CN112099042B

CN112099042B - Vehicle tracking method and system

Info

Publication number: CN112099042B
Application number: CN202010791596.7A
Authority: CN
Inventors: 杨勇刚; 胡攀攀; 李康; 蔡鄂
Original assignee: Wuhan Wanji Information Technology Co Ltd
Current assignee: Wuhan Wanji Information Technology Co Ltd
Priority date: 2020-08-07
Filing date: 2020-08-07
Publication date: 2024-04-12
Anticipated expiration: 2040-08-07
Also published as: CN112099042A

Abstract

The embodiment of the invention provides a vehicle tracking method and a system, wherein the method comprises the following steps: the method comprises the steps of acquiring position information of one or more laser radars in a target channel and a detection area corresponding to the laser radars, controlling the one or more laser radars to acquire data of a target vehicle in the detection area, generating a dynamic vehicle information matrix, determining real-time position information of the target vehicle in the target channel based on the position information of the one or more laser radars and the dynamic vehicle information matrix, solving the technical problem that the vehicle running in the tunnel is difficult to track in real time, and achieving the technical effect of improving the efficiency and the accuracy of positioning the position information of the running vehicle in the tunnel.

Description

Vehicle tracking method and system

Technical Field

The embodiment of the invention relates to the field of communication, in particular to a vehicle tracking method and a system.

Background

Along with the rapid development of economy, traffic volume is increased, tunnels are more and more, the lengths of the tunnels are from hundreds of meters to tens of kilometers, the number of vehicles running in the tunnels is also more and more, and great risks are brought to the safe operation management of the tunnels. The running vehicles in the tunnel are tracked in real time, so that the risk of tunnel operation management can be reduced.

At present, the real-time tracking of the vehicles in the tunnel is mainly realized by installing positioning receiving or transmitting equipment on the vehicles, and because the number of the middle-length tunnels is increased, the signals of the positioning equipment in the tunnels are easy to weaken or shield, the situation that the vehicles cannot be tracked and positioned occurs, the problem that the vehicles in the tunnels cannot be tracked in real time in the whole tunnels more or less exists in the related technology, and the risk is brought to the safe operation management of the tunnels.

Aiming at the technical problem that the real-time tracking of the vehicles running in the tunnel is difficult in the related art, no effective solution is proposed at present.

Disclosure of Invention

The embodiment of the invention provides a vehicle tracking method, a device, a system, a storage medium and an electronic device, which are used for at least solving the problem that the vehicle running in a tunnel is difficult to track in real time in the related technology.

According to an embodiment of the present invention, there is provided a vehicle tracking method including: acquiring position information of one or more laser radars in a target channel and a detection area corresponding to the laser radars; controlling the one or more laser radars to collect data of a target vehicle in the detection area, and generating a dynamic vehicle information matrix; real-time location information of the target vehicle within the target pathway is determined based on the location information of the one or more lidars and the dynamic vehicle information matrix.

According to another embodiment of the present invention, there is provided a vehicle tracking apparatus including: the acquisition module is used for acquiring the position information of one or more laser radars in the target channel and the detection area corresponding to the laser radars; the control module is used for controlling the one or more laser radars to collect data of a target vehicle in the detection area and generating a dynamic vehicle information matrix; and the determining module is used for determining real-time position information of the target vehicle in the target channel based on the position information of the one or more laser radars and the dynamic vehicle information matrix.

According to another embodiment of the present invention, there is provided a vehicle tracking system including: the laser radar data acquisition module is connected with the vehicle detection module and the laser radar and is used for acquiring target vehicle data in a target channel in real time based on the laser radar and sending the target vehicle data to the vehicle detection module; the vehicle detection module is connected with the laser radar data acquisition module and the vehicle tracking module and is used for calculating the target information of the target vehicle from the target vehicle data in real time; the vehicle tracking module is connected with the vehicle detection module and is used for determining real-time position information of the target vehicle in the target channel, position information of the same laser radar scanning the target vehicle and matching information of scanning the target vehicle between adjacent laser radars based on the target information; the laser radars are alternately arranged on two sides of the center of the target channel, the horizontal distance of each adjacent laser radar is within a preset horizontal distance threshold value range, the included angle between each laser radar and the horizontal direction is larger than a first angle threshold value, an overlapping area exists in the detection range of each adjacent laser radar, and the sum of the detection areas of all the laser radars covers the target channel; and the time synchronization module is connected with the laser radar data acquisition module, the vehicle detection module, the vehicle tracking module and the laser radar and is used for synchronizing the time of all devices in the target channel.

According to a further embodiment of the invention, there is also provided a computer readable storage medium having stored therein a computer program, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.

According to a further embodiment of the invention, there is also provided an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.

According to the invention, the position information of one or more laser radars in a target channel and the detection area corresponding to the laser radars are acquired; controlling the one or more laser radars to collect data of a target vehicle in the detection area, and generating a dynamic vehicle information matrix; based on the position information of the one or more laser radars and the dynamic vehicle information matrix, the real-time position information of the target vehicle in the target channel is determined, a mode of determining the real-time position information of the vehicle in a GPS (global positioning system) mode in the related art is replaced, the technical problem that the vehicle running in the tunnel is difficult to track in real time is solved, and the technical effect of improving the efficiency and the accuracy of positioning the position information of the running vehicle in the tunnel is achieved.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiments of the invention and together with the description serve to explain the invention and do not constitute a limitation on the invention. In the drawings:

fig. 1 is a block diagram of a hardware structure of a mobile terminal of a vehicle tracking method according to an embodiment of the present invention;

FIG. 2 is a flow chart of a vehicle tracking method according to an embodiment of the present invention;

FIG. 3 is a flow chart of another vehicle tracking method according to an embodiment of the invention;

FIG. 4 is a schematic diagram of a vehicle tracking method according to an embodiment of the present invention;

FIG. 5 is a flow chart of yet another vehicle tracking method according to an embodiment of the present invention;

FIG. 6 is a flow chart of yet another vehicle tracking method according to an embodiment of the invention;

fig. 7 is a schematic diagram of a vehicle tracking system according to an embodiment of the invention.

Fig. 8 is a block diagram of a vehicle tracking apparatus according to an embodiment of the present invention.

Detailed Description

Embodiments of the present invention will be described in detail below with reference to the accompanying drawings in conjunction with the embodiments.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order.

The method embodiments provided in the embodiments of the present application may be performed in a mobile terminal, a computer terminal or similar computing device. Taking the mobile terminal as an example, fig. 1 is a block diagram of a hardware structure of a mobile terminal of a vehicle tracking method according to an embodiment of the present invention. As shown in fig. 1, a mobile terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting of the structure of the mobile terminal described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.

The memory 104 may be used to store computer programs, such as software programs and modules of application software, such as computer programs corresponding to the vehicle tracking method in the embodiment of the present invention, and the processor 102 executes the computer programs stored in the memory 104 to perform various functional applications and data processing, that is, implement the method described above. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The transmission means 106 is arranged to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used to communicate with the internet wirelessly.

