Non-stop detection system and data processing method thereof

By using lidar in the non-site non-stop detection system to obtain the space-time trajectory of the vehicle and match it with the vehicle pictures and weighing information, the problem of inaccurate matching of vehicle data is solved, and the accuracy and reliability of law enforcement data is improved.

CN118942259APending Publication Date: 2024-11-12VANJEE TECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310516472.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-09
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

In the non-site non-stop detection system, the matching of vehicle photos and weighing information has the problem of incomplete overlap between time and space coordinates, resulting in low data matching accuracy, especially in multi-lane and multi-vehicle situations.

Method used

Lidar is used to obtain the laser point cloud data of the vehicle, form the temporal and spatial trajectory of the vehicle, and match it with the vehicle picture data and weighing information, and judge the matching accuracy by the European-style distance and overlap threshold.

Benefits of technology

It improves the accuracy of vehicle data matching, enhances the reliability of the system for vehicle passing records, and reduces the error rate of law enforcement data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure FT_1
    Figure FT_1
  • Figure FT_2
    Figure FT_2
  • Figure FT_3
    Figure FT_3
Patent Text Reader

Abstract

The invention relates to a non-stop detection system and a data processing method thereof, and the method comprises the steps: obtaining the laser point cloud data of a vehicle, determining the spatial-temporal trajectory of the vehicle in a detection region according to the continuous laser point cloud data after the vehicle passes through the detection region, and obtaining the vehicle image data of the vehicle, and according to detection time and detection coordinates in the vehicle picture information, matching the vehicle picture information with the spatial-temporal trajectory to obtain a vehicle passing record of the vehicle. It can be understood that according to the embodiment, the spatial-temporal trajectory corresponding to the vehicle contour is formed through the laser point cloud data, the real moving state of the vehicle in the detection area can be truly reflected, and therefore the data matching accuracy can be improved by matching the spatial-temporal trajectory of the vehicle with the vehicle picture information.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application generally relates to the field of vehicle detection technology, and in particular to a non-stop detection system and a data processing method thereof. Background Art

[0002] This section is intended to provide background or context for the embodiments of the invention set forth in the claims. The descriptions herein may include concepts that may be explored, but not necessarily concepts that have been previously thought of or explored. Therefore, unless otherwise noted herein, the content described in this section is not prior art with respect to the specification and claims of this application, and is not admitted to be prior art by inclusion in this section.

[0003] The off-site non-stop detection system is an unattended evidence collection and enforcement system used to detect illegal driving and overload of road vehicles. Due to the unattended nature of the off-site non-stop detection system, it requires the data used for law enforcement to be clear, complete, and enforceable, which places high demands on the off-site non-stop detection system.

[0004] The enforcement data of the off-site non-stop detection system mainly includes vehicle photos (used to identify vehicle license plates) and vehicle weighing information. The capture camera obtains vehicle photos when the vehicle passes a fixed position, and records the time when the vehicle photos are obtained; the weighing device obtains the weighing waveform data when the vehicle passes through the weighing area, and obtains the vehicle's weighing information based on the weighing waveform data, and records the time when the weighing information is generated. The system completes the matching based on the acquisition time, approximate location of the vehicle photo, and the time of the weighing information. Since the generation time of the weighing information and the capture time and spatial coordinates of the vehicle photo are not completely coincident, the system often has problems matching the weighing information and vehicle photo information. With the promotion and application of the off-site non-stop detection system, the problem of mismatch between weighing information and vehicle capture pictures is becoming more and more serious. Summary of the invention

[0005] In order to at least solve one or more of the above technical problems, the present disclosure provides a non-stop detection system and a data processing method thereof to improve the accuracy of data matching.

[0006] In a first aspect, the present disclosure provides a data processing method for a non-stop detection system, comprising: When a vehicle is detected passing through the detection area, the laser point cloud data of the vehicle is acquired, and the spatiotemporal trajectory of the vehicle in the detection area is determined based on the time-continuous laser point cloud data after the vehicle passes through the detection area; Acquire vehicle image data of the vehicle, wherein the vehicle image data includes vehicle image information, and the vehicle image information includes detection time and detection coordinates; Based on the detection time and the detection coordinates in the vehicle image information, the vehicle image information is matched with the spatiotemporal trajectory to obtain a passing record of the vehicle.

[0007] In one embodiment, matching the vehicle image information with the spatiotemporal trajectory to obtain the vehicle passing record includes: Calculate the Euclidean distance between the space-time vector of the space-time trajectory of the vehicle and the space-time vector of the vehicle image information according to the time and coordinates in the space-time trajectory of the vehicle and the detection time and coordinates in the vehicle image information; When the Euclidean distance is less than a preset value, the spatiotemporal trajectory is matched with the vehicle image information to obtain a passing record of the vehicle.

