Vehicle information detection method and system, storage medium and electronic device

Abstract

The application discloses a vehicle information detection method and system, a storage medium and an electronic device. The method comprises the following steps: obtaining a group of scanning frames obtained by transverse scanning of a transverse scanning component, wherein the group of scanning frames comprises a vehicle end frame of a target vehicle; determining a first vehicle head distance of the target vehicle according to a first vehicle head frame of the target vehicle scanned by a multi-line scanning component, wherein the first vehicle head distance is the distance between the vehicle head of the target vehicle and the multi-line scanning component in the driving direction; determining a target displacement according to a first frame number and a reference displacement of the target vehicle, wherein the first frame number is the number of scanning frames in the group of scanning frames, the scanning time of which is between the scanning time of the first vehicle head frame and the scanning time of the vehicle end frame, and the target displacement is the vehicle displacement of the target vehicle between the scanning time of the first vehicle head frame and the scanning time of the vehicle end frame; and determining the vehicle length of the target vehicle according to the first vehicle head distance, a preset component distance and the target displacement.

Description

Technical Field

[0001] This application relates to the field of vehicle identification, and more specifically, to a vehicle information detection method and system, a storage medium, and an electronic device. Background Technology

[0002] To reduce the safety hazards caused by overloaded freight vehicles, vehicle information can be acquired, for example, by using a vehicle contour recognition system to detect the vehicle's contour information. This system can use a single-line LiDAR to detect the vehicle's width, height, length, and other information to obtain complete vehicle contour information, thereby determining whether the vehicle is overloaded.

[0003] In related technologies, longitudinal scanning components typically scan along the vehicle's direction of travel to accurately measure vehicle length. However, when a moving vehicle is not directly beneath the scanning range of the length-measuring laser, accurate length measurement becomes difficult, or even impossible. When using multi-line scanning components to measure vehicle length, the scanning angle is limited, and in situations with multiple vehicles traveling side-by-side, obstructions can cause the loss of information about parts of the vehicle's body, affecting the overall accuracy of the vehicle's outline measurement.

[0004] Therefore, it is evident that the vehicle information detection methods in the relevant technologies suffer from the technical problem of low accuracy due to the lack of vehicle information. Summary of the Invention

[0005] This application provides a vehicle information detection method and system, storage medium, and electronic device to at least solve the technical problem of low accuracy in vehicle information detection due to missing vehicle information in related technologies.

[0006] According to one aspect of the embodiments of this application, a vehicle information detection method is provided, comprising: acquiring a set of scan frames obtained by a lateral scanning component performing a lateral scan, wherein the set of scan frames includes a vehicle tail frame of a target vehicle, the target vehicle is traveling in a target lane, and the vehicle tail frame is the last frame of the target vehicle in the set of scan frames; determining a first headway distance of the target vehicle based on a first headway frame of the target vehicle scanned by a multi-line scanning component, wherein the multi-line scanning component is located in front of the lateral scanning component in the driving direction of the target lane, and the first headway distance is the distance between the head of the target vehicle and the multi-line scanning component in the driving direction; and determining a target displacement based on a first frame number and a reference displacement of the target vehicle. The first frame number is the number of scan frames included in a set of reference frames. The set of reference frames includes scan frames whose scanning time is between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. The reference displacement is the vehicle displacement of the target vehicle between two adjacent frames in the set of scan frames including the vehicle rear frame and the set of reference frames. The target displacement is the vehicle displacement of the target vehicle between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. The vehicle length of the target vehicle is determined according to the first vehicle front distance, the preset component distance, and the target displacement. The preset component distance is the distance between the lateral scanning component and the multi-line scanning component in the driving direction, which is preset.

[0007] According to another aspect of the embodiments of this application, a vehicle information detection system is also provided, comprising: a lateral scanning component for lateral scanning of a passing target vehicle; a multi-line scanning component located in front of the lateral scanning component in the driving direction of the target vehicle for multi-line scanning of the target vehicle; and a data processing component for acquiring a set of scan frames obtained by the lateral scanning component, wherein the set of scan frames includes a vehicle tail frame of the target vehicle, the target vehicle is traveling in a target lane, and the vehicle tail frame is the last frame of the target vehicle in the set of scan frames; and determining a first headway distance of the target vehicle based on a first headway frame of the target vehicle scanned by the multi-line scanning component, wherein the first headway distance is the distance between the headway of the target vehicle and the multi-line scanning component in the driving direction. The target displacement is determined based on the first frame number and the reference displacement of the target vehicle. The first frame number is the number of scan frames included in a set of reference frames. The set of reference frames includes scan frames whose scanning time is between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. The reference displacement is the vehicle displacement of the target vehicle between two adjacent frames in the set of scan frames containing the vehicle rear frame and the set of reference frames. The target displacement is the vehicle displacement of the target vehicle between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. The vehicle length of the target vehicle is determined based on the first vehicle front distance, the preset component distance, and the target displacement. The preset component distance is the pre-set distance between the lateral scanning component and the multi-line scanning component in the driving direction.

[0008] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer-readable storage medium, and the computer program is configured to execute the above-described vehicle information detection method when it is run.

[0009] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the vehicle information detection method described above through the computer program.

[0010] In this embodiment, a method for vehicle length detection is employed, combining a lateral scanning component with a multi-line scanning component. Lateral scanning components and multi-line scanning components positioned in front of the lateral scanning components in the direction of travel are respectively installed on the target road. The target road can have multiple lanes, each allowing vehicles to pass. The system determines the moment when the rear of the vehicle passes the scanning surface of the lateral scanning component (at which point the position of the rear of the vehicle is consistent with the scanning surface of the lateral scanning component). Based on the number of scanning frames between the moment of the end and a certain moment, and the displacement of the vehicle between two adjacent frames, the displacement of the vehicle between the moment of the end and a certain moment is determined, which is equivalent to determining the position of the rear of the vehicle at a certain moment. The position of the front of the vehicle at that certain moment can be determined by the multi-line scanning component. Therefore, based on the positions of the rear and front of the vehicle at the same moment, since the lateral scanning component is combined with the multi-line scanning component to measure the vehicle length, the requirements of the longitudinal scanning component on the vehicle's driving position can be reduced. At the same time, the limitation of the scanning angle of the multi-line scanning component can be reduced. This avoids the impact of missing vehicle body information due to vehicle occlusion on the accuracy of vehicle length detection, thereby improving the technical effect of improving the accuracy of vehicle information detection. This solves the technical problem of low accuracy of vehicle information detection due to missing vehicle information in related technologies. Attached Figure Description

[0011] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0012] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram of the hardware environment of an optional vehicle information detection method according to an embodiment of this application;

[0014] Figure 2 This is a flowchart illustrating an optional vehicle information detection method according to an embodiment of this application;

[0015] Figure 3 This is a schematic diagram of an optional vehicle contour recognition system according to an embodiment of this application;

[0016] Figure 4 This is a schematic diagram of an optional vehicle information detection method according to an embodiment of this application;

[0017] Figure 5 This is a structural block diagram of an optional electronic device according to an embodiment of this application. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0019] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0020] According to one aspect of the embodiments of this application, a vehicle information detection method is provided. Optionally, in this embodiment, the above-described vehicle information detection method can be applied to, for example... Figure 1 The hardware environment shown includes detection component 102 and server 104. For example... Figure 1 As shown, server 104 is connected to detection component 102 via a network and can be used to identify vehicle information based on the detection data of detection component 102, such as identifying the outline information of a vehicle. A database can be set up on the server or independently to provide data storage services for server 104. Here, both detection component 102 and server 104 can belong to a vehicle outline recognition system.

[0021] The aforementioned network may include, but is not limited to, at least one of the following: wired network, wireless network. The aforementioned wired network may include, but is not limited to, at least one of the following: wide area network, metropolitan area network, local area network; the aforementioned wireless network may include, but is not limited to, at least one of the following: Wi-Fi (Wireless Fidelity), Bluetooth. The detection component 102 may include a lateral scanning component and a multi-line scanning component, wherein the lateral scanning component may be, but is not limited to, a laser sensor, such as a single-line lidar (a single-line laser for laser ranging); and the multi-line scanning component may be, but is not limited to, a multi-line laser sensor, such as a multi-line lidar (a multi-line laser for laser ranging).

[0022] The vehicle information detection method of this embodiment can be executed by server 104, by detection component 102, or by both server 104 and detection component 102. Taking the execution of the vehicle information detection method of this embodiment by server 104 as an example... Figure 2 This is a flowchart illustrating an optional vehicle information detection method according to an embodiment of this application, as shown below. Figure 2 As shown, the process of this method may include the following steps:

[0023] Step S202: Obtain a set of scan frames obtained by the lateral scanning component performing lateral scanning. The set of scan frames includes the vehicle tail frame of the target vehicle. The target vehicle is driving on the target lane. The vehicle tail frame is the last frame of the target vehicle scanned by the lateral scanning component in the set of scan frames.

