vehicle location (such as ICP registration and Harris feature point matching methods), this scheme has a lower computational load, resulting in higher data registration efficiency. Attached Figure Description
[0019] The above and other objects, features, and advantages of exemplary embodiments of the present disclosure will become readily apparent upon reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of the present disclosure are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts, wherein:
[0020] Figure 1 and Figure 2 The following are exemplary application scenarios for obtaining vehicle length that can be applied to the embodiments of this disclosure;
[0021] Figure 3 An exemplary flowchart of a method for obtaining vehicle length according to an embodiment of the present disclosure is shown;
[0022] Figure 4 An exemplary flowchart illustrates a method for determining point cloud data of the overall outline of a vehicle according to an embodiment of the present disclosure;
[0023] Figure 5 An exemplary principle block diagram of a vehicle length detection device according to an embodiment of the present disclosure is shown. Detailed Implementation
[0024] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.
[0025] Figure 1 and Figure 2 Application scenarios for obtaining vehicle length that can be applied to embodiments of this disclosure are illustrated. For example... Figure 1 and Figure 2 As shown, a detection device 101 is mounted on a gantry (e.g., a gantry frame, not shown) spanning the lane. The mounting height can be set according to the height of a typical large vehicle, for example, greater than or equal to 5 meters (above the highest point of the vehicle), thus facilitating vehicle scanning. Furthermore, the scanning surface of the detection device can be perpendicular to the ground and parallel to the vehicle's direction of travel. Moreover, to perform a comprehensive scan of the vehicle and obtain more sufficient point cloud data, the scanning angle of the detection device can be greater than or equal to 100°.
[0026] In one implementation, the aforementioned detection device can be a single-line scanning laser rangefinder, which can scan the vehicle's cross-section. For ease of description, a coordinate system can be first determined; for example, the projection of the detection device onto the ground can be taken as the origin (0,0), the vehicle's direction of travel can be the X direction, and vertically upward can be taken as the positive Y direction.
[0027] Figure 1 The image shows the front of the vehicle before it returned to its starting point. Figure 2 The image shows the rear of the vehicle after it has left its original position. For example... Figure 1 As shown, the vehicle can be scanned within a preset area (first driving area) before its front end enters the origin, yielding first point cloud data. This first point cloud data can include point cloud data from the front of the vehicle.
[0028] like Figure 2 As shown, the vehicle can be scanned within a preset area (second driving area) after its rear has left the origin, yielding second point cloud data. This second point cloud data can include point cloud data from the rear of the vehicle.
[0029] Figure 1 and Figure 2 The reference s sign indicates the scan line emitted by the detection device 101. Typically, both the first and second point cloud data can include multiple frames of point cloud data.
[0030] In one implementation scenario, preset distances L and T can be selected to determine the first and second driving areas. Specifically, the vehicle's driving direction (positive or negative) and its movement towards or away from the origin can be determined based on the changes in the number of scan points in the intervals [-L,0] and (0,T] in the X direction.
[0031] When the vehicle is traveling in the forward direction, in the first stage, at least the point cloud frame sequence A of all points along the X-axis from coordinate (T,0) to the origin (0,0) is acquired; in the second stage, at least the point cloud frame sequence B of all points along the X-axis from the origin (0,0) to (-L,0) is acquired. When the vehicle is traveling in the reverse direction, in the first stage, at least the point cloud frame sequence A of all points along the X-axis from coordinate (-T,0) to the origin (0,0) is acquired; in the second stage, at least the point cloud frame sequence B of all points along the X-axis from the origin (0,0) to (L,0) is acquired.
[0032] The above text combined Figure 1 and Figure 2 The application scenarios of this disclosure have been described. It is understood that the above embodiments are merely exemplary and not restrictive, and those skilled in the art can modify them as needed. For example, a ranging device installed on the vehicle can be used to continuously monitor whether the vehicle is approaching or leaving the origin and its direction of travel. Additionally, the detection device can be installed in other locations within the lane (e.g., on one side of the lane) or mounted using other equipment (e.g., a pillar).