[0008] In one embodiment, matching the vehicle image information with the spatiotemporal trajectory includes: According to the time and coordinates in the space-time trajectory of the vehicle, the space-time range of the vehicle contour is obtained; According to the detection time and the detection coordinates in the vehicle picture information, the spatiotemporal range of the vehicle picture information corresponding to the vehicle picture information is obtained; The degree of overlap between the spatiotemporal range of the vehicle outline and the spatiotemporal range of the vehicle image information is compared, and when the degree of overlap is greater than a preset degree of overlap threshold, the spatiotemporal trajectory is matched with the vehicle image information.

[0009] In one embodiment, the process of forming the space-time trajectory includes: When the vehicle passes through the detection area, the laser point cloud data of the vehicle is acquired in real time, the vehicle coordinates and the vehicle contour coordinates are obtained according to the laser point cloud data of the vehicle, and the vehicle coordinates and the vehicle contour coordinates are associated and stored in a time series to form a spatiotemporal trajectory of the vehicle.

[0010] In one embodiment, the process of obtaining the vehicle image data includes: Obtaining the vehicle coordinates and vehicle posture of the vehicle according to the acquired laser point cloud data of the vehicle; When it is determined according to the vehicle coordinates and the vehicle posture that the vehicle has traveled to a capture position, a picture acquisition device in a detection area is triggered to capture the vehicle to acquire the vehicle picture data.

[0011] In one embodiment, the data processing method further includes: When the vehicle travels to the weighing area corresponding to the non-stop detection system, the weighing data of the vehicle is obtained by using the weighing device in the weighing area, and the weighing information is obtained according to the weighing data of the vehicle.

[0012] In one embodiment, after obtaining the weighing data, the data processing method further includes: Calculate the Euclidean distance between the space-time vector of the space-time trajectory of the vehicle and the space-time vector of the weighing information according to the time and coordinates in the space-time trajectory of the vehicle and the detection time and detection coordinates in the vehicle weighing information; When the Euclidean distance is less than a preset value, the space-time trajectory is matched with the weighing information to obtain a passing record of the vehicle.

[0013] In one embodiment, the vehicle weighing information includes the position and time of the vehicle in the weighing area obtained by the weighing device; after obtaining the weighing data, the data processing method further includes: According to the time and coordinates in the space-time trajectory of the vehicle, the space-time range of the vehicle contour is obtained; The time and space range of the weighing information obtained according to the vehicle weighing information, the time and space range of the weighing information including the time range of the vehicle passing through the weighing area and the space range of the vehicle passing through the weighing area; The degree of overlap between the spatiotemporal range of the vehicle profile and the spatiotemporal range of the vehicle weighing information is compared, and when the degree of overlap is greater than a preset degree of overlap threshold, the spatiotemporal trajectory is matched with the vehicle weighing information.

[0014] In a second aspect, the present disclosure further provides a non-stop detection system, comprising: A laser radar, arranged above the detection area of ​​the non-stop detection system, for acquiring point cloud data of the vehicle in real time when the vehicle passes through the detection area; An image capture device is arranged above the detection area of ​​the non-stop detection system, and is used to capture the vehicle when the vehicle travels to the capture area corresponding to the non-stop detection system to obtain vehicle image data of the vehicle, wherein the vehicle image data includes vehicle image information, and the vehicle image information includes detection time and detection coordinates; A data processing device is respectively communicatively connected with the laser radar and the capture device, and is used to receive the point cloud data and the vehicle image data; and determines the spatiotemporal trajectory of the vehicle in the detection area based on the time-continuous laser point cloud data after the vehicle passes through the detection area, and matches the vehicle image information with the spatiotemporal trajectory based on the detection time and detection coordinates in the vehicle image information to obtain a passing record of the vehicle.

[0015] In one embodiment, matching the vehicle image information with the spatiotemporal trajectory to obtain the vehicle passing record includes: Calculate the Euclidean distance between the space-time vector of the space-time trajectory of the vehicle and the space-time vector of the vehicle image information according to the time and coordinates in the space-time trajectory of the vehicle and the detection time and coordinates in the vehicle image information; When the Euclidean distance is less than a preset value, the spatiotemporal trajectory is matched with the vehicle image information to obtain a passing record of the vehicle.

[0016] In one embodiment, matching the vehicle image information with the spatiotemporal trajectory includes: According to the time and coordinates in the space-time trajectory of the vehicle, the space-time range of the vehicle contour is obtained; According to the detection time and the detection coordinates in the vehicle picture information, the spatiotemporal range of the vehicle picture information corresponding to the vehicle picture information is obtained; The degree of overlap between the spatiotemporal range of the vehicle outline and the spatiotemporal range of the vehicle image information is compared, and when the degree of overlap is greater than a threshold value of the degree of overlap, the spatiotemporal trajectory is matched with the vehicle image information.