[0024] The vehicle information detection method in this embodiment can be applied to scenarios where vehicle contour recognition is performed on passing vehicles within a preset area, and can be applied to a vehicle contour recognition system. The preset area can be a highway or other area requiring vehicle contour recognition, and may include multiple lanes. The vehicle contour can include vehicle length, vehicle width, and vehicle height. The vehicle information detection method described above can be applied to the detection of vehicle length. By detecting the vehicle length and combining it with vehicle width and height detected through other methods, and further combining other vehicle contour information, complete vehicle contour information can be determined, thereby determining whether the vehicle exceeds limits, such as being too wide or too high. In some examples of this embodiment, a vehicle contour recognition system applied to a highway is used as an example for illustration.

[0025] Here, the vehicle contour recognition system may use a dynamic vehicle contour measurement method, which can calculate vehicle contour information such as length, width, and height during vehicle movement. In off-site law enforcement, vehicle contour information helps to identify overloaded vehicles, thereby ensuring vehicle driving safety.

[0026] A vehicle contour recognition system may include detection components for detecting vehicle contour information, such as lateral scanning components for detecting vehicle width and height. Since laser point cloud information can reflect the vehicle's position in real time during movement, it is often used for dynamic vehicle contour measurement. The aforementioned lateral scanning component can be a laser sensor (e.g., a single-line laser). The laser sensor uses laser light as a signal source, receives the laser light reflected back by an object, and thus calculates the distance. Lateral scanning components can also be microwave sensors, infrared sensors, ultrasonic sensors, etc. In this embodiment, a single-line laser is used as an example for explanation.

[0027] In this embodiment, the lateral scanning component can be located on a support structure set on the target road. The support structure can be a support structure that spans the target road, such as a gantry frame bracket (i.e., a gantry frame), an L-shaped bracket, etc. The target road can contain n lanes (N is the number of lanes). Correspondingly, the number of lateral scanning components can be n+1, that is, the installation distance between two adjacent lateral scanning components is one lane, its scanning direction is perpendicular to the driving direction, and the scanning surfaces of the n+1 lateral scanning components are located on the same vertical plane, where n is a positive integer greater than or equal to 1.

[0028] Optionally, the lateral scanning components can be connected to the same controller's host computer circuit to form a multi-motor control system. Based on the initial state feedback from each lateral scanning component, the controller outputs the corresponding synchronization compensation to each motor through the coordination of the synchronization control structure and algorithm, ensuring that the lateral scanning components have the same initial scanning angle and speed.

[0029] For example, taking a single-line laser (or laser rangefinder) as the lateral scanning component, the single-line laser S i (i = 1, 2, ...) can be installed on the same gantry (installation height h can be 6-7m), S i A single line can be used, with the same frequency and not less than 25 Hz, a scanning angle of 180°, and its scanning direction perpendicular to the direction of travel, and two adjacent lasers S i Installation spacing d i (i = 1, 2, ...) One lane, multiple S i The scanning planes are located on the same vertical plane. i Connected to the same host computer circuit, a multi-motor control system is formed. Based on the initial state feedback from each laser, the controller, through the coordination of a synchronous control structure and algorithm, outputs corresponding synchronization compensation to each motor to ensure S i They have the same initial scan angle and rotation speed.

[0030] For a given lane, a lateral scan can be performed using its corresponding lateral scanning component. This scanning process can be continuous or triggered when a vehicle (e.g., a target vehicle) is detected approaching the support structure where the lateral scanning component is located; this embodiment does not impose any limitations on this. Here, since the scanning angle of the lateral scanning component is not strictly within its corresponding lane, data from other lanes can also be scanned using lateral scanning components corresponding to other lanes.

[0031] The lateral scanning component can perform lateral scanning, obtaining a set of scan frames. This set of scan frames can contain frames with vehicle data or frames without vehicle scan data. During the lateral scanning process, the target vehicle can travel in the target lane of the target road. As the vehicle travels across the scanning surface of the lateral scanning component, the scan frames scanned by the lateral scanning component can contain the target vehicle's vehicle data. Since the scanning surface of the lateral scanning component is fixed, while the target vehicle is moving, the set of scan frames can contain vehicle frames scanned at different times, showing different positions of the target vehicle (e.g., the front, rear, etc.). In chronological order of scanning time, the lateral scanning component can first scan the target vehicle's start frame, then scan the target vehicle's body frames, and finally scan the target vehicle's end frame. Here, the end frame can be the last frame of the target vehicle in the set of scan frames (i.e., the scan frame containing the target vehicle's vehicle data and scanned latest).

[0032] Step S204: Determine the first frontal distance of the target vehicle based on the first frontal frame of the target vehicle scanned by the multi-line scanning component.

[0033] In related technologies, vehicle outline measurement can be performed using a single-line laser. When measuring vehicle outline, a length-measuring laser (a type of single-line laser) typically scans along the vehicle's direction of travel to accurately measure the vehicle length. However, when the vehicle is not directly beneath the length-measuring laser's scanning range during travel, a length-measuring blind zone exists, making accurate length measurement difficult or even impossible. This prevents true outline measurement during free-flowing vehicle travel. The traditional solution is to add a length-measuring laser, but this increases costs.

[0034] However, if a multi-line laser-based contour measurement method is used, the scanning angle of the multi-line laser will be limited. When multiple vehicles are traveling in parallel, occlusion will cause the loss of some vehicle body information, thus affecting the overall contour measurement accuracy. Therefore, relying solely on multi-line lasers to calculate vehicle contour information is insufficient to solve the problem of inaccurate contour measurement caused by blind spots due to occlusion when multiple vehicles are traveling in parallel.

[0035] To at least address some of the aforementioned problems, in this embodiment, on a road with multiple lanes, in the direction of travel of the target lane (which could also be the direction of travel of one or more other lanes), another support structure can be installed in front of the support structure where the lateral scanning component is located. A multi-line scanning component can be installed on this support structure, and the number of multi-line scanning components can be one or more. Here, the multi-line scanning component can be a multi-line laser with at least 32 lines. Its number and installation angle can be determined based on the number and width of the lanes, ensuring that all vehicles can be scanned. The multi-line laser can have multiple emission sources. By distributing these multiple emission sources vertically and utilizing the rotation of a motor to form multiple scanning beams, multiple laser beams can be emitted and received simultaneously.

[0036] For example, taking a transverse scanning component as a single-line laser and a multi-line scanning component as a multi-line laser as an example, the single-line laser S i (i = 1, 2, ...), Multi-line laser M i The installation method of (i = 1, 2, ...) in the road is as follows: Figure 3 As shown. Single-line laser S i The setup method is similar to that described above, and it is installed in Figure 3 On the gantry in the middle. Multi-line laser M i Same frequency and not lower than 10Hz, installed in Figure 3 The gantry is mounted on gantry two. Considering the blind spots of multi-line laser scanning and ranging capabilities, the distance D between gantry one and gantry two can be greater than 18m and less than 50m. Additionally, considering vehicle height and minimizing obstruction from passing vehicles, the installation height h of the two gantries can be 6-7m. Using multiple multi-line lasers to perform omnidirectional scanning of vehicles in the lane can avoid detection blind spots caused by multiple vehicles driving side-by-side.

[0037] The multi-line scanning component can continuously scan vehicles across multiple lanes. When a target vehicle is within the scanning range of the multi-line scanning component, it can scan multiple frames of point cloud data corresponding to the target vehicle. Based on these multiple frames of point cloud data, the vehicle length (from the front to the rear of the vehicle) can be determined. However, when multiple vehicles are traveling side-by-side in a lane, occlusion may cause the multi-line scanning component to miss some vehicle body information. To avoid inaccurate contour measurements due to blind spots caused by occlusion, and to improve the accuracy of vehicle length detection, and considering that vehicles are traveling closer to the multi-line scanning component, the likelihood of the front of the vehicle being occluded is relatively low compared to other positions. In this embodiment, the front position of the target vehicle can be determined based on the front frame scanned by the multi-line scanning component, and the vehicle length can be determined based on the front and rear positions at the same time. A single scan by the multi-line scanning component yields a set of data frames, which may include the front frame of the target vehicle, frames containing only partial vehicle data of the target vehicle, or frames containing no vehicle data of the target vehicle. For a given set of data frames obtained from a single scan, the first front view frame of the target vehicle is determined. Based on the position of the target vehicle's front end in the first front view frame, the first front view distance of the target vehicle can be determined. Here, the first front view frame can be the front view frame scanned by the multi-line scanning component at any given time, and the first front view distance can be the distance between the front of the target vehicle and the multi-line scanning component in the driving direction at the corresponding time.

[0038] Optionally, the scanning time corresponding to the first vehicle front frame (i.e., the first moment) can be the same as the moment when the lateral scanning component scans the vehicle's closing frame (i.e., the second moment). However, considering that the frequencies of the lateral scanning component and the multi-line scanning component may be asynchronous, when the lateral scanning component scans the vehicle's closing frame at the second moment, the multi-line scanning component may not have scanning data about the target vehicle. Therefore, the first moment can also be different from the second moment; it can be a moment before the second moment or a moment after the second moment.

[0039] Step S206: Determine the target displacement based on the first frame number and the reference displacement of the target vehicle.

[0040] Since the positions of the lateral scanning component and the multi-line scanning component are usually fixed, the horizontal distance between them (or, in other words, the distance in the driving direction) is fixed. If the horizontal distance between the front of the target vehicle and the multi-line scanning component, and the distance between the rear of the target vehicle and the lateral scanning component can be determined at a certain moment (e.g., the first moment, the second moment, etc.), and combined with the horizontal distance between the lateral scanning component and the multi-line scanning component, the length of the target vehicle can be determined.