[0033] The present disclosure will now describe the vehicle length acquisition scheme in detail with reference to application scenarios such as those shown in the above embodiments.
[0034] Figure 3 An exemplary flowchart of a method 300 for obtaining vehicle length according to an embodiment of the present disclosure is shown.
[0035] like Figure 3 As shown, method 300 may include, in step S301, acquiring first point cloud data of the vehicle within a first driving area and second point cloud data within a second driving area. The first driving area, the second driving area, and the first and second point cloud data have been combined with the aforementioned... Figure 1 and Figure 2 The illustrated embodiments have been described and will not be repeated here. In this embodiment, the first point cloud data can be the point cloud frame sequence A described in the previous embodiments, and the second point cloud data can be the point cloud frame sequence B described in the previous embodiments.
[0036] As described in the background section, a significant reason for the inaccuracy in vehicle length measurements in the prior art is the inability to register due to unclear vehicle body features. To address this issue, this disclosure utilizes salient features on the front and rear of the vehicle within different driving areas (e.g., the point closest to the detection device in the first driving area before the vehicle enters the origin, and the point closest to the detection device in the second driving area after the vehicle leaves the origin) to reconstruct the front (including the vehicle body) and rear portions (obtaining their outlines). The resulting overall vehicle outline can then be used for vehicle length measurement. Based on this, the first point cloud data can be the point cloud data obtained when the front portion of the vehicle is within the first driving area, and it includes the point cloud data of the front portion. Similarly, the second point cloud data can be the point cloud data obtained when the rear portion of the vehicle is within the second driving area, and it also includes the point cloud data of the rear portion.
[0037] After acquiring the first and second point cloud data, the method proceeds to step S302, whereby the point cloud data of the overall vehicle outline is determined based on the first and second point cloud data. A relatively accurate overall vehicle outline can be obtained from these two parts of point cloud data, and further, a relatively accurate vehicle length can be derived from them.
[0038] After obtaining the point cloud data of the overall vehicle outline, the method can proceed to step S303 to obtain the vehicle length based on the point cloud data of the overall vehicle outline. In one implementation scenario, the point cloud data of the two points furthest apart in the driving direction can be determined based on the point cloud data of the overall vehicle outline, and then the vehicle length can be calculated based on the point cloud data of the two furthest points. Taking the aforementioned coordinate system as an example, the maximum and minimum x-coordinates can be obtained from the point cloud data of the overall vehicle outline, and the difference between the two coordinates can be calculated; this difference is the vehicle length.
[0039] As described above, this solution utilizes salient feature points at the front and rear of the vehicle within different driving areas for data registration, thereby enabling the measurement of vehicle length based on the obtained overall vehicle profile. This characteristic reduces the requirements for the installation and performance of the detection device, and since only a single detection device is needed to acquire point cloud data, the overall equipment cost is low.
[0040] Figure 4 An exemplary flowchart illustrates a method for determining point cloud data of the overall contour of a vehicle according to an embodiment of this disclosure. Figure 4 As shown, method 400 may include, at step S401, obtaining point cloud data of a first contour of the vehicle based on the first point cloud data.
[0041] As described in the foregoing embodiments, the first point cloud data may include multiple frames of point cloud data. Based on this, point cloud data of the vehicle's first contour can be obtained through data fusion. Specifically, the distance between each of one or more first feature points on the vehicle's first contour and the same reference position at different times can be determined based on the multiple frames of point cloud data, where the distance is the distance in the vehicle's driving direction. Then, the point cloud data from different times in the first point cloud data can be fused based on this distance to obtain the point cloud data of the first contour. It can be understood that the characteristic of a single-scan point cloud is that it is denser in the near and sparser in the far. This solution can increase the density of the point cloud at a distance by fusing point cloud data from different times, thus better restoring the vehicle contour.