[0017] In one of the embodiments, the non-stop detection system further includes a weighing device, and the weighing device is arranged in a weighing area in the non-stop detection area; The weighing device is used to obtain the weighing data of the vehicle by using the weighing device in the weighing area when the vehicle travels to the weighing area corresponding to the non-stop detection system, and obtain weighing information according to the weighing data of the vehicle.

[0018] According to an embodiment of the present disclosure, the vehicle passing record is obtained by acquiring laser point cloud data of the vehicle, determining the spatiotemporal trajectory of the vehicle in the detection area based on the laser point cloud data that is continuous in time after the vehicle passes through the detection area, and acquiring vehicle image data of the vehicle, and matching the vehicle image information with the spatiotemporal trajectory based on the detection time and detection coordinates in the vehicle image information. It can be understood that this embodiment uses laser point cloud data to form a spatiotemporal trajectory corresponding to the vehicle contour, which can truly reflect the actual movement state of the vehicle in the detection area. Therefore, matching the spatiotemporal trajectory of the vehicle with the vehicle image information can improve the accuracy of data matching. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present disclosure will become readily understood. In the accompanying drawings, several embodiments of the present disclosure are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein: Figure 1 An exemplary schematic diagram of a current non-stop detection system is shown; Figure 2 A schematic diagram showing the current non-stop detection system image data acquisition position and weighing data acquisition position; Figure 3 A schematic diagram of the space-time trajectory of a vehicle and the location for obtaining image data according to the present embodiment is shown; Figure 4 A flow chart showing a data processing method according to the present embodiment; Figure 5 A schematic diagram showing the space-time range of the vehicle profile, the space-time range of the weighing information, and the space-time range of the picture information according to the present embodiment; Figure 6 A schematic diagram showing the time and space range of vehicle weighing information according to the present embodiment; Figure 7 A schematic diagram of the layout of the non-stop detection system applied according to this embodiment is shown. DETAILED DESCRIPTION

[0020] The principles and spirit of the present disclosure will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present disclosure, and are not intended to limit the scope of the present disclosure in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0021] The off-site non-stop detection system is an unattended system that uses non-stop monitoring technology to obtain vehicle model, vehicle weight, body size, and vehicle identity. After obtaining the vehicle information, it automatically analyzes and determines whether the vehicle is overloaded or has other violations. The vehicle violation information and related evidence chain are then transmitted to relevant law enforcement personnel for law enforcement. Therefore, the binding and matching of various types of vehicle information obtained through multiple devices in the off-site non-stop detection system (i.e., the process of forming an evidence chain for law enforcement) is particularly important.

[0022] Figure 1 FIG. 1 shows an exemplary schematic diagram of an existing off-site non-stop detection system. Figure 1As shown, a weighing device 2 is arranged on the roadbed along the road surface where the vehicle travels. The weighing device can be one or more of a narrow strip weighing sensor, a quartz weighing sensor, and a flat weighing sensor. Multiple rows of weighing devices are usually arranged in the same lane of the same system to form a weighing area on the road. Above the weighing area, a gantry 3 is often arranged, and other vehicle data acquisition devices 4 are arranged on the crossbeam of the gantry 3. The vehicle data acquisition device usually includes / but is not limited to: electronic devices such as snapshot cameras, video cameras, contour recognition devices, microwave antennas, etc. All weighing devices 2 and vehicle data acquisition devices 4 are connected to electronic instruments or data processing equipment in a wired or wireless manner.

[0023] When the vehicle 5 passes through the weighing device 2, the weighing device 2 obtains the weighing information of the vehicle and transmits it to the data processing device; when the vehicle enters the recognition range of the data acquisition device 4, the data acquisition device 4 obtains the vehicle data, including but not limited to picture information, video information, appearance profile information, etc., and transmits it to the data processing device. The data processing device matches the above information according to the acquisition time and lane number in the weighing information, picture information, video information, and profile information, and then transmits it to the back end and stores it.

[0024] Combination Figure 1 From the relevant description, it can be seen that the traditional off-site non-stop detection system has the following defects, because the vehicle's weighing information, picture information, video information, appearance outline information, etc. are obtained by different devices at different times, and then transmitted to the data processing equipment. There are differences in the acquisition time between different information of the same vehicle, and due to different vehicle models, different driving behaviors (constant speed, acceleration and deceleration, stop and go, etc.), and different driving paths (straight driving, S-shaped driving, lane changing, etc.), the acquisition time difference between different information will be further aggravated, which makes it very difficult for the data processing unit to match the above vehicle information. In addition, the non-stop detection system is often arranged on multiple lanes at the same time, such as Figure 2 As shown in the figure, when multiple vehicles pass by at the same time or a vehicle changes lanes, the acquisition time difference between various types of vehicle information will become larger, and the lane numbers of various types of vehicle information will be inconsistent, which will further reduce the vehicle information matching rate of the data processing device.