[0041] When the first and second moments differ, the vehicle length cannot be directly determined based on the first distance between the vehicle's front end and the pre-set distances between the lateral scanning and multi-line scanning components in the driving direction. In this case, the displacement of the target vehicle during the time interval between the second and first moments can be determined. Based on this displacement, the distance between the front end of the target vehicle and the multi-line scanning component in the driving direction at the second moment (i.e., the moment the vehicle ends) can be determined, or the distance between the rear end of the target vehicle and the lateral scanning component in the driving direction at the first moment can be determined. At this point, the horizontal distance between the front end and the multi-line scanning component, and the distance between the rear end and the lateral scanning component at the same moment can be determined, thereby determining the vehicle length.

[0042] In this embodiment, the target displacement can be determined based on the first frame number and the reference displacement of the target vehicle. Here, the target displacement can be the vehicle displacement of the target vehicle between the scanning time of the first front frame and the scanning time of the vehicle rear frame, i.e., the displacement of the target vehicle during the time period between the second and first moments. The first frame number can be the number of scan frames included in a set of reference frames. Here, a set of reference frames can include scan frames whose scanning time is located between the scanning time of the first front frame and the scanning time of the vehicle rear frame. These may include scan frames containing vehicle data of the target vehicle, or they may not contain vehicle data of the target vehicle. The reference displacement can be the vehicle displacement of the target vehicle between two adjacent frames in the set of scan frames containing the vehicle rear frame and the set of reference frames; that is, the distance the target vehicle moves in its driving direction during the time period between the scanning times of any two adjacent frames in the set of scan frames containing the vehicle rear frame and the set of reference frames. Optionally, the target displacement can be determined by multiplying the first frame number and the reference displacement.

[0043] The aforementioned reference displacement can be determined by the vehicle displacement of the target vehicle detected by a ranging sensor installed on the support structure where the lateral scanning component is located between two measurement moments, and the ratio of the time interval between the two measurement moments to the scanning interval of the lateral scanning component. This method of determining the reference displacement increases the cost of vehicle length detection due to the need for additional hardware resources. Optionally, two vehicle front frames scanned by the multi-line scanning component at any two scanning moments can be selected. Based on the two vehicle front frames, the displacement of the target vehicle within the time interval between the two scanning moments can be determined. This displacement is then combined with the ratio of the time interval between the two scanning moments to the scanning interval of the lateral scanning component (i.e., the number of times the lateral scanning component can perform lateral scans within the time interval between the two scanning moments) to determine the aforementioned reference displacement. The aforementioned any two scanning moments can both be scanning moments before the scanning moment of the vehicle's final frame, or both can be scanning moments after the scanning moment of the vehicle's final frame, or may include one scanning moment before the scanning moment of the vehicle's final frame and one scanning moment after the scanning moment of the vehicle's final frame. Correspondingly, the aforementioned two vehicle front frames may or may not include the first vehicle front frame; this embodiment does not limit this. The above are merely optional methods for determining the reference displacement; this embodiment does not limit the method for determining the reference displacement.

[0044] For example, based on the position of the single-line laser frame (i.e., the scan frame) within the multi-line laser data frames, and using a proportional relationship, the distance X between the front of the target vehicle and the multi-line laser at the moment of vehicle closure can be calculated. This method solves the problem of not being able to obtain the vehicle's front position at the moment of single-line closure, and thus calculate the vehicle length, due to the asynchronous frequencies of the single-line and multi-line lasers.

[0045] When calculating X, the distances X1 and X2 between the vehicle's head frame and the multi-line laser in the two frames of the multi-line laser can be calculated separately. Assuming that the two frames of the multi-line laser are separated by C single-line laser frames, and the target vehicle is separated by C1 single-line laser frames between the vehicle's tail frame and the first reference frame, then the reference displacement is ABS(X1-X2) / C; the vehicle displacement of the target vehicle between the vehicle's tail frame and the first reference frame is ABS(X1-X2)*(C1 / C).

[0046] Step S208: Determine the vehicle length of the target vehicle based on the first vehicle head distance, the preset component distance, and the target displacement, wherein the preset component distance is the distance between the pre-set lateral scanning component and the multi-line scanning component in the driving direction.

[0047] In this embodiment, after obtaining the first vehicle headway and the target displacement, the vehicle length of the target vehicle can be determined based on the first vehicle headway, the preset component distance, and the target displacement. Here, the preset component distance is the pre-set distance between the lateral scanning component and the multi-line scanning component in the driving direction.

[0048] Optionally, the scanning time corresponding to the first vehicle head distance can be located before or after the scanning time corresponding to the vehicle tail frame. Different methods can be used to determine the vehicle length of the target vehicle for different scenarios.

[0049] When the scanning time corresponding to the first vehicle head distance is before the scanning time corresponding to the vehicle tail frame, the sum of the first vehicle head distance and the target displacement can be used as the distance between the vehicle head and the multi-line scanning component in the driving direction when the target vehicle tails up; the difference between the preset component distance and the distance between the vehicle head and the lateral scanning component in the driving direction when the target vehicle tails up can be determined as the vehicle length of the target vehicle.

[0050] When the scanning time corresponding to the first vehicle head distance is after the scanning time corresponding to the vehicle tail frame, the difference between the first vehicle head distance and the target displacement can be used as the distance between the vehicle head and the multi-line scanning component in the driving direction when the target vehicle tails up; the difference between the preset component distance and the distance between the vehicle head and the lateral scanning component in the driving direction when the target vehicle tails up can be determined as the vehicle length of the target vehicle.

[0051] For example, such as Figure 3 As shown, the distance between the single-line laser and the multi-line laser in the driving direction is D. The distance between the front of the target vehicle and the multi-line laser at the moment of vehicle closure is X. The length of the target vehicle can be deduced as L = DX.

[0052] Through steps S202 to S208, a set of scan frames obtained by the lateral scanning component is acquired. This set of scan frames includes the vehicle's final frame, indicating the target vehicle is traveling in the target lane. The final frame is the last frame of the target vehicle scanned by the lateral scanning component in the set of scan frames. Based on the first front frame of the target vehicle scanned by the multi-line scanning component, the first front distance of the target vehicle is determined. The multi-line scanning component is located in front of the lateral scanning component in the direction of travel of the target lane, and the first front distance is the distance between the front of the target vehicle and the multi-line scanning component in the direction of travel. Based on the first frame number and the reference displacement of the target vehicle, the target displacement is determined. The first frame number is the number of scan frames included in a set of reference frames. A set of reference frames includes scan frames whose scanning time is between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. The reference displacement is the vehicle displacement of the target vehicle between two adjacent frames in the set of scan frames containing the vehicle rear frame and the set of reference frames. The target displacement is the vehicle displacement of the target vehicle between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. Based on the first vehicle front distance, the preset component distance, and the target displacement, the vehicle length of the target vehicle is determined. The preset component distance is the distance between the pre-set lateral scanning component and the multi-line scanning component in the driving direction. This solves the technical problem of low accuracy of vehicle information detection due to the lack of vehicle information in related technologies, and improves the accuracy of vehicle information monitoring.

[0053] In one exemplary embodiment, acquiring a set of scan frames obtained by the lateral scanning component performing a lateral scan includes:

[0054] S11, when there are multiple lateral scanning components, the scanning data of multiple lateral scanning components are fused to obtain a set of scanning frames. The multiple lateral scanning components perform lateral scanning at the same scanning time using the same initial scanning angle and rotation speed. Each scanning frame in the set of scanning frames includes the target lane data scanned by multiple lateral scanning components at the same time.

[0055] For roads with multiple lanes, multiple lateral scanning units need to be installed to ensure that vehicles traveling in different lanes are scanned. With multiple lateral scanning units, a controller can operate multiple units simultaneously with the same initial scan angle and rotation speed; that is, they perform lateral scans at the same scan time using the same initial scan angle and rotation speed. In addition to the lateral scanning unit corresponding to the target lane, lateral scanning units corresponding to other lanes can also scan the target vehicle's data. To improve the accuracy of vehicle contour information detection, the data of the target lane scanned by different lateral scanning units at the same time can be fused to obtain a single scan frame, facilitating the analysis of vehicle contour information. This set of scan frames can be obtained by fusing the scan data from multiple lateral scanning units.

[0056] Optionally, the scanning data from multiple lateral scanning components can be fused using an interleaved approach. Considering that the data scanned by each lateral scanning component is in a component coordinate system with its own coordinate origin, to facilitate data fusion, a certain lateral scanning component can be used as a reference. Based on a preset coordinate transformation relationship between component coordinate systems, the data of the target lane scanned by multiple lateral scanning components at the same time can be converted into data in the component coordinate system of the reference lateral scanning component, and the converted data can then be fused.

[0057] For example, at any given moment, the single-line laser S i (i>1) Data scanned at the same moment are converted from polar coordinates to rectangular coordinates, and then translated according to their distance from the single-line laser S1 (i.e., the reference horizontal scanning component) to unify them into the coordinate system of the single-line laser S1. Based on the x-coordinate of the point cloud of each single-line laser, the data is then processed in an interleaved manner using several single-line lasers S1. i The data is fused to obtain a single-line fused frame Sd i (That is, a scan frame).