In this embodiment, a vehicle tracking method running on a mobile terminal, a computer terminal or a similar computing device is provided, and fig. 2 is a schematic flow chart of a vehicle tracking method according to an embodiment of the present invention, as shown in fig. 2, the flow chart includes the following steps:

s202, acquiring position information of one or more laser radars in a target channel and a detection area corresponding to the laser radars, wherein the position information is determined based on the distance between the one or more laser radars and the boundary of the target channel;

s204, controlling one or more laser radars to collect data of a target vehicle in a detection area, and generating a dynamic vehicle information matrix, wherein the target vehicle is a vehicle passing through a target channel, and the dynamic vehicle information matrix records the distance between the target vehicle and the laser radars;

S206, determining real-time position information of the target vehicle in the target channel based on the position information of the one or more laser radars and the dynamic vehicle information matrix.

Alternatively, in this embodiment, the location information of the one or more lidars may be obtained in advance by the server or the terminal, or may be determined according to a distance between the lidars and a distance between the lidars near the channel boundary and the channel boundary.

Alternatively, in the present embodiment, the target tunnel may include, but is not limited to, a tunnel capable of passing a target vehicle, for example, a railway tunnel, a canal tunnel, a mountain tunnel, a city underground tunnel, a submarine tunnel, a river crossing tunnel, etc., and the laser radar may include, but is not limited to, a 3D (three dimensional, three-dimensional) laser radar.

The target vehicle may include, but is not limited to, a vehicle, a train, a motorcycle, etc. capable of passing through the target aisle.

The above is merely an example, and the present embodiment is not limited in any way.

Alternatively, in the present embodiment, the detection area of the above-described lidar may be determined based on, but not limited to, the height, width, curvature of the channel, and the height and detection angle at which the lidar is mounted.

Optionally, in this embodiment, the distance between the target vehicle and the laser radar, the vehicle number, the laser radar number, the vehicle type, the vehicle length, the vehicle height, the vehicle speed, the lane, the position of the vehicle relative to the entrance or the exit of the tunnel, that is, the absolute position of the vehicle, the position of the vehicle relative to the laser radar, that is, the relative position of the vehicle, the detection time, the vehicle body reflection intensity value, the ratio of the vehicle body reflection intensity value to the relative position of the vehicle, the ratio of the number of points of the laser radar detected in the unit length to the relative position of the vehicle, the vehicle body reflection intensity value is the light intensity value received by the laser radar after reflection and is related to the reflectivity of the laser of the vehicle body to the surface of the vehicle, the distance and the angle of the laser radar, and other vehicle information or vehicle data related to the target vehicle.

Specifically, the lidar may be, but not limited to, installed at a position away from the first threshold of the road surface according to one or more factors of a tunnel height, a tunnel width, a tunnel curvature and a detection range of the lidar, wherein a detection angle of the lidar in a horizontal direction is larger than a second threshold, a horizontal direction angle resolution is within a third threshold range, a field angle of view of the lidar in a vertical direction is larger than a fourth threshold, a vertical direction angle resolution is within a fifth threshold range, the lidars are alternately installed at two sides of a center of the tunnel, a horizontal distance of each adjacent lidar is within a preset horizontal distance threshold range, and a detection range of each adjacent lidar has an overlapping area, and a sum of detection areas of all the lidars covers all the tunnels, wherein the first threshold, the second threshold, the third threshold, the fourth threshold and the fifth threshold may be preset according to practical situations.

The included angle between the laser radar and the horizontal direction is adjusted according to the tunnel width, the tunnel curvature and the laser radar detection range, when the detection range of the laser radar has no blind area, and the overlapping area is an area formed by overlapping the detection lines at the outermost sides of the two laser radars by 1/3 to 1/5; when the detection range of the laser radar has a blind area, the included angle between the laser radar and the horizontal direction is adjusted to enable the blind area to be smaller than a first threshold value, and the outermost detection line of the adjacent laser radar at least covers half of the blind area of the other side. The installation height of the laser radar is limited by one or more factors of tunnel height, tunnel width, tunnel curvature and detection range of the laser radar, so that the effective range of the laser radar for detecting the tunnel pavement reaches a preset range, namely all detection lines of the laser radar can cover all lanes in the tunnel, the maximum distance of intersection lines of adjacent detection lines for scanning the lane pavement does not exceed a certain threshold value, and the installation height of the laser radar is more than 5 meters.

Optionally, in this embodiment, taking the laser radar as a 3D laser radar as an example, a detection angle of the 3D laser radar in a horizontal direction is greater than a second threshold, a horizontal direction angle resolution is within a third threshold range, a field angle of view of the laser radar in a vertical direction is greater than a fourth threshold, a vertical direction angle resolution is within a fifth threshold range, a ranging distance of the 3D laser radar is greater than 50 meters, the 3D laser radar has a plurality of detection lines, a detection surface formed by rotating the detection lines around a road surface in a vertical direction has a plurality of intersections with the road surface, and a maximum interval between adjacent intersections is not greater than a preset intersection interval; the 3D laser radar is sequentially distributed from the tunnel entrance to the tunnel exit according to the detection range, and the detection ranges of the adjacent 3D laser radars are overlapped, and the sequence of vehicles passing through the detection areas of the 3D laser radars is as follows: the vehicle passes through the first 3D laser radar detection area, the vehicle passes through the detection area where the 3D laser radar and the second 3D laser radar overlap, the vehicle passes through the second 3D laser radar detection area, and the vehicle passes through all the detection areas of the 3D laser radars in the tunnel and passes through the tunnel in sequence.

When the included angles of adjacent detection lines of the 3D laser radar are different, the included angle of the adjacent detection line with the long scanning distance is required to be not larger than the included angle of the adjacent detection line with the short scanning distance; and (3) scanning a detection line with the closest 3D laser radar, and when the intersection line distance formed between the detection line and the road surface is greater than a set threshold value along the running direction of the vehicle, at least one detection line with the farthest adjacent 3D laser radar can detect the position right below the other 3D laser radar, and/or adjusting the installation angle of the 3D laser radar in the vertical direction, so that the 3D laser radar can detect the tunnel road surface without blind areas.

In addition, all 3D laser radars in the tunnel need to be subjected to coordinate calibration, and the coordinate calibration reference systems of all 3D laser radars are the same.

Optionally, in this embodiment, the data of the target vehicle may include, but is not limited to, one or more of a vehicle type, a vehicle height, a vehicle length, and a vehicle speed element, when the lidar detects that the vehicle enters the detection area, calculating vehicle information to form a vehicle information vector, calculating vehicle data at a next lidar detection time, calculating vehicle data at the time, adding one or more of a lane of the vehicle, an absolute position of the vehicle, a relative position of the vehicle, a reflection intensity value of the vehicle body, a detection time, a ratio of the reflection intensity value of the vehicle body to the relative position of the vehicle, and a ratio of a number of points of a unit length of the lidar detected vehicle to the relative position of the vehicle to the vehicle information vector of the vehicle, and updating one or more of the vehicle type, the vehicle height, the vehicle length, and the vehicle speed element of the vehicle by using a policy; when the vehicle passes through the detection area of the laser radar, the vehicle information vector contains the position information of the vehicle at each detection moment of passing through the laser radar; different vehicle information vectors detected by the laser radar in the scanning range of the laser radar are further formed into a vehicle information matrix of the laser radar, when a new vehicle enters the laser radar detection area, the vehicle information matrix is added with one vehicle information vector, when the vehicle leaves the laser radar detection area, the vehicle information matrix is reduced by one vehicle information vector, and the reduced vehicle information vector is added or updated into a vehicle whole-course tracking array.