[0025] In view of this, in order to overcome the above-mentioned deficiencies in one or more aspects, in an embodiment of the present disclosure, a laser point cloud acquisition device, such as a multi-line laser radar, is added to the non-stop detection system, and a data processing method of the non-stop detection system is disclosed, including: when a vehicle is detected passing through a detection area, acquiring laser point cloud data of the vehicle, and determining the spatiotemporal trajectory of the vehicle in the detection area according to the time-continuous laser point cloud data after the vehicle passes through the detection area, such as Figure 3As shown. In specific implementation, the laser point cloud data of the vehicle passing through the detection area can be obtained through a 64-line / 128-line laser, and then the point cloud data of each vehicle can be obtained through clustering. After the coordinates of the vehicle laser point cloud data are converted and analyzed, the coordinates or position of the vehicle, the current time, the vehicle outline, the coordinates of the outline and other information can be obtained. After the vehicle passes through the detection area, the spatiotemporal trajectory of the vehicle in the detection area (including the corresponding position coordinates of the vehicle within the time period) can be obtained by trajectory matching / tracking of the point cloud data of each vehicle, and it can be matched with the candidate data composed of information obtained by one or more devices obtained through other settings. In this embodiment, the candidate data may be one or more of the acquired vehicle image data, vehicle weighing data, etc.

[0026] In one embodiment, if the candidate data includes vehicle image data, then Figure 4 As shown, the method includes: Step S401, when a vehicle is detected passing through a detection area, the laser point cloud data of the vehicle is acquired, and the spatiotemporal trajectory of the vehicle in the detection area is determined based on the time-continuous laser point cloud data after the vehicle passes through the detection area.

[0027] Specifically, a density clustering algorithm or a deep network model can be used to identify the laser point cloud data corresponding to the vehicle from each frame of point cloud data; then, the Hungarian matching algorithm is used to match the point cloud data corresponding to the identified vehicle with the vehicle in the detection area, and the Kalman filter algorithm is used to predict the next moment position of the vehicle in the detection area, thereby tracking the vehicle and continuously obtaining point cloud data corresponding to the same vehicle.

[0028] Step S402, obtaining vehicle image data of the vehicle, wherein the vehicle image data includes vehicle image information, and the vehicle image information includes detection time and detection coordinates.

[0029] Specifically, the process of acquiring the vehicle image data may include: obtaining the vehicle coordinates and vehicle posture of the vehicle based on the acquired laser point cloud data of the vehicle; when it is determined based on the vehicle coordinates and the vehicle posture that the vehicle has traveled to the capture position, triggering the image acquisition device in the detection area to capture the vehicle to obtain the vehicle image data.

[0030] Step S403: Based on the detection time and detection coordinates in the vehicle image information, the vehicle image information is matched with the spatiotemporal trajectory to obtain a passing record of the vehicle.

[0031] That is, in this embodiment, when a vehicle passes through the detection area, the vehicle image data of the vehicle is obtained, and the vehicle image data includes vehicle image information, and the vehicle image information includes the detection time and detection coordinates. In specific implementation, the vehicle image data is automatically acquired by the capture camera when the vehicle enters the capture area, and then the vehicle license plate, detection time, and the coordinates of the vehicle in the lane are obtained through image analysis technology, such as deep learning technology (such as VGG, ResNet neural network). In actual operation, the coordinates of the vehicle in the lane can be obtained by analyzing the position of the characteristic part of the vehicle (such as the front or rear of the vehicle) in the picture, and then corresponding to the actual lane coordinates (the focal length and direction of the capture camera are basically fixed).

[0032] Finally, the vehicle image information is matched with the spatiotemporal trajectory to obtain the vehicle passing record. In specific implementation, after obtaining the vehicle image information and the spatiotemporal trajectory, the data processing device can intercept the close spatiotemporal trajectory data in the vehicle spatiotemporal trajectory according to the time information in the vehicle image information, and then further complete the information matching by comparing the coordinate information in the image information with the coordinate information in the intercepted spatiotemporal trajectory data.