[0058] Here, the detection of approaching vehicles, vehicle construction, and vehicle termination is achieved by fusing the scan data from multiple single-line lasers. This avoids detection errors caused by incomplete scanning by a single single-line laser in obstructed scenarios. Furthermore, laser fusion is more effective in filtering out interference points.

[0059] In this embodiment, by fusing the scanning data of multiple lateral scanning components, the accuracy of vehicle contour information detection can be improved.

[0060] In an exemplary embodiment, determining the first frontal distance of the target vehicle based on the first frontal frame of the target vehicle scanned by the multi-line scanning component includes:

[0061] S21, perform feature matching between the first front frame and the vehicle point cloud model of the target vehicle to obtain the matching frame of the first front frame in the vehicle point cloud model.

[0062] S22, the difference between the distance between the first vehicle front frame and the multi-line scanning component in the driving direction and the distance between the matching frame and the vehicle front of the vehicle point cloud model is determined as the first vehicle front distance.

[0063] Because of the spacing and divergence angle between the scan lines of the multi-line scanning component, the first frame of the vehicle's front end scanned by the multi-line scanning component may not be the actual front end of the vehicle. Therefore, if the position of the front end in the first frame is directly used as the actual position of the target vehicle's front end to determine the first front end distance, there may be a difference between the first front end distance and the actual distance between the target vehicle's front end and the multi-line scanning component in the driving direction, reducing the accuracy of the vehicle length. In this embodiment, feature matching can be used to match the first front end frame with the vehicle point cloud model of the target vehicle to obtain a matching frame of the first front end frame in the vehicle point cloud model. Based on the difference between the distance between the matching frame and the vehicle's front end in the vehicle point cloud model, the distance between the first front end frame and the multi-line scanning component in the driving direction is compensated to determine the actual value of the first front end distance. That is, the difference between the distance between the first front end frame and the multi-line scanning component in the driving direction and the distance between the matching frame and the vehicle's front end in the vehicle point cloud model can be determined as the first front end distance.

[0064] The aforementioned vehicle point cloud model can be established based on the scanning data of the lateral scanning component or the scanning data of the multi-line scanning component; this embodiment does not impose any limitation on either. The aforementioned feature matching method can be: matching the first vehicle front frame with each frame of the point cloud in the vehicle point cloud model, and selecting the frame with the highest score as the matching frame in the vehicle point cloud model that matches the first vehicle front frame based on the matching score.

[0065] For example, feature matching is performed between the first front-end frame and each frame in the vehicle point cloud model Cloud_all. Based on the matching score, the best matching frame in Cloud_all is obtained, and the value Offset_s between the best matching frame and the first front-end frame in Cloud_all is calculated. The distance X1 between the front of the vehicle and the multi-line laser is calculated based on the first front-end frame. After compensation, the actual distance between the front of the vehicle and the multi-line laser is X1-Offset_s. By matching the front-end frame in the multi-line laser data frame with the vehicle point cloud model Cloud_all, the true front-end position is found. This avoids the situation where the first front-end frame scanned in the multi-line laser scanning frame may not be the actual front-end portion due to the spacing between the two lines.

[0066] In this embodiment, by matching the multi-line scanning component's front frame with the vehicle point cloud model using feature matching, the true position of the vehicle's front is determined, thereby determining the true distance between the vehicle's front and the multi-line scanning component, which can improve the accuracy of vehicle length detection.

[0067] In an exemplary embodiment, before determining the first frontal distance of the target vehicle based on the first frontal frame of the target vehicle scanned by the multi-line scanning component, the method further includes:

[0068] S31, based on the vehicle displacement of the target vehicle between the scanning times of two adjacent frames in a set of vehicle frames, determine the vehicle displacement corresponding to each vehicle frame in the set of vehicle frames, wherein a set of vehicle frames is all the scanning frames from the vehicle start frame to the vehicle end frame of the target vehicle in a set of scanning frames, the vehicle start frame is the first frame of the target vehicle scanned by the lateral scanning component in a set of scanning frames, and the vehicle displacement corresponding to each vehicle frame is the vehicle displacement of the target vehicle between the scanning time of each vehicle frame and the scanning time of the vehicle start frame.

[0069] S32, shift each vehicle frame to the vehicle displacement corresponding to each vehicle frame to obtain an updated set of vehicle frames;

[0070] S33, perform an addition operation on the updated set of vehicle frames to obtain the vehicle point cloud model of the target vehicle.

[0071] In this embodiment, considering that a single frame of point cloud data is difficult to completely contain the point cloud data of the entire vehicle, a vehicle point cloud model of the target vehicle can be established based on multi-frame point cloud data. Here, multi-frame point cloud data is point cloud data obtained by scanning different positions of the target vehicle on the scanning surface of the lateral scanning component at different times. It can be all the scanning frames of the target vehicle from the vehicle start frame to the vehicle end frame in a set of scanning frames, that is, a set of vehicle frames, where the vehicle start frame is the first frame of the target vehicle scanned by the lateral scanning component in a set of scanning frames.

[0072] For a set of vehicle frames, each vehicle frame can be displaced according to its corresponding vehicle displacement. This displacement corresponds to the vehicle displacement of the target vehicle between the scanning time of each vehicle frame and the scanning time of the vehicle's initial frame, resulting in an updated set of vehicle frames. After obtaining the updated set of vehicle frames, an addition operation can be performed on them to obtain the target vehicle's point cloud model. This addition operation can be performed directly on the updated set of vehicle frames, or it can be performed after removing all point cloud data except for the target vehicle's point cloud data from each vehicle frame.

[0073] Here, since the position of the lateral scanning component is fixed, the positions of the vehicle data in the scanned vehicle frames are the same or nearly the same in the driving direction (considering possible deviations). Adding the vehicle frames will result in vehicle point cloud data within a single plane. Therefore, the sum of the vehicle frames cannot be directly used as the vehicle point cloud model of the target vehicle. Instead, by displacing each vehicle frame according to its corresponding vehicle displacement, it's equivalent to the lateral scanning component moving to the responding position and then scanning the corresponding vehicle position of the target vehicle. Therefore, performing the addition operation on the updated set of vehicle frames yields a more realistic vehicle point cloud model.

[0074] In this embodiment, in order to determine the vehicle displacement corresponding to each vehicle frame, firstly, the vehicle displacement of the target vehicle between the scanning times of any two adjacent frames in a set of vehicle frames can be determined; then, by adding the vehicle displacements between the scanning times of any two adjacent frames from the vehicle starting frame to each vehicle frame, the vehicle displacement corresponding to each vehicle frame can be obtained.

[0075] For example, let the vehicle start frame be Sd1 and the vehicle end frame be Sd. 10 For example, a group of vehicle frames are Sd1 to Sd2. 10 The vehicle displacement between Sd1 and Sd2 is ΔX1, the vehicle displacement between Sd2 and Sd3 is ΔX2, and so on. Each vehicle frame (Sd1, Sd2, ..., Sd3) in a set of vehicle frames... 10 The corresponding vehicle displacements are 0, ΔX1, ΔX1+ΔX2, ..., ΔX1+ΔX2+...+, ΔX9. Let Sd1~Sd... 10 Displacement is performed according to the corresponding vehicle displacement, and the displacement values ​​Sd1 to Sd are then processed. 10 Perform the addition operation to obtain the vehicle point cloud model of the target vehicle.

[0076] In this embodiment, each vehicle frame is displaced according to the vehicle displacement between the scanning time of each vehicle frame and the scanning time of the vehicle's starting frame, and the displaced vehicle frames are added together to obtain a vehicle point cloud model, which can improve the accuracy of vehicle point cloud model construction.

[0077] In one exemplary embodiment, the above method further includes:

[0078] S41, determine the first multi-line scanning frame and the second multi-line scanning frame in a set of multi-line scanning frames scanned by the multi-line scanning component, wherein the first multi-line scanning frame is the multi-line scanning frame whose scanning time is before the scanning time of the vehicle start frame and is closest to the scanning time of the vehicle start frame in the set of multi-line scanning frames, and the second multi-line scanning frame is the multi-line scanning frame whose scanning time is after the scanning time of the vehicle start frame in the set of multi-line scanning frames.

[0079] S42, repeatedly perform the following vehicle displacement determination operation until the vehicle displacement of the target vehicle between any two adjacent scan times in a set of vehicle frames has been determined:

[0080] Obtain the total displacement of the target vehicle between the scanning time of the first multi-line scan frame and the scanning time of the second multi-line scan frame;

[0081] Determine the number of scan frames contained in a set of current frames to obtain the target number, wherein a set of current frames contains scan frames whose scanning time is between the scanning time of the first multi-line scan frame and the scanning time of the second multi-line scan frame.

[0082] The vehicle displacement obtained by removing the total vehicle position from the difference between the target number and 1 is determined as the vehicle displacement of the target vehicle between the scanning times of two adjacent frames in a set of target frames. Here, a set of target frames is a set of scanning frames in the current frame for which the corresponding vehicle displacement is to be determined.

[0083] The first multi-line scan frame is updated to the next multi-line scan frame in a set of multi-line scan frames to obtain the updated first multi-line scan frame, and the second multi-line scan frame is updated to the next multi-line scan frame in a set of multi-line scan frames to obtain the updated second multi-line scan frame.