Through the steps, the method comprises the steps of acquiring the position information of one or more laser radars in a target channel and a detection area corresponding to the laser radars, controlling the one or more laser radars to acquire data of a target vehicle in the detection area, generating a dynamic vehicle information matrix, determining the real-time position information of the target vehicle in the target channel based on the position information of the one or more laser radars and the dynamic vehicle information matrix, replacing the mode of determining the real-time position information of the vehicle in a related technology by means of GPS and the like, solving the technical problem that the vehicle running in a tunnel is difficult to track in real time, and improving the efficiency and accuracy of positioning the position information of the vehicle running in the tunnel.

In an alternative embodiment, determining the location information of the target vehicle within the target pathway based on the location information of the one or more lidars and the dynamic vehicle information matrix comprises:

in the case where the lidar is one, determining first target relative position information between the target vehicle and the lidar based on position information corresponding to the one lidar and a distance between the target vehicle and the lidar;

Determining second target relative position information between the plurality of target vehicles and the plurality of lidars based on the position information corresponding to the plurality of lidars and the distance between the plurality of target vehicles and each of the plurality of lidars in the case where the plurality of lidars are plural;

and determining real-time position information of the target vehicle in the target channel according to the first target relative position information or the second target relative position information.

Alternatively, in the present embodiment, the absolute position of the target vehicle is the position of the target vehicle with respect to the tunnel exit or entrance, and at this detection time, the vehicle absolute position is derived using the position of the lidar and the relative position of the target vehicle and the lidar, that is, the real-time position of the target vehicle within the tunnel; when the vehicle passes through the detection area of the 3D lidar, the vehicle information vector contains vehicle absolute position information and relative position information of the vehicle at each detection time by the 3D lidar.

In an alternative embodiment, in a case where the plurality of lidars is plural, determining second target relative position information between the plurality of target vehicles and the plurality of lidars based on the position information corresponding to the plurality of lidars and a distance between the plurality of target vehicles and each of the plurality of lidars includes: acquiring a first detection area corresponding to the first laser radar, a second detection area corresponding to the second laser radar and a third detection area formed by overlapping parts of the first detection area and the second detection area, wherein the first laser radar and the second laser radar are adjacent laser radars, and the detection areas comprise the first detection area, the second detection area and the third detection area; determining first relative position information of the first target vehicle based on the first position information of the first laser radar and a distance between the first target vehicle and the first laser radar when the first target vehicle is detected in the first detection area; determining second relative position information of the second target vehicle based on the second position information of the second lidar and a distance between the second target vehicle and the second lidar, in a case where the second target vehicle is detected by the second detection region; and determining the first target vehicle and the second target vehicle as the same target vehicle according to the target vehicle parameters recorded in the dynamic vehicle information matrix under the condition that the first target vehicle is detected by the first laser radar in the third detection area and the second target vehicle is detected by the second laser radar in the third detection area.

In an alternative embodiment, after the first target vehicle and the second target vehicle are determined to be the same target vehicle according to the target vehicle parameters recorded in the dynamic vehicle information matrix, the method further includes: and determining the second target relative position information according to the first relative position information and the second relative position information.

Optionally, in this embodiment, when the target vehicle passes through the previous 3D lidar detection area to the overlapping area, and when the vehicle passes through the overlapping area detected by the adjacent 3D lidar, the adjacent previous 3D lidar collects vehicle data, uploads the vehicle data to a vehicle information recognition unit corresponding to the 3D lidar, the vehicle information recognition unit calculates the vehicle data to obtain a first vehicle information vector, where the first vehicle information records the first position information, the adjacent next 3D lidar collects the vehicle data, uploads the first vehicle information to a vehicle information recognition unit corresponding to the lidar, the vehicle information recognition unit calculates the vehicle data to obtain a second vehicle information vector, where the second vehicle information records the second position information, the first vehicle information vector and a corresponding element in the second vehicle information vector are compared in similarity, and according to weights of the assigned elements, the calculation of the real-time position of the vehicle is completed, and according to the other lidar detection vehicle data, the confidence weights of the elements in the preassigned vehicle information vector are calculated, and the confidence coefficients of all the comparison elements are calculated, that the confidence coefficients of the comparison elements and the confidence coefficients of the elements in the preassigned vehicle information vector are the confidence coefficients of the vehicle information are equal to the confidence coefficients of the vehicle tracking elements, and the confidence coefficients of the vehicle tracking elements are equal to the confidence coefficients of successfully detected, and the vehicle tracking is matched with the vehicle information, and the confidence coefficients is greater than the confidence that the vehicle tracking is successfully detected by the vehicle, and the vehicle is matched with the vehicle; when a vehicle enters a second 3D laser radar after the vehicle runs out of an adjacent first 3D laser radar detection area, at the moment, the vehicle information vector of the vehicle detected by the first 3D laser radar is stored in vehicle whole-course tracking data, the vehicle information vector of the vehicle is not successfully matched with the vehicle information vector detected by the second 3D laser radar, at the current detection moment, the vehicle data is detected by the second 3D laser radar, the second vehicle information vector is calculated, the vehicle information vector which is the same as the number of the first 3D laser radar and is not successfully matched with the second 3D laser radar is searched from a vehicle whole-course tracking array, confidence is calculated sequentially with the second vehicle information vector according to the weight of a pre-allocated vehicle information vector element, the vehicle information vector with the highest confidence is selected, and the vehicle data vector which is matched with the second vehicle information vector in a tracking mode is the vehicle information vector with the highest confidence, namely the vehicle tracking matching is successful, and the process of matching from one 3D laser radar to the adjacent 3D laser radar is completed. In the process of matching the adjacent laser radar detection vehicle tracking, when the vehicle tracking module comprises more than one vehicle tracking calculation unit, the first vehicle tracking calculation unit is used for processing the vehicle tracking data detected by the first 3D laser radar, and the second vehicle tracking calculation unit is used for processing the vehicle tracking data detected by the second 3D laser radar, the vehicle data in the first vehicle tracking unit in the processing overlapping area is transmitted to the second vehicle tracking calculation unit through the main control unit, or the vehicle tracking data processed by the first vehicle tracking unit is transmitted to the second vehicle tracking calculation unit through the main control unit, so that the second vehicle tracking calculation unit is convenient to process the vehicle tracking data.

And similarly, when the vehicle exits the tunnel, all 3D laser radars in the tunnel detect the vehicle and obtain corresponding vehicle tracking data, and all absolute position information of the vehicle passing through the tunnel is extracted from the vehicle whole-course tracking array according to the laser radar numbers sequentially passing through the vehicle numbers, namely all track information of the vehicle passing through the tunnel, the vehicle whole-course position vector storage is formed, and the vehicle information in the vehicle whole-course tracking array is deleted.

By the method and the device, real-time position information of the target vehicle in the whole process of the target channel can be effectively obtained.

In an alternative embodiment, acquiring location information of one or more lidars within the target pathway includes: placing the one or more lidars in a first coordinate system, and determining an abscissa X of the lidar in the first coordinate system and an ordinate Y of the lidar in the first coordinate system; position information of one or more lidars in the target pathway is determined based on the abscissa X and the ordinate Y.