[0033] In another embodiment, when a vehicle passes through the detection area, the laser point cloud data of the vehicle is obtained by the laser point cloud device, and the front image data of the vehicle is obtained by the snapshot camera. Then, the position coordinates and time of the front of the vehicle are obtained by analyzing the laser point cloud data of the vehicle, and the front feature vector of the laser point cloud data is obtained. After the vehicle passes, all the head feature vectors of the vehicle in the detection area are stored in time series, and the spatiotemporal trajectory of the vehicle is obtained. After analyzing the front image data, the front position coordinates and time of the vehicle image are obtained, and the feature vector of the image is obtained. Finally, the Euclidean distances between the feature vectors of the image and the feature vectors in the spatiotemporal trajectory are calculated respectively. If a certain number of Euclidean distances are less than a threshold, it is considered that the vehicle image information and the vehicle spatiotemporal trajectory are matched. The specific formula is as follows;

[0034] In another embodiment, the data processing method of the non-stop detection system further includes: When the vehicle travels to the weighing area corresponding to the non-stop detection system, the weighing data of the vehicle is obtained by using the weighing device in the weighing area, and the weighing information is obtained according to the weighing data of the vehicle.

[0035] The weighing information obtained by the weighing device is also matched with other data to the same vehicle. Therefore, after obtaining the weighing data, the data processing method further includes: Calculate the Euclidean distance between the space-time vector of the space-time trajectory of the vehicle and the space-time vector of the weighing information according to the time and coordinates in the space-time trajectory of the vehicle and the detection time and detection coordinates in the vehicle weighing information; When the Euclidean distance is less than a preset value, the space-time trajectory is matched with the weighing information to obtain a passing record of the vehicle.

[0036] Specifically, when a vehicle passes through the detection area, the laser point cloud device obtains the laser point cloud data of the vehicle, the snapshot camera obtains the front image data of the vehicle, and the weighing device obtains the weighing data of the vehicle. After analyzing the laser point cloud data, the position coordinates and time of the front of the vehicle are obtained, and the feature vector of the front of the vehicle is obtained. After analyzing the front image data, the feature vector of the front image is obtained. After analyzing the weighing data of the weighing device, the vehicle model, vehicle weight, and vehicle weighing feature vector are obtained. ,in The median value of the weighing data acquisition time, is the position coordinate of the vehicle when the weighing data is obtained. Similarly, the Euclidean distance between the weighing feature vector and the point cloud spatiotemporal trajectory can be calculated, and when it is less than the threshold, it is considered that the match is completed.

[0037] In another embodiment of the present disclosure, in the data processing method of the non-stop detection system, the step of matching the vehicle image information with the spatiotemporal trajectory includes: According to the time and coordinates in the space-time trajectory of the vehicle, the space-time range of the vehicle contour is obtained; According to the detection time and the detection coordinates in the vehicle picture information, the spatiotemporal range of the vehicle picture information corresponding to the vehicle picture information is obtained; The degree of overlap between the spatiotemporal range of the vehicle outline and the spatiotemporal range of the vehicle image information is compared, and when the degree of overlap is greater than a preset degree of overlap threshold, the spatiotemporal trajectory is matched with the vehicle image information.

[0038] like Figure 5 As shown in the figure, when a vehicle passes through the detection area, the laser point cloud data of the vehicle is obtained. After the vehicle passes, all the laser point cloud data generated by the vehicle in the area are converted into the vehicle's spatiotemporal trajectory, and the spatiotemporal range of the vehicle contour is further obtained. The spatiotemporal range of the vehicle contour shows the spatiotemporal range generated by the vehicle contour when it travels in the area. Compared with the vehicle spatiotemporal trajectory (such as Figure 3 As shown in Figure 2), the vehicle contour time and space range can more comprehensively represent the time and space range occupied by the vehicle when driving in the area, further improving the matching accuracy. In specific implementation, the vehicle appearance contour can be obtained based on the laser point cloud data of the vehicle at each moment, and then the vehicle appearance contour can be projected into the actual lane space based on the time and space coordinates in the vehicle's time and space trajectory to form the vehicle contour time and space range, as shown in Figure 2. Figure 5 shown.

[0039] When a vehicle passes through the detection area, the image data of the vehicle is obtained, such as obtaining a front photo of the vehicle through a snapshot camera. Figure 5 middle The vehicle's weighing data is obtained through weighing equipment, such as Figure 5 middle The spatial range is shown. The vehicle image data is then converted into vehicle image information (vehicle head image information), and the spatiotemporal range of the vehicle head image information is calculated. For example, the captured image information of the vehicle includes the time value of the captured image and the coordinates of the vehicle head in the captured image within the detection area. Then, the image contour and the area occupied by the vehicle head image are identified using image technology based on the vehicle head image, and then projected into the space of the detection area to determine the spatiotemporal range of the vehicle head image information. Then, the degree of overlap between the vehicle contour spatiotemporal range and the vehicle image information spatiotemporal range is compared, and when the degree of overlap is greater than a preset overlap threshold, the spatiotemporal trajectory is matched with the vehicle image information. It can be immediately noted that the preset overlap threshold can be set according to needs or experience.