[0084] Since the scanning surface of the lateral scanning component is perpendicular to the direction of travel of the target vehicle, the vehicle displacement cannot be directly determined by scanning the target vehicle at different times using the lateral scanning component. In this embodiment, the vehicle displacement between the scanning times of two adjacent frames in a set of vehicle frames can be determined by combining the scanning data of the multi-line scanning component.

[0085] In this embodiment, considering that the moving speed of the target vehicle usually changes with time, in order to improve the accuracy of vehicle displacement determination, the vehicle displacement of the target vehicle between the scanning times of two adjacent frames in a set of vehicle frames (i.e., the vehicle displacement of the target vehicle in each scanning interval) can be estimated based on the sequential relationship between the scanning time of the multi-line scanning component and the scanning time of the lateral scanning component, as well as the vehicle head position determined by the scanning data of the multi-line scanning component at different scanning times.

[0086] Optionally, a first multi-line scanning frame and a second multi-line scanning frame can be selected from a set of multi-line scanning frames scanned by the multi-line scanning component. Here, the first multi-line scanning frame can be the multi-line scanning frame whose scanning time is before and closest to the scanning time of the vehicle's starting frame in the set of multi-line scanning frames. The second multi-line scanning frame can be a multi-line scanning frame whose scanning time is after the scanning time of the vehicle's starting frame in the set of multi-line scanning frames (which can be spaced several multi-line scanning frames apart from the first multi-line scanning frame). The scanning time of the vehicle's starting frame can be the time when the target vehicle is first scanned by the lateral scanning component.

[0087] For example, when a single-line laser detects an approaching vehicle, this time is marked as t0, and the single-line fusion trigger is Sdm (i.e., the vehicle's initial frame). In the data queue, the laser data Md0 (i.e., the first multi-line scan frame) of the multi-line laser Mi before time t0 and the subsequent multi-line laser data Mdm (i.e., the second multi-line scan frame) are found. When detecting an approaching vehicle, the vehicle height can be determined based on the vehicle data scanned by the single-line laser. Whether there is a vehicle in Sdi is determined based on whether the vehicle height reaches a preset height threshold.

[0088] Since a set of vehicle frames may not all be located between the first multi-line scan frame and the second multi-line scan frame, in order to improve the accuracy of vehicle displacement determination, multiple iterations can be used to determine the vehicle displacement of the target vehicle between the scanning times of two adjacent frames in a subset of vehicle frames in a set of vehicle frames, until the vehicle displacement of the target vehicle between the scanning times of any two adjacent frames in a set of vehicle frames is determined.

[0089] During an iteration, the front position of the target vehicle can be determined at the scanning time of the first and second multi-line scan frames, respectively. Based on the change in the front position of the target vehicle, the total displacement of the target vehicle between the scanning times of the first and second multi-line scan frames can be obtained. Simultaneously, based on the scanning times of the first and second multi-line scan frames, the scan frames whose scanning times fall between the scanning times of the two multi-line scan frames can be identified within a set of scan frames; that is, a set of current frames. Furthermore, the number of scan frames contained within this set of current frames can be determined, thus obtaining the target quantity.

[0090] In this embodiment, the total vehicle displacement is the total displacement of the target vehicle within the time period during which the lateral scanning component scans a set of current frames. The vehicle displacement between the scanning times of two adjacent frames in a set of current frames can be determined based on the total vehicle displacement and the target quantity. Since the scanning interval of a set of current frames is the difference between the target quantity and 1, the vehicle displacement obtained by subtracting the difference between the target quantity and 1 from the total vehicle displacement can be determined as the vehicle displacement between the scanning times of two adjacent frames in a set of current frames. Furthermore, considering that there is a certain time interval between the scanning time of the first multi-line scanning frame and the scanning time of the earliest scanning frame in a set of current frames (i.e., the two scanning times do not completely overlap), and a certain time interval between the scanning time of the last scanning frame in a set of current frames and the scanning time of the second multi-line scanning frame (i.e., the two scanning times do not completely overlap), the vehicle displacement obtained by subtracting the target quantity from the total vehicle displacement can also be determined as the vehicle displacement between the scanning times of two adjacent frames in a set of current frames.

[0091] Considering that during an iteration, the scanning interval between two adjacent frames in a set of current frames may include scanning intervals where the vehicle displacement has been determined, the vehicle displacement determined in this iteration can be used only as the time interval where the vehicle displacement has not been determined. That is, it can be used only as the vehicle displacement between the scanning times of two adjacent frames in a set of target frames. A set of target frames can be a set of scanning frames in the current frames where the corresponding vehicle displacement is to be determined.

[0092] For example, such as Figure 4 As shown, for the above t0, Sd m Md0 and Md m The next frame after Md0 is a single-line fused frame, Sd0, Md m The previous single-line fused frame is Sd n Through Md0, Md m Feature matching to obtain Md0 and Md m The vehicle displacement Δx between the two lines and the number of single-line fused data frames n+1 are used to calculate Md0 and Md. m The average displacement Δx / n of the single-line fused frames between Sd m To Sd n The point cloud frame data are shifted by 0*(Δx / n), 1*(Δx / n), 2*(Δx / n), ..., (nm)*(Δx / n). Then, the shifted single-line fused frames are summed to obtain Cloud_all. This method of establishing a vehicle point cloud model based on the vehicle displacement between two adjacent frames of the multi-line laser and the single-line fused frames effectively avoids the problem of sparse vehicle body scanning and inaccurate vehicle front-end acquisition when the vehicle is far from the multi-line laser.

[0093] After one iteration, if there are scan frames in a set of scan frames where the corresponding vehicle displacement is not determined, the next iteration can continue. The first multi-line scan frame can be updated to the next multi-line scan frame in the set of multi-line scan frames, resulting in an updated first multi-line scan frame. Similarly, the second multi-line scan frame can be updated to the next multi-line scan frame in the set of multi-line scan frames, resulting in an updated second multi-line scan frame. This vehicle displacement determination operation is repeated until the vehicle displacement of the target vehicle between any two adjacent scan times in a set of vehicle frames has been determined.

[0094] It should be noted that the number of multi-line scanning components can be one or more. When there are multiple multi-line scanning components, a set of multi-line scanning frames can contain multi-line scanning frames scanned by multiple multi-line scanning components. The first multi-line scanning frame and the second multi-line scanning frame can be multi-line scanning frames scanned by the same multi-line scanning component, or they can be multi-line scanning frames scanned by different multi-line scanning components. This embodiment does not limit this.

[0095] For example, in the case of Sd m To Sd n After displacement, for Md (m+1) and Md i Inter-line fusion frame Sd i After performing the same displacement operation on (i = n + 1, ...), the result is added to Cloud_all, and so on. Once the single-line fusion frame Sde detects the vehicle's tail, the vehicle point cloud model Cloud_all is obtained.

[0096] In this embodiment, by combining the scanning data of the multi-line scanning component to determine the displacement corresponding to each vehicle frame scanned by the lateral scanning component, the accuracy of point cloud displacement can be improved, thereby improving the accuracy of vehicle point cloud model establishment.

[0097] In an exemplary embodiment, the first vehicle front frame is the last vehicle front frame corresponding to the target vehicle scanned by the multi-line scanning component before the vehicle rear frame. That is, it is the target vehicle's front frame among the multi-line scan frames whose scanning time is before the scanning time of the vehicle rear frame and whose time interval between the two scanning times is the shortest. Correspondingly, the above method further includes:

[0098] S51, determine the second front distance of the target vehicle based on the second front frame of the target vehicle scanned by the multi-line scanning component, wherein the second front frame is the front frame corresponding to the target vehicle that is first scanned by the multi-line scanning component after the vehicle's rear frame.

[0099] S52, the quotient of the distance difference between the first vehicle front distance and the second vehicle front distance and the sum of the first frame number and the second frame number is determined as the reference displacement, wherein the second frame number is the number of scan frames in a set of scan frames whose scanning time is located between the scanning time of the vehicle tail frame and the scanning time of the second vehicle front frame.

[0100] In this embodiment, when calculating the reference position, the displacement of the target vehicle within the time interval between two scanning moments can be determined based on two vehicle front frames scanned by the multi-line scanning component at any two scanning moments. This displacement is then determined by combining the ratio of the time interval between the two scanning moments to the scanning interval of the lateral scanning component (i.e., the number of times the lateral scanning component can perform lateral scans within the time interval between the two scanning moments). The two vehicle front frames can be the first vehicle front frame. Alternatively, the other vehicle front frame can be the second vehicle front frame, which can be the first vehicle front frame corresponding to the target vehicle scanned by the multi-line scanning component after the vehicle's final frame.

[0101] For the second front-end frame, the horizontal distance between the front of the target vehicle and the multi-line scanning component at the scanning time of the second front-end frame, i.e., the second front-end distance, can be determined in a manner similar to that in the previous embodiments. The number of scanning frames whose scanning time falls between the scanning time of the vehicle's closing frame and the scanning time of the second front-end frame, i.e., the second frame number, can also be determined. The difference between the first front-end distance and the second front-end distance is the total displacement of the target vehicle during the time interval between the scanning time corresponding to the first front-end frame and the scanning time corresponding to the second front-end frame. The number of scanning frames whose scanning time falls between the scanning time corresponding to the first front-end frame and the scanning time corresponding to the second front-end frame is the sum of the first frame number and the second frame number. The quotient of the difference between the first front-end distance and the second front-end distance and the sum of the first and second frame numbers is determined as the reference displacement. Here, the second front-end distance can be obtained by compensating for the distance by feature matching between the second front-end frame and the vehicle point cloud model, in a manner similar to that described above. This will not be repeated here.