In an alternative embodiment, acquiring location information of one or more lidars within the target pathway includes: placing the laser radar in a first coordinate system, and determining an abscissa X of the laser radar in the first coordinate system according to the preset width of the target channel and/or the distance between the laser radar and the single side or two sides of the target channel; determining an ordinate Y of the laser radar in the first coordinate system according to the distance between the laser radar and the boundary of the target channel under the condition that the number of the laser radars is one; determining position information of the one lidar based on the abscissa X and the ordinate Y; when the number of the laser radars is multiple, the adjacent laser radars detect the same target vehicle when the target vehicle passes through the third detection area, so that the relative positions of the target vehicle relative to the adjacent laser radars are obtained; determining the sum of the relative positions of the vehicles along the driving direction as the distance of the adjacent laser radar in the driving direction; detecting the same target vehicle for multiple times, calculating an average value of the distances of the adjacent laser radars in the driving direction, and determining the average value as the distance between the adjacent laser radars; determining an ordinate Y of the laser radar in the first coordinate system according to the distance between the adjacent laser radars and the distances between the multiple laser radars and the boundary of the target channel; position information of the plurality of lidars is determined based on the abscissa X and the ordinate Y.

Alternatively, in the present embodiment, in the case where there is only one of the number of lidars, one lidar is placed in the first coordinate system, and its position information is determined according to the width of the tunnel and/or the distance of one side or both sides of the lidar detection target path.

Optionally, in this embodiment, fig. 3 is a flowchart of another vehicle tracking method according to an embodiment of the present invention, and as shown in fig. 3, the step of obtaining the position information of the multiple lidars in the target channel may include, but is not limited to, the following steps:

s302: placing all the laser radars in the same coordinate system, and calculating the position X of the laser radars in the width direction of the tunnel according to the width of the tunnel and/or the distance between one side or two sides of the tunnel detected by the laser radars;

s304: when a vehicle passes through the overlapping area, adjacent laser radars detect the same position of the vehicle to obtain positions of the vehicle relative to the adjacent laser radars respectively, the sum of the relative positions of the vehicle along the driving direction is the distance of the adjacent laser radars in the driving direction, the positions of the vehicle in the overlapping area are detected for a plurality of times, the average value of the distances is calculated to obtain the accurate distance of the adjacent laser radars, and then the distances of all the adjacent laser radars are calculated;

Wherein the same location of the vehicle includes, but is not limited to, one or more of the head, tail, bulge or recess of the vehicle itself, and axle of the vehicle.

S306: and calculating the position Y of all the laser radars along the vehicle direction according to the determined distance between one or more laser radars and the entrance or exit of the tunnel and the distance between all the adjacent laser radars, and completing the position calibration of the laser radars.

And S308, numbering the laser radars from the entrance to the exit or from the exit to the entrance of the tunnel sequentially, giving out plane coordinates of the laser radars according to the distance between the laser radars and the exit or entrance of the tunnel, and forming inherent information data of the laser radars, namely position information of all the laser radars, wherein in FIG. 4, the laser radars can be distributed in a target channel in a mode shown in FIG. 4, the boundaries of the target channel are the boundaries 402 and 408 shown in FIG. 4, the first laser radar 404 and the second laser radar 406 are adjacent, the running direction of a target vehicle is a direction 410, and a detection overlapping area 412 of the adjacent laser radars.

In an alternative embodiment, in a case where the first target vehicle is detected by the first lidar in the third detection area and the second target vehicle is detected by the second lidar in the third detection area, determining the first target vehicle and the second target vehicle as the same target vehicle according to the target vehicle parameters recorded in the dynamic vehicle information matrix includes: acquiring first target vehicle data corresponding to a first target vehicle, which is acquired by a first laser radar, and generating a first target vehicle vector; acquiring second target vehicle data corresponding to a second target vehicle acquired by a second laser radar, and generating a second target vehicle vector; calculating the similarity of the first target vehicle vector and the second target vehicle vector, and generating a first target confidence; and determining the first target vehicle and the second target vehicle as the same target vehicle when the first target confidence is greater than the confidence threshold.

Optionally, in this embodiment, fig. 5 is a schematic flow chart of another vehicle tracking method according to an embodiment of the present invention, as shown in fig. 5, the steps of the vehicle matching method between adjacent lidars may be as follows:

s502, when the vehicle runs to two adjacent laser radar detection areas, namely an overlapping area, calculating a first vehicle information vector according to one laser radar detection vehicle data;

s504, calculating a second vehicle information vector according to the vehicle data detected by the other laser radar;

s506, calculating the confidence coefficient of the vehicle information vector according to the weight of the confidence coefficient of each element in the pre-allocated vehicle information vector;

s508, when the confidence coefficient is larger than a confidence coefficient threshold value, the two adjacent laser radars are considered to detect the same vehicle;

fig. 6 is a schematic flow chart of another vehicle tracking method according to an embodiment of the present invention, as shown in fig. 6, the following steps of the vehicle matching method between adjacent lidars may be further shown:

s604, after the vehicle runs out of the adjacent first laser radar detection area, the second laser radar detects that the vehicle enters, and the second laser radar detects vehicle data to calculate a second vehicle information vector;

S606, searching a vehicle information vector which is the same as the number of the first laser radar and is not successfully matched with the tracking of the second laser radar from the vehicle whole-course tracking array;

s608, according to the weight of the pre-allocated vehicle information vector element and the second vehicle information vector, calculating the confidence coefficient in sequence;

and S610, selecting a group of vehicle information vectors with highest confidence and greater than a confidence threshold, and tracking matched data vectors for the second vehicle information vector.

Wherein the vehicle information vector includes at least one or more of the following elements: the method comprises the steps of vehicle numbering, laser radar numbering, vehicle type, vehicle length, vehicle height, vehicle speed, lane, position of a vehicle relative to a tunnel entrance or exit, namely the absolute position of the vehicle, the position of the vehicle relative to the laser radar, namely the relative position of the vehicle, detection time, vehicle body reflection intensity value, ratio of vehicle body reflection intensity value to the relative position of the vehicle, ratio of the number of laser radar detection vehicle unit length to the relative position of the vehicle, vehicle body reflection intensity value being the light scanning emitted by the laser radar on the vehicle body, and the light intensity value received by the laser radar after reflection, wherein the value is related to the reflectivity of the vehicle body to laser, the vehicle body surface, the distance and the angle of the laser radar.

Further, in one detection period of the laser radar, one or more detection lines detect the vehicle, and the ratio of the number of points of the detection line detecting the vehicle to the length of the number of points enclosed by the vehicle body is the number of points of the laser radar detecting the unit length of the vehicle, wherein the value is related to the angular resolution of the plane of the laser radar detection line, the size of the vehicle and the distance position of the vehicle and the laser radar.

The method comprises the steps that similarity comparison is carried out between a first vehicle information vector of a vehicle detected by a first adjacent laser radar and a corresponding element in a second vehicle information vector of the vehicle detected by a second laser radar, and according to the weight of the distributed element, the sum of the similarity of all the compared elements and the weight products corresponding to the corresponding element is calculated, namely the confidence coefficient of vehicle tracking matching, and when the confidence coefficient is larger than a confidence coefficient threshold, the vehicle information vector is considered to be successfully matched, namely the vehicle tracking matching is successful.