[0040] Similarly, in another embodiment, the vehicle weighing information includes the position and time of the vehicle in the weighing area obtained by the weighing device; after obtaining the weighing data, the data processing method further includes: According to the time and coordinates in the space-time trajectory of the vehicle, the space-time range of the vehicle contour is obtained; The time and space range of the weighing information obtained according to the vehicle weighing information, the time and space range of the weighing information including the time range of the vehicle passing through the weighing area and the space range of the vehicle passing through the weighing area; The degree of overlap between the spatiotemporal range of the vehicle profile and the spatiotemporal range of the vehicle weighing information is compared, and when the degree of overlap is greater than a preset degree of overlap threshold, the spatiotemporal trajectory is matched with the vehicle weighing information.

[0041] Please continue to see Figure 5 , when the vehicle passes through the detection area, the vehicle's weighing data is obtained, the vehicle's weighing information is determined based on the vehicle's weighing data, and then the vehicle's weighing information is determined based on the vehicle's weighing information. The time range triggers the No. 1 weighing device in lane 1. The weighing device can identify the position of the left and right tires of the vehicle, and thus obtain the horizontal lateral space range of the vehicle. According to the information of the vehicle's multi-axle trigger weighing equipment, the horizontal and longitudinal spatial range of the vehicle can also be obtained. ,like Figure 6Finally, the spatiotemporal range of the vehicle laser point cloud data is compared with the spatiotemporal range of the weighing data. If the ratio of the spatiotemporal range of the vehicle weighing data exceeds the preset threshold, the match is successful. It is understandable that the threshold value corresponding to the spatiotemporal range of the vehicle contour overlap with the spatiotemporal range of the vehicle weighing information and the threshold value corresponding to the spatiotemporal range of the vehicle contour overlap with the spatiotemporal range of the vehicle image information may be the same or different.

[0042] Based on the same inventive concept, the present disclosure also provides a non-stop detection system, see Figure 7 , including: a laser radar 101, a capture device and a data processing device (not shown).

[0043] The laser radar 101 is arranged above the detection area of ​​the off-site detection system and is used to obtain laser point cloud data of the vehicle. In specific implementation, one or more 64-line / 128-line laser radars can be used to obtain vehicle point cloud data, and then complete vehicle point cloud data is obtained through data clustering, segmentation, and fusion processing.

[0044] The capture device is arranged above the detection area of ​​the off-site detection system. When the vehicle passes through the capture area, the vehicle is captured to obtain the vehicle image information of the vehicle. The capture device can be a capture camera, and the vehicle image information is obtained through the capture camera. Specifically, the vehicle image information includes the head image information, panoramic image information, and tail image information of the above-mentioned vehicle. The image capture device can include: a vehicle head image capture device 1021, a vehicle panoramic image capture device 1022, and a vehicle tail image capture device 1023. Among them, the vehicle head image capture device is used to collect the above-mentioned head image information; the vehicle panoramic image capture device is used to collect the above-mentioned panoramic image information, and the vehicle tail image capture device is used to collect the above-mentioned tail image information. The vehicle head image capture device 1021, the vehicle panoramic image capture device 1022, and the vehicle tail image capture device 1023 can respectively collect the vehicle head image information, the panoramic image information, and the tail image information, so as to realize multi-angle image shooting and comprehensively obtain the vehicle image information.

[0045] The data processing device 104 is connected to the laser radar, the weighing device and the snapshot device, and is used to receive the laser point cloud information, the weighing information and the snapshot image information. The vehicle's driving space-time trajectory is obtained according to the laser point cloud data, and data matching is performed according to the vehicle's driving space-time trajectory, the vehicle weighing information and the snapshot image information.

[0046] In yet another embodiment, matching the vehicle image information with the spatiotemporal trajectory to obtain a passing record of the vehicle includes: Calculate the Euclidean distance between the space-time vector of the space-time trajectory of the vehicle and the space-time vector of the vehicle image information according to the time and coordinates in the space-time trajectory of the vehicle and the detection time and coordinates in the vehicle image information; When the Euclidean distance is less than a preset value, the spatiotemporal trajectory is matched with the vehicle image information to obtain a passing record of the vehicle.

[0047] In yet another embodiment, matching the vehicle image information with the spatiotemporal trajectory includes: According to the time and coordinates in the space-time trajectory of the vehicle, the space-time range of the vehicle contour is obtained; According to the detection time and the detection coordinates in the vehicle picture information, the spatiotemporal range of the vehicle picture information corresponding to the vehicle picture information is obtained; The degree of overlap between the spatiotemporal range of the vehicle outline and the spatiotemporal range of the vehicle image information is compared, and when the degree of overlap is greater than a threshold value of the degree of overlap, the spatiotemporal trajectory is matched with the vehicle image information.