[0042] In one implementation scenario, the first feature point can be a point whose distance from the detection device used to scan the vehicle, determined based on each frame of point cloud data, meets a preset condition, where the distance is the distance in the vehicle's travel direction. For example, the point closest to the line x=0 in each frame of point cloud data (i.e., the point closest to the detection device in the vehicle's travel direction) can be selected as the first feature point, and the distance from this first feature point to the line x=0 can be used as the feature distance. Each point is then translated based on this feature distance. This operation is performed on all frames, resulting in all first feature points in all frames having an x-coordinate of 0. The translated point clouds are then merged into a new point cloud a, which represents the first contour of the vehicle, and the point cloud data of each point on this point cloud constitutes the point cloud data of the vehicle's first contour. As described above, the features of this first feature point are quite obvious, allowing for fast and accurate data registration and fusion.
[0043] It is understood that the above method is merely exemplary and not restrictive, and those skilled in the art can modify it to suit the needs of different scenarios. For example, the point farthest from the line x=0 or the point closest to the line x=1 can also be selected as the first feature point.
[0044] Similarly, in step S402, the method can also obtain point cloud data of the second contour of the vehicle based on the second point cloud data. The method for obtaining the point cloud data of the second contour of the vehicle can refer to the method for obtaining the point cloud data of the first contour of the vehicle described above, and will not be detailed here.
[0045] After acquiring the point cloud data of the first contour of the vehicle and the point cloud data of the second contour of the vehicle, in step S403, the method can determine the point cloud data of the overall contour of the vehicle based on the point cloud data of the first contour and the point cloud data of the second contour.
[0046] Similar to the method described above for obtaining point cloud data of the vehicle's outline, point cloud data of the overall vehicle outline can also be obtained through data fusion. Specifically, the position difference of each of one or more second feature points on the vehicle at different times can be determined based on the point cloud data of the first and second outlines, where the position difference is the position difference in the vehicle's driving direction. Then, the point cloud data of the first and second outlines can be fused based on this position difference to obtain the point cloud data of the overall vehicle outline.
[0047] Specifically, curve fitting can be performed on the point cloud data of the first contour and the point cloud data of the second contour to obtain the contour curves of the first and second rear portions of the vehicle. Additionally, the contour curve of the first rear portion and the first straight line (e.g., [missing information]) can be determined based on the point cloud data of the first and second contours. Figure 1 The point cloud data at the tangent point of the straight line r1 in the middle and the contour curve of the second rear part of the vehicle and the second straight line (e.g. Figure 2 The point cloud data at the tangent point of the straight line r2), where the first and second straight lines are parallel. In one implementation, the two straight lines can be y = kx + h and y = kx + m, respectively. Based on the contour shape of the rear of the vehicle and the height-to-length ratio of the first contour, the value of k varies depending on the vehicle's direction of travel. For example, when the vehicle is traveling forward, its value range can be [-1, -0.2], and when the vehicle is traveling backward, its value range can be [0.2, 1]. Choosing such a value range allows it to be tangent to the contour curves of the first and second rear of the vehicle to obtain the tangent point. By obtaining parallel lines with different k values and finding the tangent points with the contour curves of the first and second rear of the vehicle, one or more sets of second feature points can be obtained. In addition, h and m are not equal.
[0048] Furthermore, based on the point cloud data at the tangent point between the contour curve of the first rear portion of the vehicle and the first straight line, and the point cloud data at the tangent point between the contour curve of the second rear portion of the vehicle and the second straight line, the position difference of each of the one or more second feature points on the vehicle at different times can be determined.
[0049] Using tangent points as feature points for data registration reduces dependence on vehicle shape, thereby minimizing or even eliminating the influence of the vehicle's motion and position (i.e., not affecting registration) on the registration process. This solves the problem of tracking (and registering) large vehicles with flat bodies. Therefore, the front and rear sections of the vehicle can be quickly stitched together using these feature points. Furthermore, this approach requires less computation than previous point cloud registration methods based on vehicle position (such as ICP registration and Harris feature point matching), resulting in higher data registration efficiency.