[0102] For example, in the data queue, the previous frame of multi-line laser data frame Md is obtained from Sde. n And the next frame of multi-line laser data frame Md (n+1) (That is, two frames before and after the single-line fusion frame ends, involving multi-line lasers), extract Mdn and Md. (n+1) CRRC head frame Md n_s and Md (n+1)_s Md n_s and Md (n+1)_sPerform feature matching with each frame in Cloud_all, and obtain the best matching frame in Cloud_all based on the matching score. Calculate the values ​​Offset_s and Offset_s+1 between the best matching frame and the first frame of the vehicle head in Cloud_all.

[0103] Calculate Md separately n and Md (n+1) The front frame of the car in Md n_s and Md (n+1)_s After compensation, the actual distances between the vehicle front and the multi-line laser are X1 and X2, respectively. 1-Offset_s and X 2-Offset_s+1 Assuming the distance between the single-line fusion final frame Sde and Md is... n Interval C1 single-line fusion frames, distance Md (n+1) By merging C2 single-line laser frames at intervals, the distance X between the vehicle's front and the multi-line laser at the end of a single-line laser cycle can be derived as X = (X... 1-Offset_s )-(ABS((X 1-Offset_s )-(X 2-Offset_s+1 )))*(C1 / (C1+C2)).

[0104] In this embodiment, by selecting the front frame of the vehicle from the multi-line scan frames scanned by the multi-line scanning component before and after the vehicle's end as the data for determining the reference displacement, the accuracy of the reference displacement determination can be improved, thereby enhancing the accuracy of vehicle length detection.

[0105] In one exemplary embodiment, the above method further includes:

[0106] S61, acquire multiple candidate frames scanned by the multi-line scanning component during the same data scan, wherein each candidate frame is a data frame scanned by a different scanning component in the multi-line scanning component;

[0107] S62, the candidate frame in which the height of the target vehicle is greater than or equal to a preset height threshold is determined as the first front frame.

[0108] Because a multi-line scanning unit contains multiple scanning components, after a single data scan, the multi-line scanning unit can obtain multiple frames of scan data, and the number of frames can be the same as the number of lines in the multi-line scanning unit. Within the scanning area of ​​the multi-line scanning unit, the data frames scanned by the multi-line scanning unit can simultaneously contain vehicle point cloud data and other non-vehicle point cloud data (e.g., ground). However, there is a significant difference in height between vehicles and the ground. Based on this characteristic, the frames related to the target vehicle can be identified among the multiple frames scanned by the multi-line scanning unit, thereby determining the front frame of the target vehicle.

[0109] In this embodiment, multiple candidate frames scanned by the multi-line scanning component during the same data scan can be obtained. The scanning times corresponding to the multiple candidate frames can be the same or different. The scanning time of a specific line scanning component can be used as the scanning time of the multi-line scanning component. Here, each candidate frame in the multiple candidate frames can be a data frame scanned by a different scanning component in the multi-line scanning component.

[0110] For example, such as Figure 4 As shown, for a multi-line laser, the multi-line laser data frame Md before and after the termination... n Md (n+1) The text contains a frame Md containing the front of the vehicle. n_s and Md (n+1)_s Multiple candidate frames, including those from [the previous frame].

[0111] Based on the typical height of a vehicle's front end, a height threshold can be preset. Candidate frames containing target vehicles whose height is greater than or equal to the preset height threshold are then identified as the first front end frame. If at least two candidate frames contain target vehicles whose height is greater than or equal to the preset height threshold, either one can be selected as the first front end frame.

[0112] In this embodiment, the accuracy of vehicle length detection can be improved by determining the vehicle front frame based on the scan frames containing vehicle height values ​​greater than or equal to a preset height threshold in the multi-line scan frames.

[0113] The vehicle information detection method in this application embodiment will be explained below with reference to an optional example. In this optional example, the lateral scanning component is a single-line laser S. i The multi-line scanning component is a multi-line laser M. i The moment when the single-line laser first detects the car is t0, and the single-line fusion trigger frame is Sd. m .

[0114] To address the challenge of accurately measuring the length, width, and height of vehicles dynamically using only single-line or multi-line lasers, this optional example provides a free-flow profile detection method. This method combines single-line and multi-line lasers to achieve accurate measurement of vehicle profile dimensions in free-flow conditions. It solves the problem of unmeasurable vehicle length due to lane changes or crossings during driving, and addresses the decrease in vehicle profile accuracy caused by occlusion when multiple vehicles are traveling side-by-side. The vehicle information detection method in this optional example may include the following steps:

[0115] Step 1: Through coordinate transformation and translation, adjust the coordinates of the several single-line lasers S used. i The data is fused to obtain a single-line fused frame Sd i .

[0116] Step 2: Based on the data from the single-line laser, determine the time when it first detects the car as t0.

[0117] Step 3, using the multi-line laser data frame Md0 before time t0 and several multi-line laser data frames Md after time t0. m Feature matching is used to obtain the vehicle displacement Δx between the two frames and the number of single-line fused data frames n+1 between the two frames. Md0 and Md are then calculated. m The average displacement Δx / n between two single-line fused frames.

[0118] Step 4, for Sd m To Sd n The point cloud frame data are shifted by 0*(Δx / n), 1*(Δx / n), 2*(Δx / n), ..., (nm)*(Δx / n), and then the shifted point cloud frames are added together to obtain Cloud_all.

[0119] Step 5, for Md (m+1) Md i Inter-line fusion frame Sd i After performing the same displacement operation on (i = n + 1, ...), the result is added to Cloud_all, and so on. Once the single-line fusion frame Sde detects the vehicle's tail, the vehicle point cloud model Cloud_all is obtained.

[0120] Step 6: Based on the vehicle height threshold, determine the previous frame of multi-line laser data frame Md. n And the next frame of multi-line laser data frame Md (n+1) The front frame of the car in Md n_s and Md (n+1)_s .

[0121] Step 7, Md n_s and Md (n+1)_s Perform feature matching with each frame in Cloud_all, and obtain the best matching frame in Cloud_all based on the matching score. Calculate the values ​​Offset_s and Offset_s+1 between the best matching frame and the first frame of the vehicle head in Cloud_all.

[0122] Step 8, based on the front frame Md n_s and Md (n+1)_s The calculated distances from the vehicle's front to the multi-line laser are X1 and X2. After compensation, the actual distances from the vehicle's front to the multi-line laser are X1 and X2, respectively. 1-Offset_s X 2-Offset_s+1 .

[0123] Step 9, calculate Md n and Md (n+1)The front frame of the car in Md n_s and Md (n+1)_s After compensation, the actual distances between the vehicle front and the multi-line laser are X1 and X2, respectively. 1-Offset_s and X 2-Offset_s+1 Assuming the distance between the single-line fusion final frame Sde and Md is... n Interval C1 single-line fusion frames, distance Md (n+1) By merging C2 single-line laser frames at intervals, the distance X between the vehicle's front and the multi-line laser at the end of a single-line laser cycle can be derived as X = (X... 1-Offset_s )-(ABS((X 1-Offset_s )-(X 2-Offset_s+1 )))*(C1 / (C1+C2)). Then the length of the vehicle is L=DX.

[0124] This optional example demonstrates how a combination of single-line and multi-line lasers can be used to dynamically measure the outline of a vehicle. This method enables the measurement of vehicle outlines in free-flowing conditions, solving the problem of inaccurate vehicle outline measurement in complex scenarios such as lane changes, lane crossings, and occlusions, thereby improving the accuracy of vehicle outline information detection.

[0125] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0126] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM (Read-Only Memory) / RAM (Random Access Memory), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0127] According to another aspect of the embodiments of this application, a vehicle information detection system for implementing the above-described vehicle information detection method is also provided. The vehicle information detection system may include:

[0128] Lateral scanning component, used to scan passing target vehicles laterally;

[0129] The multi-line scanning component is located in front of the lateral scanning component in the direction of travel of the target vehicle, and is used to perform multi-line scanning of the target vehicle;

[0130] The data processing unit is used to acquire a set of scan frames obtained by the lateral scanning unit during lateral scanning. The set of scan frames includes the vehicle's tail frame, where the target vehicle is traveling in the target lane, and the tail frame is the last frame of the target vehicle in the set of scan frames. Based on the first front frame of the target vehicle scanned by the multi-line scanning unit, the unit determines the first front distance of the target vehicle, where the first front distance is the distance between the front of the target vehicle and the multi-line scanning unit in the driving direction. Based on the first frame number and the target vehicle's reference displacement, the unit determines the target displacement, where the first frame number is the number of scans contained in the set of reference frames. The frame number is defined as follows: a set of reference frames includes scan frames whose scanning time is between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame; the reference displacement is the vehicle displacement of the target vehicle between two adjacent frames in the set of scan frames containing the vehicle rear frame and a set of reference frames; and the target displacement is the vehicle displacement of the target vehicle between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. The vehicle length of the target vehicle is determined based on the first vehicle front distance, the preset component distance, and the target displacement, wherein the preset component distance is the distance between the pre-set lateral scanning component and the multi-line scanning component in the driving direction.