[0048] In another embodiment, the non-stop detection system also includes a weighing device 103, which is arranged in a weighing area in the non-stop detection area; the weighing device is used to obtain the weighing data of the vehicle by using the weighing device in the weighing area when the vehicle travels to the weighing area corresponding to the non-stop detection system, and obtain weighing information based on the weighing data of the vehicle.

[0049] Specifically, the weighing device 103 is arranged on the roadbed of the detection area road, and is used to obtain the weighing information of the vehicles passing thereon. In the specific implementation, the weighing device can select one or more of a narrow bar weighing sensor, a quartz weighing sensor, and a flat weighing sensor, and all weighing devices transmit weighing data to the data processing device via wireless or limited communication, so that the weighing information can be obtained according to the weighing data of the vehicle.

[0050] In another embodiment, after acquiring the weighing data, the data processing device is used to execute: Calculate the Euclidean distance between the space-time vector of the space-time trajectory of the vehicle and the space-time vector of the weighing information according to the time and coordinates in the space-time trajectory of the vehicle and the detection time and detection coordinates in the vehicle weighing information; When the Euclidean distance is less than a preset value, the space-time trajectory is matched with the weighing information to obtain a passing record of the vehicle.

[0051] In another embodiment, when the vehicle weighing information includes the position and time of the vehicle in the weighing area obtained by the weighing device; after obtaining the weighing data, the data processing device is used to specifically perform: According to the time and coordinates in the space-time trajectory of the vehicle, the space-time range of the vehicle contour is obtained; The time and space range of the weighing information obtained according to the vehicle weighing information, the time and space range of the weighing information including the time range of the vehicle passing through the weighing area and the space range of the vehicle passing through the weighing area; The degree of overlap between the spatiotemporal range of the vehicle profile and the spatiotemporal range of the vehicle weighing information is compared, and when the degree of overlap is greater than a preset degree of overlap threshold, the spatiotemporal trajectory is matched with the vehicle weighing information.

[0052] It should be noted that although the operations of the method of the present invention are described in a particular order in the accompanying drawings, this does not require or imply that the operations must be performed in this particular order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flow chart can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0053] It should be understood that the terms "first", "second", "third", "fourth", etc. in the claims, specifications and drawings of the present disclosure are used to distinguish different objects rather than to describe a specific order. The terms "include" and "comprise" used in the specifications and claims of the present disclosure indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0054] It should also be understood that the terms used in this disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure. As used in this disclosure and claims, the singular forms of "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in this disclosure and claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations.

[0055] As used in this specification and claims, the term "if" can be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrases "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.

[0056] Although multiple embodiments of the present disclosure have been shown and described herein, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art may think of many changes, modifications, and alternatives without departing from the thought and spirit of the present disclosure. It should be understood that in the process of practicing the present disclosure, various alternatives to the embodiments of the present disclosure described herein may be adopted. The attached claims are intended to define the scope of protection of the present disclosure, and therefore cover equivalents or alternatives within the scope of these claims.

Claims

1. A data processing method for a non-stop detection system, It is characterized in that include: When a vehicle is detected passing through the detection area, the laser point cloud data of the vehicle is acquired, and the spatiotemporal trajectory of the vehicle in the detection area is determined based on the time-continuous laser point cloud data after the vehicle passes through the detection area; Acquire vehicle image data of the vehicle, wherein the vehicle image data includes vehicle image information, and the vehicle image information includes detection time and detection coordinates; Based on the detection time and the detection coordinates in the vehicle image information, the vehicle image information is matched with the spatiotemporal trajectory to obtain a passing record of the vehicle.

2. The data processing method according to claim 1, It is characterized in that Matching the vehicle image information with the spatiotemporal trajectory to obtain a passing record of the vehicle includes: Calculate the Euclidean distance between the space-time vector of the space-time trajectory of the vehicle and the space-time vector of the vehicle image information according to the time and coordinates in the space-time trajectory of the vehicle and the detection time and coordinates in the vehicle image information; When the Euclidean distance is less than a preset value, the spatiotemporal trajectory is matched with the vehicle image information to obtain a passing record of the vehicle.

3. The data processing method according to claim 1, It is characterized in that Matching the vehicle image information with the spatiotemporal trajectory includes: According to the time and coordinates in the space-time trajectory of the vehicle, the space-time range of the vehicle contour is obtained; According to the detection time and the detection coordinates in the vehicle picture information, the spatiotemporal range of the vehicle picture information corresponding to the vehicle picture information is obtained; The degree of overlap between the spatiotemporal range of the vehicle outline and the spatiotemporal range of the vehicle image information is compared, and when the degree of overlap is greater than a preset degree of overlap threshold, the spatiotemporal trajectory is matched with the vehicle image information.