The element similarity calculation method of the first element in one vehicle information vector and the corresponding second element in the other vehicle information vector is as follows:

when the element is of a numerical value type, the absolute value of the difference between the first element and the second element, the ratio of the absolute value of the difference between the first element and half of the sum of the first element and the second element and the absolute value of the difference between the ratio and 1 are the similarity of the first element and the second element;

When the element is of a non-numerical type, according to the classification processing of the element, the first element and the second element do not belong to the same major class; the first element and the second element belong to the same major class, but do not belong to the same minor class; the first element is identical to the second element, and the corresponding similarity is given respectively.

Vehicle information, forming a vehicle information vector, wherein the vehicle information vector at least comprises one or more of the following elements: the method comprises the steps of vehicle numbering, laser radar numbering, vehicle type, vehicle length, vehicle height, vehicle speed, lane, position of a vehicle relative to a tunnel entrance or exit, namely, vehicle absolute position, position of the vehicle relative to the laser radar, namely, vehicle relative position, detection time, vehicle reflection intensity value, ratio of vehicle reflection intensity value to vehicle relative position, and ratio of the number of points of the unit length of the laser radar to the vehicle relative position; further, since the detection range of the 3D lidar is relatively large, the dynamic vehicle information matrix of the lidar is formed by the vehicle information vectors of all vehicles detected in one 3D lidar detection range; calculating vehicle data at the next detection moment of the same 3D laser radar, adding one or more of a lane, a vehicle absolute position, a vehicle relative position, a vehicle reflection intensity value, a detection moment, a ratio of a vehicle reflection intensity value to a vehicle relative position, and a ratio element of the number of points of a laser radar detection vehicle unit length to the vehicle relative position of the vehicle at the moment into a vehicle information vector of the vehicle, and updating one or more of a vehicle type, a vehicle height, a vehicle length and a vehicle speed element of the vehicle by adopting a strategy; preferably, in the 3D lidar detection area, when the vehicle approaches the 3D lidar, one or more elements of the vehicle intrinsic feature in the vehicle information vector are updated in real time, and when the vehicle is far away from the 3D lidar, the vehicle intrinsic feature element in the vehicle information vector is not updated, wherein the vehicle intrinsic feature at least comprises one or more elements of a vehicle type, a vehicle length and a vehicle height; the position of the vehicle relative to the tunnel exit or entrance is obtained by adopting the position of the laser radar and the relative position of the vehicle at the detection moment, and the position is also the real-time position of the vehicle in the tunnel; when the vehicle passes through the detection area of the 3D laser radar, the vehicle information vector comprises vehicle absolute position information and relative position information of the vehicle at each detection moment of passing through the 3D laser radar; different vehicle information vectors detected by the 3D laser radar in the scanning range form a vehicle information matrix of the 3D laser radar, when a new vehicle enters the 3D laser radar detection area, the vehicle information matrix is added with a vehicle information vector of the new vehicle, when the vehicle leaves the 3D laser radar detection area, the vehicle information matrix is reduced by a vehicle information vector leaving the vehicle, and the reduced vehicle information vector is added or updated into a vehicle whole-course tracking array.

When the vehicle tracking module comprises more than one vehicle tracking calculation unit, in adjacent laser radar vehicle tracking matching, the first vehicle tracking calculation unit processes the vehicle tracking data detected by the first laser radar, and the second vehicle tracking calculation unit processes the vehicle tracking data detected by the second laser radar, the vehicle data in the first vehicle tracking unit, which are processed in the overlapping area, are transmitted to the second vehicle tracking unit through the main control unit, so that the second vehicle tracking calculation unit is convenient to process the vehicle tracking data.

When the vehicle exits the tunnel, all absolute position information of the vehicle passing through the tunnel is extracted from the vehicle whole course tracking array according to the laser radar numbers sequentially passing through the vehicle numbers, namely all track information of the vehicle passing through the tunnel, the vehicle whole course position vector storage is formed, and the vehicle information in the vehicle whole course tracking array is deleted.

In an alternative embodiment, where the target confidence level is greater than the confidence threshold, determining the first target vehicle and the second target vehicle as the same target vehicle includes:

assigning a corresponding weight value to each element in the first target vehicle vector, the weight value being a confidence that each element can be used to represent the target vehicle;

A target confidence is determined based on the weight value and the first and second target vehicle vectors.

Optionally, in this embodiment, a vehicle information vector which has not been successfully tracked and matched recently is found from a vehicle information matrix of the lidar, and the vehicle information vector detected by the lidar in a current detection period, and a confidence coefficient is calculated by using a preset weight value of the vehicle information vector according to a time difference and a distance that the vehicle passes in the time, and if the confidence coefficient is greater than a set confidence coefficient threshold, the tracking and matching are successful;

when the overlapping area is shielded by the vehicle, the adjacent second laser radar detects that a new vehicle enters the detection area where the new vehicle is located, a vehicle information vector of the new vehicle is calculated, and the vehicle information vector which is successfully matched with the vehicle information matrix of the adjacent first laser radar is not tracked, and/or the vehicle information vector which is the same as the number of the first laser radar and successfully matched with the second laser radar is searched from the vehicle whole-course tracking array, and the confidence is calculated by adopting the weight of a fourth set of vehicle information vector according to the time difference and the distance of the vehicle passing in the time, and when the confidence is larger than the set confidence threshold, the vehicle tracking matching is successful.

In an alternative embodiment, the method further comprises: controlling the third laser radar to detect a fourth detection area, wherein the detection area comprises a fourth detection area, the fourth detection area corresponds to the third laser radar, and the third laser radar is adjacent to the second laser radar;

under the condition that the second target vehicle is not detected in the fourth detection area and the third target vehicle is detected, acquiring a second vehicle information vector from the dynamic vehicle information matrix, and generating a third vehicle information vector according to the acquired third target vehicle data of the third target vehicle;

calculating the similarity between the second target vehicle vector and the third target vehicle vector according to the first time period and the passing distance of the third target vehicle in the first time period, and generating a second target confidence coefficient;

and determining the second target vehicle and the third target vehicle as the same target vehicle in the case that the second target confidence is greater than the confidence threshold.

Optionally, in this embodiment, a vehicle shielding occurs in a region detected by a laser radar, a ratio of a vehicle body reflection intensity value of a vehicle detected by the laser radar to a vehicle relative position in a current detection period, a ratio of a point number of a unit length of the vehicle detected by the laser radar to the vehicle relative position are calculated, a ratio of a vehicle body reflection intensity value in a vehicle information vector which is not successfully matched with a tracking information matrix of the laser radar to the vehicle relative position, and a ratio of a point number of a unit length of the vehicle detected by the laser radar to the vehicle relative position are sequentially calculated, a weight of a preset ratio is selected, a confidence degree of tracking matching is calculated, and when the confidence degree is greater than a set confidence degree threshold, the tracking matching is successful;

Further, the ratio of the currently detected vehicle body reflection intensity value to the vehicle relative position, the ratio of the number of points of the unit length of the vehicle to the vehicle relative position are sequentially calculated with the ratio of the vehicle body reflection intensity value to the vehicle relative position and the ratio of the number of points of the unit length of the vehicle to the vehicle relative position in a vehicle information vector which is not successfully matched with the tracking information matrix, the similarity of the ratio is calculated respectively, the sum of the products of the similarity and the weights corresponding to the ratio is the confidence of the vehicle tracking matching, and the confidence is larger than a confidence threshold value, so that the vehicle information vector is successfully matched.