[0131] It should be noted that the data processing component can be a server or a processing device that performs the aforementioned functions of determining the first vehicle headway distance, the first frame number, the reference displacement, the target displacement, and the vehicle length based on the first vehicle headway distance and the target displacement. Examples include processors and controllers. The methods for determining the first vehicle headway distance, the first frame number, the reference displacement, the target displacement, and the vehicle length based on the first vehicle headway distance and the target displacement are similar to those described in the previous embodiments and will not be repeated here.

[0132] The vehicle information detection system described above acquires a set of scan frames obtained by the lateral scanning component. Each set of scan frames includes the target vehicle's final frame, indicating the target vehicle is traveling in the target lane. The final frame is the last frame of the target vehicle scanned by the lateral scanning component within the set of scan frames. Based on the first frontal frame of the target vehicle scanned by the multi-line scanning component, the first frontal distance of the target vehicle is determined. This first frontal distance is the distance between the front of the target vehicle and the multi-line scanning component in the driving direction. Based on the first frame number and the target vehicle's reference displacement, the target displacement is determined. The first frame number is the number of scan frames included in a set of reference frames, where a set of reference frames includes the scanning time position within the set of scan frames. The scanning frames between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame, the reference displacement is the vehicle displacement of the target vehicle between two adjacent frames of the vehicle rear frame and a set of reference frames, and the target displacement is the vehicle displacement of the target vehicle between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame; the vehicle length of the target vehicle is determined based on the first vehicle front distance, the preset component distance, and the target displacement, wherein the preset component distance is the distance between the pre-set lateral scanning component and the multi-line scanning component in the driving direction. Determining the vehicle length of the target vehicle solves the technical problem of low accuracy of vehicle information detection due to the lack of vehicle information in related technologies, and improves the accuracy of vehicle information monitoring.

[0133] In an exemplary embodiment, the data processing unit is further configured to fuse the scanning data of multiple lateral scanning units when there are multiple lateral scanning units to obtain a set of scanning frames, wherein the multiple lateral scanning units perform lateral scanning at the same scanning time using the same initial scanning angle and rotation speed, and each scanning frame in the set of scanning frames includes data of the target lane scanned by the multiple lateral scanning units at the same time.

[0134] In an exemplary embodiment, the data processing unit is further configured to perform feature matching between the first vehicle front frame and the vehicle point cloud model of the target vehicle to obtain a matching frame of the first vehicle front frame in the vehicle point cloud model; and to determine the difference between the distance between the first vehicle front frame and the multi-line scanning unit in the driving direction and the distance between the matching frame and the vehicle front of the vehicle point cloud model as the first vehicle front distance.

[0135] In an exemplary embodiment, the data processing unit is further configured to, before determining the first headway of the target vehicle based on the first headway frame of the target vehicle scanned by the multi-line scanning unit, determine the vehicle displacement corresponding to each vehicle frame in the set of vehicle frames based on the vehicle displacement of the target vehicle between the scanning times of two adjacent frames in the set of vehicle frames, wherein the set of vehicle frames consists of all scanning frames from the vehicle start frame to the vehicle end frame of the target vehicle in the set of scanning frames, the vehicle start frame is the first frame of the target vehicle scanned by the lateral scanning unit in the set of scanning frames, and the vehicle displacement corresponding to each vehicle frame is the vehicle displacement of the target vehicle between the scanning time of each vehicle frame and the scanning time of the vehicle start frame; each vehicle frame is displaced to the vehicle displacement corresponding to each vehicle frame to obtain an updated set of vehicle frames; and an addition operation is performed on the updated set of vehicle frames to obtain the vehicle point cloud model of the target vehicle.

[0136] In an exemplary embodiment, the data processing unit is further configured to determine a first multi-line scan frame and a second multi-line scan frame in a set of multi-line scan frames scanned by the multi-line scan unit, wherein the first multi-line scan frame is the multi-line scan frame in the set of multi-line scan frames whose scan time is before the scan time of the vehicle start frame and is closest to the scan time of the vehicle start frame, and the second multi-line scan frame is the multi-line scan frame in the set of multi-line scan frames whose scan time is after the scan time of the vehicle start frame; the following vehicle displacement determination operation is performed cyclically until the vehicle displacement of the target vehicle between the scan times of any two adjacent frames in the set of vehicle frames has been determined: obtaining the total vehicle displacement of the target vehicle between the scan times of the first multi-line scan frame and the scan times of the second multi-line scan frame; determining a set of current frames. The number of scan frames included is used to obtain the target number. A set of current frames includes scan frames whose scanning time is between the scanning time of the first multi-line scan frame and the scanning time of the second multi-line scan frame. The vehicle displacement obtained by removing the total vehicle position by the difference between the target number and 1 is determined as the vehicle displacement of the target vehicle between the scanning times of two adjacent frames in a set of target frames. A set of target frames is a set of current frames in which the corresponding vehicle displacement is to be determined. The first multi-line scan frame is updated to the next multi-line scan frame in a set of multi-line scan frames to obtain the updated first multi-line scan frame. The second multi-line scan frame is updated to the next multi-line scan frame in a set of multi-line scan frames to obtain the updated second multi-line scan frame.

[0137] In an exemplary embodiment, the first front-end frame is the front-end frame corresponding to the target vehicle that is last scanned by the multi-line scanning component before the vehicle's closing frame; the data processing component is further configured to determine the second front-end distance of the target vehicle based on the second front-end frame of the target vehicle scanned by the multi-line scanning component, wherein the second front-end frame is the front-end frame corresponding to the target vehicle that is first scanned by the multi-line scanning component after the vehicle's closing frame; the quotient of the distance difference between the first front-end distance and the second front-end distance and the sum of the number of frames of the first frame and the second frame is determined as a reference displacement, wherein the number of frames in a set of scan frames whose scanning time is between the scanning time of the vehicle's closing frame and the scanning time of the second front-end frame.

[0138] In an exemplary embodiment, the data processing unit is further configured to acquire multiple candidate frames scanned by the multi-line scanning unit during the same data scan, wherein each candidate frame is a data frame scanned by a different scanning unit in the multi-line scanning unit; and to determine the candidate frame in the multiple candidate frames in which the vehicle height of the target vehicle is greater than or equal to a preset height threshold as the first vehicle front frame.

[0139] It should be noted that the examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of a device, can operate in environments such as... Figure 1 The hardware environment shown can be implemented through software or hardware, and the hardware environment includes the network environment.

[0140] According to another aspect of the embodiments of this application, a storage medium is also provided. Optionally, in this embodiment, the storage medium can be used to execute the program code of any of the vehicle information detection methods described above in the embodiments of this application.

[0141] Optionally, in this embodiment, the storage medium may be located on at least one of the network devices in the network shown in the above embodiment.

[0142] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps:

[0143] S1, acquire a set of scan frames obtained by the lateral scanning component performing lateral scanning, wherein the set of scan frames includes the vehicle tail frame of the target vehicle, the target vehicle is driving on the target lane, and the vehicle tail frame is the last frame of the target vehicle in the set of scan frames.

[0144] S2, based on the first front frame of the target vehicle scanned by the multi-line scanning component, determine the first front distance of the target vehicle, wherein the multi-line scanning component is located in front of the transverse scanning component in the driving direction of the target lane, and the first front distance is the distance between the front of the target vehicle and the multi-line scanning component in the driving direction.

[0145] S3. Determine the target displacement based on the first frame number and the reference displacement of the target vehicle. The first frame number is the number of scan frames contained in a set of reference frames. A set of reference frames includes scan frames whose scanning time is between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. The reference displacement is the vehicle displacement of the target vehicle between two adjacent frames in the set of scan frames containing the vehicle rear frame and a set of reference frames. The target displacement is the vehicle displacement of the target vehicle between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame.

[0146] S4. Determine the length of the target vehicle based on the first vehicle head distance, the preset component distance, and the target displacement. The preset component distance is the distance between the lateral scanning component and the multi-line scanning component in the driving direction.

[0147] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated in this embodiment.

[0148] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, ROMs, RAMs, portable hard drives, magnetic disks, or optical disks.

[0149] According to another aspect of the embodiments of this application, an electronic device for implementing the above-described vehicle information detection method is also provided. The electronic device may be a server, a terminal, or a combination thereof.

[0150] Figure 5 This is a structural block diagram of an optional electronic device according to an embodiment of this application, such as... Figure 5 As shown, it includes a processor 502, a communication interface 504, a memory 506, and a communication bus 508. The processor 502, communication interface 504, and memory 506 communicate with each other via the communication bus 508.

[0151] Memory 506 is used to store computer programs;

[0152] When processor 502 executes a computer program stored in memory 506, it performs the following steps:

[0153] S1, acquire a set of scan frames obtained by the lateral scanning component performing lateral scanning, wherein the set of scan frames includes the vehicle tail frame of the target vehicle, the target vehicle is driving on the target lane, and the vehicle tail frame is the last frame of the target vehicle in the set of scan frames.