4. The data processing method according to claim 1, It is characterized in that The process of forming the space-time trajectory includes: When the vehicle passes through the detection area, the laser point cloud data of the vehicle is acquired in real time, the vehicle coordinates and the vehicle contour coordinates are obtained according to the laser point cloud data of the vehicle, and the vehicle coordinates and the vehicle contour coordinates are associated and stored in a time series to form a spatiotemporal trajectory of the vehicle.

5. The data processing method according to claim 1, It is characterized in that The process of obtaining the vehicle image data includes: Obtaining the vehicle coordinates and vehicle posture of the vehicle according to the acquired laser point cloud data of the vehicle; When it is determined according to the vehicle coordinates and the vehicle posture that the vehicle has traveled to a capture position, a picture acquisition device in a detection area is triggered to capture the vehicle to acquire the vehicle picture data.

6. The data processing method according to claim 1, It is characterized in that Also includes: When the vehicle travels to the weighing area corresponding to the non-stop detection system, the weighing data of the vehicle is obtained by using the weighing device in the weighing area, and the weighing information is obtained according to the weighing data of the vehicle.

7. The data processing method according to claim 6, It is characterized in that After obtaining the weighing data, the data processing method further includes: Calculate the Euclidean distance between the space-time vector of the space-time trajectory of the vehicle and the space-time vector of the weighing information according to the time and coordinates in the space-time trajectory of the vehicle and the detection time and detection coordinates in the vehicle weighing information; When the Euclidean distance is less than a preset value, the space-time trajectory is matched with the weighing information to obtain a passing record of the vehicle.

8. The data processing method according to claim 6, It is characterized in that The vehicle weighing information includes the position and time of the vehicle in the weighing area obtained by the weighing device; after obtaining the weighing data, the data processing method further includes: According to the time and coordinates in the space-time trajectory of the vehicle, the space-time range of the vehicle contour is obtained; The time and space range of the weighing information obtained according to the vehicle weighing information, the time and space range of the weighing information including the time range of the vehicle passing through the weighing area and the space range of the vehicle passing through the weighing area; The degree of overlap between the spatiotemporal range of the vehicle profile and the spatiotemporal range of the vehicle weighing information is compared, and when the degree of overlap is greater than a preset degree of overlap threshold, the spatiotemporal trajectory is matched with the vehicle weighing information.

9. A non-stop detection system, It is characterized in that include: A laser radar, arranged above the detection area of ​​the non-stop detection system, for acquiring point cloud data of the vehicle in real time when the vehicle passes through the detection area; An image capture device is arranged above the detection area of ​​the non-stop detection system, and is used to capture the vehicle when the vehicle travels to the capture area corresponding to the non-stop detection system to obtain vehicle image data of the vehicle, wherein the vehicle image data includes vehicle image information, and the vehicle image information includes detection time and detection coordinates; A data processing device, which is in communication with the laser radar and the capture device, and is used to receive the point cloud data and the vehicle image data; Furthermore, the spatiotemporal trajectory of the vehicle in the detection area is determined based on the time-continuous laser point cloud data after the vehicle passes through the detection area, and based on the detection time and detection coordinates in the vehicle image information, the vehicle image information is matched with the spatiotemporal trajectory to obtain the vehicle passing record.

10. The non-stop detection system according to claim 9, It is characterized in that Matching the vehicle image information with the spatiotemporal trajectory to obtain a passing record of the vehicle includes: Calculate the Euclidean distance between the space-time vector of the space-time trajectory of the vehicle and the space-time vector of the vehicle image information according to the time and coordinates in the space-time trajectory of the vehicle and the detection time and coordinates in the vehicle image information; When the Euclidean distance is less than a preset value, the spatiotemporal trajectory is matched with the vehicle image information to obtain a passing record of the vehicle.

11. The non-stop detection system according to claim 9, It is characterized in that Matching the vehicle image information with the spatiotemporal trajectory includes: According to the time and coordinates in the space-time trajectory of the vehicle, the space-time range of the vehicle contour is obtained; According to the detection time and the detection coordinates in the vehicle picture information, the spatiotemporal range of the vehicle picture information corresponding to the vehicle picture information is obtained; The degree of overlap between the spatiotemporal range of the vehicle outline and the spatiotemporal range of the vehicle image information is compared, and when the degree of overlap is greater than a threshold value of the degree of overlap, the spatiotemporal trajectory is matched with the vehicle image information.

12. The non-stop detection system according to claim 9, It is characterized in that It also includes a weighing device, which is arranged in a weighing area in the non-stop detection area; The weighing device is used to obtain the weighing data of the vehicle by using the weighing device in the weighing area when the vehicle travels to the weighing area corresponding to the non-stop detection system, and obtain weighing information according to the weighing data of the vehicle.