When the overlapping area is shielded by the vehicle, the ratio of the reflected intensity value of the vehicle body to the relative position of the vehicle, the ratio of the number of points of the laser radar detection vehicle unit length to the relative position of the vehicle are calculated under the condition that the adjacent second laser radar detects that a new vehicle enters the detection area where the new vehicle is located, vehicle information vectors which are not successfully tracked and matched with the adjacent first laser radar in the vehicle information matrix are sequentially searched for, and/or the vehicle information vectors which are the same as the first laser radar in number and are not successfully tracked and matched with the second laser radar are searched for in the vehicle whole-course tracking array, the ratio of the reflected intensity value of the vehicle to the relative position of the vehicle, the ratio of the number of points of the laser radar detection vehicle unit length to the relative position of the vehicle are selected, the preset weight of another ratio is calculated, and the confidence of tracking and the vehicle tracking and the matching are successfully performed when the confidence is larger than the set confidence threshold.

Further, the ratio of the reflected intensity value of the vehicle body detected by the second laser radar to the relative position of the vehicle, the ratio of the number of the unit length of the vehicle to the relative position of the vehicle, and the vehicle information vector which is not successfully tracked and matched with the adjacent first laser radar in the vehicle information matrix in sequence, and/or the vehicle information vector which is the same as the number of the first laser radar and is not successfully tracked and matched with the second laser radar in the vehicle information vector is searched from the vehicle whole-course tracking array, the ratio of the reflected intensity value of the vehicle to the relative position of the vehicle and the ratio of the number of the unit length of the vehicle to the relative position of the vehicle are respectively calculated, the sum of products of the similarity and the ratio is the confidence of the vehicle tracking and the matching, and the vehicle information vector which has the maximum confidence and is greater than the confidence threshold is selected, so that the vehicle information vector is successfully matched.

In an alternative embodiment, controlling one or more lidars to collect data of a target vehicle generates a dynamic vehicle information matrix, comprising:

controlling one or more lidars to collect data of a target vehicle of at least one of:

the method comprises the steps of determining the absolute position of a target vehicle, the position of the target vehicle relative to a laser radar, the vehicle body reflection intensity value of the target vehicle, the ratio of the vehicle body reflection intensity value to the position of the target vehicle relative to the laser radar, and the ratio of the number of points of the unit length of the laser radar detection target vehicle to the relative position of the target vehicle, wherein the number of points of the unit length of the laser radar detection target vehicle is the ratio of the number of points of the detection target vehicle to the length of the point enclosed on the target vehicle body in one detection period of the laser radar through one or more detection lines; .

Generating one or more vehicle information vectors according to the data of the target vehicle, wherein the one or more vehicle information vectors are in one-to-one correspondence with the target vehicle;

a dynamic vehicle information matrix is generated based on the one or more vehicle information vectors.

Optionally, in this embodiment, specifically, when the lidar detects that the vehicle enters the detection area, vehicle information is calculated to form a vehicle information vector, at the next lidar detection time, vehicle data of the time is calculated, one or more of a lane, an absolute position of the vehicle, a relative position of the vehicle, a reflection intensity value of the vehicle body, a detection time, a ratio of the reflection intensity value of the vehicle body to the relative position of the vehicle, and a ratio of a point number of a unit length of the lidar detected vehicle to the relative position of the vehicle are added to the vehicle information vector of the vehicle, and one or more of a vehicle type, a vehicle height, a vehicle length, and a vehicle speed element of the vehicle are updated by using a policy.

In an alternative embodiment, after controlling the one or more lidars to collect data of the target vehicle and generating the dynamic vehicle information matrix, the method further comprises:

under the condition that the laser radar detects that the target vehicle runs in the direction of approaching the laser radar, the data of the target vehicle are updated in real time by using a preset updating strategy;

When the lidar detects that the target vehicle is traveling in a direction away from the lidar, data of the target vehicle is maintained.

Optionally, in this embodiment, in one lidar detection area, when the vehicle approaches the lidar, one or more elements of the vehicle intrinsic feature in the vehicle information vector are updated in real time, and when the vehicle is far away from the lidar, the vehicle intrinsic feature element in the vehicle information vector is not updated, where the vehicle intrinsic feature at least includes one or more elements of a vehicle type, a vehicle length, and a vehicle height.

Further, the real-time position of the vehicle relative to the tunnel exit or entrance is derived using the position of the lidar and the real-time position of the vehicle relative to the lidar (i.e., the vehicle relative position).

In an alternative embodiment, there is also provided a vehicle tracking system, as shown in fig. 7, comprising:

the laser radar data acquisition module 702 is connected with the vehicle detection module and the laser radar, and is used for acquiring target vehicle data in a target channel in real time based on the laser radar and sending the target vehicle data to the vehicle detection module;

the vehicle detection module 704 is configured to calculate, in real time, target information of the target vehicle from the target vehicle data;

The vehicle tracking module 706 is configured to determine real-time position information of the target vehicle in the target channel, position information of the target vehicle scanned by the same lidar, and matching information of the target vehicle between adjacent lidars;

the lidars 708 are alternately installed at two sides of the center of the target channel, the horizontal distance of the adjacent lidars is within a preset horizontal distance threshold, the included angle between the lidars and the horizontal direction is greater than a first angle threshold, an overlapping area exists in the detection ranges of the adjacent lidars, and the sum of the detection areas of all the lidars covers the target channel;

and the time synchronization module 710 is connected with the laser radar data acquisition module 702, the vehicle detection module, the vehicle tracking module 706 and the laser radar 708 and is used for synchronizing the time of all devices in the target channel.

From the description of the above embodiments, it will be clear to a person skilled in the art that the method according to the above embodiments may be implemented by means of software plus the necessary general hardware platform, but of course also by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present invention.

The present embodiment also provides a vehicle tracking device, which is used to implement the foregoing embodiments and preferred embodiments, and will not be described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

Fig. 8 is a block diagram of a vehicle tracking apparatus according to an embodiment of the present invention, as shown in fig. 7, including:

an acquiring module 802, configured to acquire position information of one or more lidars in a target channel and a detection area corresponding to the lidar;

a control module 804, configured to control the one or more lidars to collect data of a target vehicle in the detection area, and generate a dynamic vehicle information matrix;

a determining module 806 is configured to determine real-time location information of the target vehicle within the target lane based on the location information of the one or more lidars and the dynamic vehicle information matrix.

In an alternative embodiment, the determining module 806 includes:

A first determining unit configured to determine first target relative position information between the target vehicle and the lidar based on position information corresponding to the one lidar and a distance between the target vehicle and the lidar, in a case where the lidar is one;

a second determining unit configured to determine second target relative position information between the plurality of target vehicles and the plurality of lidars based on position information corresponding to the plurality of lidars and a distance between the plurality of target vehicles and each of the plurality of lidars, in a case where the plurality of lidars are plural;

and the third determining unit is used for determining real-time position information of the target vehicle in the target channel according to the first target relative position information or the second target relative position information.