[0154] S2, based on the first front frame of the target vehicle scanned by the multi-line scanning component, determine the first front distance of the target vehicle, wherein the multi-line scanning component is located in front of the transverse scanning component in the driving direction of the target lane, and the first front distance is the distance between the front of the target vehicle and the multi-line scanning component in the driving direction.

[0155] S3. Determine the target displacement based on the first frame number and the reference displacement of the target vehicle. The first frame number is the number of scan frames contained in a set of reference frames. A set of reference frames includes scan frames whose scanning time is between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. The reference displacement is the vehicle displacement of the target vehicle between two adjacent frames in the set of scan frames containing the vehicle rear frame and a set of reference frames. The target displacement is the vehicle displacement of the target vehicle between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame.

[0156] S4. Determine the length of the target vehicle based on the first vehicle head distance, the preset component distance, and the target displacement. The preset component distance is the distance between the lateral scanning component and the multi-line scanning component in the driving direction.

[0157] Optionally, the communication bus can be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 The symbol is represented by a single thick line, but this does not indicate that there is only one bus or one type of bus. The communication interface is used for communication between the aforementioned electronic device and other devices.

[0158] The memory may include RAM, or non-volatile memory, such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0159] The processors mentioned above can be general-purpose processors, including but not limited to: CPU (Central Processing Unit), NP (Network Processor), etc.; they can also be DSP (Digital Signal Processor), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0160] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments, and will not be repeated here.

[0161] Those skilled in the art will understand that Figure 5 The structure shown is for illustrative purposes only. The device that implements the above vehicle information detection method can be a terminal device, such as a smartphone (e.g., Android phone, iOS phone), tablet computer, handheld computer, mobile internet device (MID), PAD, etc. Figure 5 This does not limit the structure of the aforementioned electronic device. For example, the electronic device may also include components that are more... Figure 5 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 5 The different configurations shown.

[0162] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, ROM, RAM, disk or optical disk, etc.

[0163] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0164] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0165] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0166] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0167] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the solution provided in this embodiment, depending on actual needs.

[0168] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or at least two units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0169] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A vehicle information detection method, characterized in that, include: A set of scan frames obtained by the lateral scanning component performing a lateral scan is acquired, wherein the set of scan frames includes the vehicle tail frame of the target vehicle, the target vehicle is driving on the target lane, and the vehicle tail frame is the last frame of the target vehicle in the set of scan frames; Based on the first front frame of the target vehicle scanned by the multi-line scanning component, the first front distance of the target vehicle is determined, wherein the multi-line scanning component is located in front of the lateral scanning component in the driving direction of the target lane, and the first front distance is the distance between the front of the target vehicle and the multi-line scanning component in the driving direction. The target displacement is determined based on the first frame number and the reference displacement of the target vehicle. The first frame number is the number of scan frames included in a set of reference frames. The set of reference frames includes scan frames whose scanning time is between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. The reference displacement is the vehicle displacement of the target vehicle between two adjacent frames in the set of scan frames that includes the vehicle rear frame and the set of reference frames. The target displacement is the vehicle displacement of the target vehicle between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. The vehicle length of the target vehicle is determined based on the first vehicle front distance, the preset component distance, and the target displacement, wherein the preset component distance is the pre-set distance between the lateral scanning component and the multi-line scanning component in the driving direction.

2. The method according to claim 1, characterized in that, The acquisition of a set of scan frames obtained by the lateral scanning component during lateral scanning includes: When there are multiple lateral scanning components, the scanning data of the multiple lateral scanning components are fused to obtain the set of scanning frames. The multiple lateral scanning components perform lateral scanning at the same scanning time using the same initial scanning angle and rotation speed. Each scanning frame in the set of scanning frames includes the data of the target lane scanned by the multiple lateral scanning components at the same time.

3. The method according to claim 1, characterized in that, Determining the first frontal distance of the target vehicle based on the first frontal frame of the target vehicle scanned by the multi-line scanning component includes: The first front view frame is matched with the vehicle point cloud model of the target vehicle to obtain the matching frame of the first front view frame in the vehicle point cloud model. The difference between the distance between the first vehicle front frame and the multi-line scanning component in the driving direction and the distance between the matching frame and the vehicle front of the vehicle point cloud model is determined as the first vehicle front distance.

4. The method according to claim 3, characterized in that, Before determining the first frontal distance of the target vehicle based on the first frontal frame of the target vehicle scanned by the multi-line scanning component, the method further includes: Based on the vehicle displacement of the target vehicle between the scanning times of two adjacent frames in a set of vehicle frames, the vehicle displacement corresponding to each vehicle frame in the set of vehicle frames is determined. The set of vehicle frames comprises all scanning frames from the vehicle start frame to the vehicle end frame of the target vehicle in the set of scanning frames. The vehicle start frame is the first frame of the target vehicle scanned by the lateral scanning component in the set of scanning frames. The vehicle displacement corresponding to each vehicle frame is the vehicle displacement of the target vehicle between the scanning time of each vehicle frame and the scanning time of the vehicle start frame. Each vehicle frame is then shifted to its corresponding vehicle displacement to obtain the updated set of vehicle frames. An addition operation is performed on the updated set of vehicle frames to obtain the vehicle point cloud model of the target vehicle.

5. The method according to claim 4, characterized in that, The method further includes: The first multi-line scanning frame and the second multi-line scanning frame are determined from a set of multi-line scanning frames scanned by the multi-line scanning component. The first multi-line scanning frame is the multi-line scanning frame in the set of multi-line scanning frames whose scanning time is before the scanning time of the vehicle start frame and is closest to the scanning time of the vehicle start frame. The second multi-line scanning frame is the multi-line scanning frame in the set of multi-line scanning frames whose scanning time is after the scanning time of the vehicle start frame. The following vehicle displacement determination operation is performed repeatedly until the vehicle displacement of the target vehicle between the scan times of any two adjacent frames in the set of vehicle frames has been determined: Obtain the total displacement of the target vehicle between the scanning time of the first multi-line scan frame and the scanning time of the second multi-line scan frame; Determine the number of scan frames contained in a set of current frames to obtain the target number, wherein the set of current frames includes scan frames whose scanning time is located between the scanning time of the first multi-line scan frame and the scanning time of the second multi-line scan frame. The vehicle displacement obtained by removing the total vehicle position from the difference between the target number and 1 is determined as the vehicle displacement of the target vehicle between the scanning times of two adjacent frames in a set of target frames, wherein the set of target frames is the scanning frame in the set of current frames for which the corresponding vehicle displacement is to be determined. The first multi-line scan frame is updated to the next multi-line scan frame in the group of multi-line scan frames to obtain the updated first multi-line scan frame, and the second multi-line scan frame is updated to the next multi-line scan frame in the group of multi-line scan frames to obtain the updated second multi-line scan frame.

6. The method according to claim 1, characterized in that, The first front frame is the front frame corresponding to the target vehicle that was last scanned by the multi-line scanning component before the vehicle's closing frame; the method further includes: Based on the second front frame of the target vehicle scanned by the multi-line scanning component, the second front distance of the target vehicle is determined, wherein the second front frame is the front frame corresponding to the target vehicle that is first scanned by the multi-line scanning component after the vehicle's rear frame; The reference displacement is determined by the quotient of the difference between the first vehicle front distance and the second vehicle front distance and the sum of the first frame number and the second frame number, wherein the second frame number is the number of scan frames in the set of scan frames whose scanning time is located between the scanning time of the vehicle tail frame and the scanning time of the second vehicle front frame.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: The multi-line scanning component acquires multiple candidate frames scanned during the same data scan, wherein each candidate frame is a data frame scanned by a different scanning component in the multi-line scanning component. The candidate frames in the plurality of candidate frames in which the vehicle height of the target vehicle is greater than or equal to a preset height threshold are determined as the first vehicle front frame.

8. A vehicle information detection system, characterized in that, include: Lateral scanning component, used to scan passing target vehicles laterally; A multi-line scanning component is located in front of the lateral scanning component in the driving direction of the target vehicle, and is used to perform multi-line scanning on the target vehicle; A data processing unit is used to acquire a set of scan frames obtained by the lateral scanning unit during lateral scanning, wherein the set of scan frames includes a vehicle tail frame of the target vehicle, the target vehicle is traveling in the target lane, and the vehicle tail frame is the last frame of the target vehicle in the set of scan frames; based on the first front frame of the target vehicle scanned by the multi-line scanning unit, a first front distance of the target vehicle is determined, wherein the first front distance is the distance between the front of the target vehicle and the multi-line scanning unit in the driving direction; based on the first frame number and the reference displacement of the target vehicle, a target displacement is determined, wherein the first frame number is the number of scan frames included in a set of reference frames. The set of reference frames includes scan frames whose scanning time is located between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. The reference displacement is the vehicle displacement of the target vehicle between two adjacent frames in the set of scan frames containing the vehicle rear frame and the set of reference frames. The target displacement is the vehicle displacement of the target vehicle between the scanning time of the first vehicle front frame and the scanning time of the vehicle rear frame. The vehicle length of the target vehicle is determined based on the first vehicle front distance, the preset component distance, and the target displacement. The preset component distance is the distance between the lateral scanning component and the multi-line scanning component in the driving direction, which is preset.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method of any one of claims 1 to 7.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method of any one of claims 1 to 7 through the computer program.

Images