[0050] To ensure that the two tangent points obtained above are the same feature point, in one embodiment, after determining the point cloud data at the tangent point of the contour curve of the first rear portion of the vehicle and the first straight line, and before determining the position difference of each of the one or more second feature points on the vehicle at different times, the position difference of the tangent points of the contour curve of the first rear portion of the vehicle and the first straight line, and the tangent points of the contour curve of the second rear portion of the vehicle and the second straight line in a preset direction can be determined based on the point cloud data at the tangent points of the contour curve of the first rear portion of the vehicle and the first straight line, and the tangent points of the contour curve of the second rear portion of the vehicle and the second straight line. The preset direction can be a direction other than the vehicle's driving direction, such as a direction perpendicular to the ground.
[0051] Specifically, in response to a position difference less than or equal to a preset difference value, the tangent points of the contour curve of the first rear portion of the vehicle and the first straight line, and the tangent points of the contour curve of the second rear portion of the vehicle and the second straight line, are used as second feature points on the vehicle. Based on these, the position difference of each of the one or more second feature points on the vehicle at different times is calculated. Generally, if the vehicle position difference is not greater than 0.5m, it can be considered as the same vehicle. Therefore, the preset difference value here can be any value within the range of 0 to 0.5, such as 0, 0.3, or 0.5. This scheme ensures the consistency of the two obtained tangent points, thereby guaranteeing the accuracy of data registration and fusion.
[0052] The preceding section, with reference to embodiments, described a scheme for stitching together the point clouds of the first and second contours of a vehicle by fitting the contour curve of the rear portion. It is understood that since the rear of the vehicle is less likely to be obscured by the cargo it carries, utilizing this feature ensures the accuracy of the registration results. In another implementation scenario, a similar method to the above embodiments can be used to fit the two contour curves of the front portion of the vehicle, thereby performing data fusion to obtain the point cloud data of the overall vehicle contour; this will not be detailed here.
[0053] Figure 5An exemplary principle block diagram of a vehicle length detection device 500 according to an embodiment of the present disclosure is shown. (The foregoing is in conjunction with...) Figure 1 and Figure 2 The application scenarios shown are applicable to the vehicle length detection device 500 in this solution, and this solution is not limited to the application scenarios listed above.
[0054] like Figure 5 As shown, the vehicle length detection device 500 may include a detection device 501 and a data processing unit 502. The detection device 501 may be positioned above the lane, with its scanning surface perpendicular to the ground and parallel to the vehicle's direction of travel. It scans the vehicle when the front portion is within a first driving area to obtain first point cloud data, which includes point cloud data of the front portion. It can also scan the vehicle when the rear portion is within a second driving area to obtain second point cloud data, which also includes point cloud data of the rear portion. The detection device 501 may be the aforementioned... Figure 1 and Figure 2 The detection device 101 in the illustrated embodiment can be fixedly or detachably connected to a gantry or column to ensure installation stability or replaceability. Furthermore, the fixed connection can be achieved by riveting or welding with connectors, while the detachable connection can be achieved by snap-fitting or screwing with connectors. As described in the foregoing embodiments, the first point cloud data and the second point cloud data can include multiple frames of point cloud data.
[0055] The data processing unit 502 can be electrically connected to the detection device 501 and is used to determine the point cloud data of the overall vehicle outline based on the first point cloud data and the second point cloud data, and to obtain the length of the vehicle based on the point cloud data of the overall vehicle outline. The data processing unit 502 may include a controller or PLC, etc., and can be connected to the detection device 501 by wired or wireless means. The wired connection can be a USB connection or a fiber optic connection, and the wireless connection can include a Wi-Fi connection.
[0056] The method for obtaining vehicle length has been described in detail above with reference to one or more embodiments, and will not be repeated here. As can be seen from the description of the foregoing embodiments, this solution can utilize salient feature points of the front and rear of the vehicle in different driving areas for data registration, thereby allowing the measurement of vehicle length based on the overall vehicle outline obtained from the registration. Furthermore, this solution has low requirements for the installation and performance of the detection device, and is relatively inexpensive.