In an alternative embodiment, the first determining unit includes:

the first acquisition subunit is configured to acquire a first detection area corresponding to a first laser radar, a second detection area corresponding to a second laser radar, and a third detection area formed by an overlapping portion of the first detection area and the second detection area, where the first laser radar and the second laser radar are adjacent laser radars, and the detection areas include the first detection area, the second detection area, and the third detection area;

A first determination subunit configured to determine, when the first detection region detects a first target vehicle, first relative position information of the first target vehicle based on first position information of a first lidar and a distance between the first target vehicle and the first lidar;

a second determination subunit configured to determine, when a second target vehicle is detected in the second detection region, second relative position information of a second target vehicle based on second position information of a second laser radar and a distance between the second target vehicle and the second laser radar;

a third determining subunit, configured to determine, when the first target vehicle is detected by the first lidar in the third detection area and the second target vehicle is detected by the second lidar in the third detection area, the first target vehicle and the second target vehicle as the same target vehicle according to the target vehicle parameters recorded in the dynamic vehicle information matrix;

and a fourth determination subunit configured to determine, when the first target vehicle and the second target vehicle are the same target vehicle, the second target relative position information according to the first relative position information and the second relative position information.

In an alternative embodiment, the acquiring module 802 is configured to acquire location information of a plurality of lidars in the target channel by:

placing the one or more lidars in a first coordinate system, and determining an abscissa X of the lidar in the first coordinate system according to a predetermined width of the target channel and/or a distance between the lidar and a single side or two sides of the target channel;

under the condition that the target vehicle passes through the third detection area, the adjacent laser radars detect the same target vehicle, and the relative positions of the target vehicle relative to the adjacent laser radars are obtained;

determining the sum of the relative positions of the vehicles along the driving direction as the distance of the adjacent laser radar in the driving direction;

detecting the same target vehicle for multiple times, calculating an average value of the distances of the adjacent laser radars in the driving direction, and determining the average value as the distance between the adjacent laser radars;

determining an ordinate Y of the laser radar in the first coordinate system according to the distance between the adjacent laser radars and the distances between the multiple laser radars and the boundary of the target channel;

Position information of the plurality of lidars is determined based on the abscissa X and the ordinate Y.

In an alternative embodiment, the acquiring module 802 is configured to acquire the location information of the multiple lidars in the target channel by:

placing the laser radar in a first coordinate system, and determining an abscissa X of the laser radar in the first coordinate system according to the preset width of the target channel and/or the distance between the laser radar and the single side or two sides of the target channel;

determining an ordinate Y of the laser radar in the first coordinate system according to the distance between the laser radar and the boundary of the target channel;

position information of the one lidar is determined based on the abscissa X and the ordinate Y.

In an alternative embodiment, the third determining subunit includes:

the first acquisition sub-module is used for acquiring first target vehicle data corresponding to the first target vehicle and acquired by the first laser radar, and generating a first target vehicle vector;

the second acquisition sub-module is used for acquiring second target vehicle data corresponding to the second target vehicle acquired by the second laser radar and generating a second target vehicle vector;

The generation sub-module is used for calculating the similarity of the first target vehicle vector and the second target vehicle vector and generating a first target confidence coefficient;

and the determining submodule is used for determining the first target vehicle and the second target vehicle as the same target vehicle under the condition that the first target confidence is larger than a confidence threshold.

In an alternative embodiment, the determining submodule is configured to determine the first target vehicle and the second target vehicle as the same target vehicle when the target confidence is greater than a confidence threshold value by:

the target confidence is determined based on the weight value and the first and second target vehicle vectors.

In an alternative embodiment, the apparatus is further adapted to:

controlling a third laser radar to detect a fourth detection area, wherein the detection area comprises the fourth detection area, the fourth monitoring area corresponds to the third laser radar, and the third laser radar is adjacent to the second laser radar;

When the second target vehicle is not detected in the fourth detection area and a third target vehicle is detected, acquiring the second vehicle information vector from the dynamic vehicle information matrix, and generating a third vehicle information vector according to the acquired third target vehicle data of the third target vehicle;

calculating the similarity between the second target vehicle vector and the third target vehicle vector according to the first time period and the distance passed by the third target vehicle in the first time period, and generating a second target confidence;

and determining the second target vehicle and the third target vehicle as the same target vehicle when the second target confidence is greater than the confidence threshold.

In an alternative embodiment, the control module 804 includes:

a control unit for controlling the one or more lidars to acquire data of the target vehicle for at least one of:

the method comprises the steps that the absolute position of a target vehicle, the position of the target vehicle relative to a laser radar, the vehicle body reflection intensity value of the target vehicle, the ratio of the vehicle body reflection intensity value to the position of the target vehicle relative to the laser radar, the laser radar detects the ratio of the number of points of the unit length of the target vehicle to the relative position of the target vehicle, wherein the number of points of the unit length of the target vehicle detected by the laser radar is the ratio of the number of points of the target vehicle to the length enclosed by the number of points on the target vehicle in one detection period of the laser radar, and the detection line detects the target vehicle through one or more detection lines; .

The first generation unit is used for generating one or more vehicle information vectors according to the data of the target vehicle, wherein the one or more vehicle information vectors are in one-to-one correspondence with the target vehicle;

a second generation unit for generating the dynamic vehicle information matrix based on the one or more vehicle information vectors.

In an alternative embodiment, the apparatus is further adapted to: after the one or more lidars are controlled to collect data of a target vehicle and generate a dynamic vehicle information matrix, under the condition that the lidar detects that the target vehicle runs in a direction close to the lidar, the data of the target vehicle are updated in real time by using a preset updating strategy; and when the laser radar detects that the target vehicle runs in the direction away from the laser radar, maintaining the data of the target vehicle.

It should be noted that each of the above modules may be implemented by software or hardware, and for the latter, it may be implemented by, but not limited to: the modules are all located in the same processor; alternatively, the above modules may be located in different processors in any combination.

Embodiments of the present invention also provide a computer readable storage medium having a computer program stored therein, wherein the computer program is arranged to perform the steps of any of the method embodiments described above when run.

In the present embodiment, the above-described computer-readable storage medium may be configured to store a computer program for performing the steps of:

s1, acquiring position information of one or more laser radars in a target channel and a detection area corresponding to the laser radars;

s2, controlling one or more laser radars to collect data of a target vehicle in a detection area, and generating a dynamic vehicle information matrix;

and S3, determining real-time position information of the target vehicle in the target channel based on the position information of the one or more laser radars and the dynamic vehicle information matrix.

The computer readable storage medium is further arranged to store a computer program for performing the steps of:

In one exemplary embodiment, the computer readable storage medium may include, but is not limited to: a usb disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing a computer program.

An embodiment of the invention also provides an electronic device comprising a memory having stored therein a computer program and a processor arranged to run the computer program to perform the steps of any of the method embodiments described above.

In an exemplary embodiment, the electronic apparatus may further include a transmission device connected to the processor, and an input/output device connected to the processor.

In an exemplary embodiment, the above-mentioned processor may be arranged to perform the following steps by means of a computer program:

Specific examples in this embodiment may refer to the examples described in the foregoing embodiments and the exemplary implementation, and this embodiment is not described herein.