[0057] As described above, the embodiments of this disclosure can be implemented as a method or apparatus. Therefore, this disclosure can be specifically implemented in the following forms: entirely hardware, entirely software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, this disclosure can also be implemented as a computer program product contained in one or more computer-readable media, which contains computer-readable program code. Any combination of one or more computer-readable media can be used. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.
[0058] Computer program code for performing the operations of this disclosure can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network (including a local area network (LAN) or a wide area network (WAN)), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0059] It should be understood that each block of the method flowcharts and / or block diagrams of the embodiments of this disclosure, as well as combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine that executes on the computer or other programmable data processing apparatus to create means for implementing the functions / operations specified in the blocks of the flowcharts and / or block diagrams. These computer program instructions can also be stored in a computer-readable medium that causes a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable medium produce a product including instruction means for implementing the functions / operations specified in the blocks of the flowcharts and / or block diagrams. The computer program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, can provide a process for implementing the functions / operations specified in the blocks of the flowcharts and / or block diagrams.
[0060] While the embodiments of this disclosure are described above, the content is merely an example for the purpose of facilitating understanding of this disclosure and is not intended to limit the scope or application scenarios of this disclosure. Any person skilled in the art can make any modifications and changes in form and detail of the implementation without departing from the spirit and scope disclosed herein; however, the scope of patent protection of this disclosure shall still be determined by the scope defined in the appended claims.
Claims
1. A method for obtaining the length of a vehicle, comprising: The system collects first point cloud data of the vehicle within a first driving area and second point cloud data of the vehicle within a second driving area. The first point cloud data is the point cloud data obtained when the front of the vehicle is within the first driving area, including the point cloud data of the front portion. The second point cloud data is the point cloud data obtained when the rear of the vehicle is within the second driving area, including the point cloud data of the rear portion. The projection of the detection device used to scan the vehicle onto the ground is taken as the origin. The first driving area is a preset area before the front of the vehicle passes the origin, and the second driving area is a preset area after the rear of the vehicle leaves the origin. Point cloud data of the overall vehicle outline is determined based on the first point cloud data and the second point cloud data, and the first point cloud data and the second point cloud data are fused into point cloud data of the overall vehicle outline; and The length of the vehicle is obtained based on the point cloud data of the overall outline of the vehicle; The point cloud data used to determine the overall outline of the vehicle includes: The first point cloud data of the vehicle's first outline is obtained based on the first point cloud data; The second point cloud data of the vehicle's second contour is obtained based on the second point cloud data; and Based on the point cloud data of the first contour and the point cloud data of the second contour, one or more second feature points on the vehicle are determined, and the position differences of the second feature points at different times are defined, wherein the position differences are position differences in the vehicle's travel direction; and The point cloud data of the first contour and the point cloud data of the second contour are fused according to the position difference to obtain the point cloud data of the overall contour of the vehicle. The determination of the position difference of the second feature point at different times based on the point cloud data of the first contour and the point cloud data of the second contour includes: Curve fitting is performed on the point cloud data of the first contour and the point cloud data of the second contour to obtain the contour curve of the first rear part and the contour curve of the second rear part of the vehicle. Based on the point cloud data of the first contour and the point cloud data of the second contour, the point cloud data at the tangent point between the contour curve of the first rear portion and the first straight line, and the point cloud data at the tangent point between the contour curve of the second rear portion and the second straight line are determined, wherein the first straight line and the second straight line are parallel lines; and Based on the point cloud data at the point of tangency between the contour curve of the first rear part of the vehicle and the first straight line, and the point cloud data at the point of tangency between the contour curve of the second rear part of the vehicle and the second straight line, the position difference of the second feature point on the vehicle at different times is determined.
2. The method according to claim 1, characterized in that, The first point cloud data includes multiple frames of point cloud data, and obtaining the point cloud data of the first contour includes: Based on the multi-frame point cloud data, one or more first feature points on the first contour of the vehicle are determined, along with the distances between the first feature points and the same reference position at different times, wherein the distances are distances in the vehicle's travel direction; and Based on the distance, the point cloud data at different times in the first point cloud data are fused to obtain the point cloud data of the first contour.