It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A vehicle tracking method, comprising:

acquiring position information of one or more laser radars in a target channel and a detection area corresponding to the laser radars;

controlling the one or more laser radars to collect data of a target vehicle in the detection area, and generating a dynamic vehicle information matrix;

determining real-time location information of the target vehicle within the target pathway based on the location information of the one or more lidars and the dynamic vehicle information matrix;

the controlling the one or more lidars to collect data of a target vehicle, generating a dynamic vehicle information matrix, includes: controlling the one or more lidars to collect data of the target vehicle for at least one of: the method comprises the steps that the absolute position of a target vehicle, the position of the target vehicle relative to a laser radar, the vehicle body reflection intensity value of the target vehicle, the ratio of the vehicle body reflection intensity value to the position of the target vehicle relative to the laser radar, the laser radar detects the ratio of the number of points of the unit length of the target vehicle to the relative position of the target vehicle, wherein the number of points of the unit length of the target vehicle detected by the laser radar is the ratio of the number of points of the target vehicle to the length enclosed by the number of points on the target vehicle in one detection period of the laser radar, and the detection line detects the target vehicle through one or more detection lines; generating one or more vehicle information vectors according to the data of the target vehicle, wherein the one or more vehicle information vectors are in one-to-one correspondence with the target vehicle; the dynamic vehicle information matrix is generated based on the one or more vehicle information vectors.

2. The method of claim 1, wherein determining location information of the target vehicle within the target pathway based on the location information of the one or more lidars and the dynamic vehicle information matrix comprises:

determining first target relative position information between the target vehicle and the lidar based on position information corresponding to the one lidar and a distance between the target vehicle and the lidar in a case where the lidar is one;

determining second target relative position information between the plurality of target vehicles and the plurality of lidars based on the position information corresponding to the plurality of lidars and the distance between the plurality of target vehicles and each of the plurality of lidars when the plurality of lidars is plural;

3. The method of claim 2, wherein, in the case where the lidar is plural, determining second target relative position information between the plurality of target vehicles and the plurality of lidars based on the position information corresponding to the plurality of lidars and the distance between the plurality of target vehicles and each of the plurality of lidars, comprises:

Acquiring a first detection area corresponding to a first laser radar, a second detection area corresponding to a second laser radar and a third detection area formed by overlapping parts of the first detection area and the second detection area, wherein the first laser radar and the second laser radar are adjacent laser radars, and the detection areas comprise the first detection area, the second detection area and the third detection area;

determining first relative position information of a first target vehicle based on first position information of a first laser radar and a distance between the first target vehicle and the first laser radar when the first detection area detects the first target vehicle;

determining second relative position information of a second target vehicle based on second position information of a second laser radar and a distance between the second target vehicle and the second laser radar when the second target vehicle is detected in the second detection area;

and determining the first target vehicle and the second target vehicle as the same target vehicle according to the target vehicle parameters recorded in the dynamic vehicle information matrix when the first target vehicle is detected by the first laser radar in the third detection area and the second target vehicle is detected by the second laser radar in the third detection area.

4. A method according to claim 3, wherein obtaining location information of one or more lidars within the target pathway comprises:

placing the one or more lidars in a first coordinate system, and determining an abscissa X of the lidar in the first coordinate system and an ordinate Y of the lidar in the first coordinate system;

position information of one or more lidars in the target pathway is determined based on the abscissa X and the ordinate Y.

5. The method of claim 4, wherein obtaining location information for one or more lidars within the target pathway comprises:

placing the laser radar in a first coordinate system, and determining an abscissa X of the laser radar in the first coordinate system according to a preset width of the target channel and/or a distance of the laser radar on one side or two sides of the target channel in the width direction of the tunnel;

determining an ordinate Y of the laser radar in the first coordinate system according to the distance between the laser radar and the entrance or the exit of the target channel under the condition that the number of the laser radars is one;

Determining position information of the one lidar based on the abscissa X and the ordinate Y;

when the number of the laser radars is multiple, the adjacent laser radars detect the same target vehicle when the target vehicle passes through the third detection area, so that the relative positions of the target vehicle relative to the adjacent laser radars are obtained;

determining an ordinate Y of the laser radars in the first coordinate system according to the distances between the adjacent laser radars and the distances between the multiple laser radars and the entrance or the exit of the target channel;

6. A method according to claim 3, wherein determining the first target vehicle and the second target vehicle as the same target vehicle based on target vehicle parameters recorded in the dynamic vehicle information matrix in the case where the first target vehicle is detected by the first lidar in the third detection area and the second target vehicle is detected by the second lidar in the third detection area, comprises:

Acquiring first target vehicle data corresponding to the first target vehicle, which is acquired by the first laser radar, and generating a first target vehicle vector;

acquiring second target vehicle data corresponding to the second target vehicle acquired by the second laser radar, and generating a second target vehicle vector;

calculating the similarity of the first target vehicle vector and the second target vehicle vector, and generating a first target confidence;

and determining the first target vehicle and the second target vehicle as the same target vehicle under the condition that the first target confidence is larger than a confidence threshold.

7. The method of claim 6, wherein determining the first target vehicle and the second target vehicle as the same target vehicle if the target confidence is greater than a confidence threshold comprises:

8. The method of claim 1, wherein after controlling the one or more lidars to collect data of a target vehicle to generate a dynamic vehicle information matrix, the method further comprises:

and when the laser radar detects that the target vehicle runs in the direction away from the laser radar, maintaining the data of the target vehicle.

9. A vehicle tracking system, comprising:

the laser radar data acquisition module is connected with the vehicle detection module and the laser radar and is used for acquiring target vehicle data in a target channel in real time based on the laser radar and sending the target vehicle data to the vehicle detection module;

the vehicle detection module is connected with the laser radar data acquisition module and the vehicle tracking module and is used for calculating the target information of the target vehicle from the target vehicle data in real time;

the vehicle tracking module is connected with the vehicle detection module and is used for determining real-time position information of the target vehicle in the target channel, position information of the same laser radar scanning the target vehicle and matching information of scanning the target vehicle between adjacent laser radars based on the target information;

The vehicle tracking module is configured to determine the real-time position information of the target vehicle in the target channel by using a dynamic vehicle information matrix and position information of one or more laser radars in the target channel, and includes:

controlling one or more of the lidars to collect data of the target vehicle for at least one of: the method comprises the steps that the absolute position of a target vehicle, the position of the target vehicle relative to a laser radar, the vehicle body reflection intensity value of the target vehicle, the ratio of the vehicle body reflection intensity value to the position of the target vehicle relative to the laser radar, the laser radar detects the ratio of the number of points of the unit length of the target vehicle to the relative position of the target vehicle, wherein the number of points of the unit length of the target vehicle detected by the laser radar is the ratio of the number of points of the target vehicle to the length enclosed by the number of points on the target vehicle in one detection period of the laser radar, and the detection line detects the target vehicle through one or more detection lines; generating one or more vehicle information vectors according to the data of the target vehicle, wherein the one or more vehicle information vectors are in one-to-one correspondence with the target vehicle; generating the dynamic vehicle information matrix based on the one or more vehicle information vectors;

The laser radars are alternately arranged on two sides of the center of the target channel, the horizontal distance of each adjacent laser radar is within a preset horizontal distance threshold value range, the included angle between each laser radar and the horizontal direction is larger than a first angle threshold value, an overlapping area exists in the detection range of each adjacent laser radar, and the sum of the detection areas of all the laser radars covers the target channel;

and the time synchronization module is connected with the laser radar data acquisition module, the vehicle detection module, the vehicle tracking module and the laser radar and is used for synchronizing the time of all devices in the target channel.