3. The method according to claim 2, characterized in that, The first feature point is a point determined based on each frame of point cloud data whose distance from the detection device used to scan the vehicle meets a preset condition, wherein the distance is the distance in the vehicle's driving direction.
4. The method according to claim 1, characterized in that, After determining the point cloud data at the tangent point between the contour curve of the first rear portion of the vehicle and the first straight line, and the point cloud data at the tangent point between the contour curve of the second rear portion of the vehicle and the second straight line, before determining the position difference of the second feature point on the vehicle at different times, the method further includes: Based on the point cloud data at the tangent point between the contour curve of the first rear portion and the first straight line, and the point cloud data at the tangent point between the contour curve of the second rear portion and the second straight line, the positional difference between the tangent points of the contour curve of the first rear portion and the first straight line, and the tangent point of the contour curve of the second rear portion and the second straight line, in a preset direction is determined, wherein the preset direction is a direction other than the vehicle's driving direction; and In response to the position difference being less than or equal to a preset difference, the tangent point between the contour curve of the first rear portion of the vehicle and the first straight line, and the tangent point between the contour curve of the second rear portion of the vehicle and the second straight line, are taken as second feature points on the vehicle, so as to calculate the position difference of each of the one or more second feature points on the vehicle at different times.
5. The method according to claim 1, characterized in that, The length of the vehicle is obtained from the point cloud data of the overall vehicle outline, including: Based on the point cloud data of the overall vehicle outline, determine the point cloud data of the two points furthest apart in the driving direction; and The length of the vehicle is calculated based on the point cloud data of the two points that are furthest apart.
6. A vehicle length detection device, characterized in that, include: The detection device, positioned above the lane, with its scanning surface perpendicular to the ground and parallel to the direction of vehicle travel, is used for: When the front part of the vehicle is located within the first driving area, the vehicle is scanned to obtain first point cloud data, wherein the first point cloud data includes point cloud data of the front part of the vehicle. as well as When the rear of the vehicle is within the second driving area, the vehicle is scanned to obtain second point cloud data, which includes point cloud data of the rear of the vehicle. The projection of the detection device on the ground is taken as the origin, where the first driving area is a preset area before the front of the vehicle passes the origin, and the second driving area is a preset area after the rear of the vehicle leaves the origin. A data processing unit, electrically connected to the detection device, is used for: The point cloud data of the overall outline of the vehicle is determined based on the first point cloud data and the second point cloud data, so as to fuse the first point cloud data and the second point cloud data into the point cloud data of the overall outline of the vehicle. as well as The length of the vehicle is obtained based on the point cloud data of the overall outline of the vehicle; The point cloud data used to determine the overall outline of the vehicle includes: The first point cloud data of the vehicle's first outline is obtained based on the first point cloud data; The second point cloud data of the vehicle's second contour is obtained based on the second point cloud data; and Based on the point cloud data of the first contour and the point cloud data of the second contour, one or more second feature points on the vehicle are determined, and the position differences of the second feature points at different times are defined, wherein the position differences are position differences in the vehicle's travel direction; and The point cloud data of the first contour and the point cloud data of the second contour are fused according to the position difference to obtain the point cloud data of the overall contour of the vehicle. The determination of the position difference of the second feature point at different times based on the point cloud data of the first contour and the point cloud data of the second contour includes: Curve fitting is performed on the point cloud data of the first contour and the point cloud data of the second contour to obtain the contour curve of the first rear part and the contour curve of the second rear part of the vehicle. Based on the point cloud data of the first contour and the point cloud data of the second contour, the point cloud data at the tangent point between the contour curve of the first rear portion and the first straight line, and the point cloud data at the tangent point between the contour curve of the second rear portion and the second straight line are determined, wherein the first straight line and the second straight line are parallel lines; and Based on the point cloud data at the point of tangency between the contour curve of the first rear part of the vehicle and the first straight line, and the point cloud data at the point of tangency between the contour curve of the second rear part of the vehicle and the second straight line, the position difference of the second feature point on the vehicle at different times is determined.