Radar-based target segmentation tracking method, device, equipment and storage medium

Abstract

The present application discloses a radar-based target segmented tracking method, device, equipment and storage medium, the method comprising: a first detection radar acquires point cloud information, and performs a first filtering on the point cloud information outside the target detection area; performs at least a second filtering on the noise points in the blind spot of the target illumination; acquires third target information within a short range through the first detection radar and the video detector; uses twin software to generate fourth target information within a long range based on the radar signal information within a long range; and uses an edge computing unit to identify and match the target information within the track relay area to complete track splicing. The present application can identify reflected signals from tunnels or walls and shield and pre-process them, greatly reducing the impact of multipath interference signals on real target detection and significantly improving tracking accuracy and stability.

Description

Technical Field

[0001] The present application relates to the field of sensor network technology, and in particular to a radar-based target segmentation tracking method, device, equipment, and storage medium. Background Art

[0002] With the development of science and technology, radar has gradually been applied in various fields. However, when using radar for detection in scenes with obstructions or walls, such as tunnels, multipath interference effects are often generated, affecting the accuracy of radar detection. This makes it impossible to accurately identify the target area, and the long-distance tracking effect is poor.

[0003] The existing solution is to suppress false targets by pre-identifying them and then adjusting the confidence level. However, this method has poor target tracking accuracy and stability, and the radar data processing work is complicated.

[0004] Based on this, a method that can achieve continuous and stable tracking of the target and suppress the multipath effect remains to be proposed. Summary of the Invention

[0005] Based on the above problems, the present application provides a radar-based target segmentation tracking method, device, equipment and storage medium, which can identify reflected signals from tunnels or walls and shield and pre-process them, greatly reducing the impact of multipath interference signals on real target detection and significantly improving tracking accuracy and stability.

[0006] The embodiments of this application disclose the following technical solutions:

[0007] The first aspect of the present application provides a radar-based target segment tracking method, comprising:

[0008] The first detection radar acquires point cloud information and determines a target detection area; performs a first filtering on point cloud information outside the target detection area to obtain first target information;

[0009] Calculating a target illumination blind area, and filtering out at least one second of the noise points in the target illumination blind area; obtaining second target information;

[0010] Acquiring information of a third target within a close range by using the first detection radar and the video detector;

[0011] Based on the radar signal information within the long range, twin software is used to generate the fourth target information within the long range;

[0012] At least one second detection radar is set up to repeat the information acquisition steps of the first detection radar; the target information in the track relay area is identified and matched through the edge computing unit to complete the track splicing.

[0013] As a possible implementation, the target detection area is a lane or tunnel area within the radar detection range, or an area with obstructions or walls on the side; the target detection area is marked and divided based on the calibration of the radar coordinate system and the world coordinate system. The method of the present invention is characterized in that the first target information includes the length, width, and height information of the detected target within the target detection area.

[0014] As a possible implementation, the second target information includes the length, width, and height information of the detection target after filtering out blind spot noise;

[0015] As a possible implementation method, the third target information includes the ID number of the target detected by the first detection radar and the vehicle model structured information.

[0016] As a possible implementation, the fourth target information generating method includes:

[0017] determining whether there is a certain radar signal within the long-range area;

[0018] If yes, the trajectory of the information in the long-range range is corrected according to the detected information and the third target information in the short-range range, that is, the fourth target information.

[0019] As a possible implementation, the fourth target information generating method includes:

[0020] determining whether there is a certain radar signal within the long-range area;

[0021] If not, then based on the known target driving route information (lane information) and the speed of the target detected last time, a continuation trajectory of the third target information within a close range, namely the fourth target information, is generated.

[0022] As a possible implementation manner, the calculation of the target illumination blind area includes:

[0023] Get radar hanging height and detection target height;

[0024] Obtaining the distance of the detection target relative to the radar position;

[0025] The target illumination blind area is determined according to the proportional relationship.

[0026] As a possible implementation, the first detection radar and the second detection radar are installed at the tail of the detection target to track the direction of the target.

[0027] As a possible implementation manner, the first detection radar and the second detection radar have a common detection area which is a trajectory relay area.

[0028] As a possible implementation manner, identifying and matching target information within the track relay area by an edge computing unit includes:

[0029] Calibrate the longitude and latitude of the first detection radar and the second detection radar to unify the coordinate system so that the targets detected by the two radars are at the same coordinates in the same coordinate system;

[0030] Set the target position difference threshold Δd0 and velocity difference threshold Δv0 detected by two radars;

[0031] After the first target detected by the first detection radar enters the track relay area, the edge computing unit calculates the position difference Δd1 and the speed difference Δv1 of the first target detected by the first detection radar and the second target detected by the second detection radar;

[0032] If it is less than a threshold, it is determined that the first target and the second target are the same target;

[0033] The edge computing unit assigns the ID number of the first target detected by the first detection radar to the second target detected by the second detection radar, and deletes the first radar target to remove duplication.

[0034] A second aspect of the present application provides a radar-based target segment tracking device, comprising:

[0035] A first target information determination unit is configured to obtain point cloud information from the first detection radar, determine a target detection area, and perform a first filtering of point cloud information outside the target detection area;

[0036] A second target information determination unit is configured to calculate a target illumination blind area and perform at least a second filtering of noise points within the target illumination blind area;

[0037] a third target information determining unit, configured to obtain third target information within a close range, specifically by using the first detection radar and the video detector;

[0038] a fourth target information determination unit, configured to generate fourth target information within the long-range range using twin software based on radar signal information within the long-range range;

[0039] The target information identification and matching unit performs target identification and trajectory matching on the target information in the trajectory relay area through the edge computing unit.

[0040] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the radar-based target segmentation tracking method as described in the first aspect of the present application is implemented.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium, which stores instructions. When the instructions are executed on a terminal device, the terminal device executes the radar-based target segmentation tracking method as described in the first aspect of the present application.

[0042] Compared with the existing technology, this application has the following beneficial effects:

[0043] By preprocessing the original point cloud information, this application can identify the reflected signals from tunnels or walls and shield and preprocess them, cluster and track the preprocessed point cloud information, and greatly reduce the impact of multipath interference signals on real target detection.

[0044] This application uses segmented tracking and radar-vision fusion methods to splice the target's trajectory using edge computing units, greatly improving the accuracy and stability of tracking. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0046] Figure 1 A schematic flow chart of a radar-based target segmented tracking method according to an embodiment of the present application;

[0047] Figure 2 A schematic diagram of the arrangement of the first detection radar and the second detection radar provided in an embodiment of the present application;

[0048] Figure 3 A schematic diagram of a blind spot calculation method provided in an embodiment of the present application;

[0049] Figure 4 A schematic diagram showing the relationship between the various units of the radar-based segmented target tracking device provided in an embodiment of the present application;

[0050] Figure 5 A schematic diagram of the electronic device structure provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] As previously described, tunnels are a typical and common special scenario in the transportation sector. Tunnel operations and maintenance are laborious and carry significant safety responsibilities. Event identification is primarily performed manually, which is unable to comprehensively, accurately, and promptly identify events occurring within the tunnel. This can lead to secondary accidents and significant loss of life and property. Therefore, tunnel transportation urgently requires new technologies that can create a digital twin of the traffic flow within the tunnel, providing a clear overview of the tunnel's conditions and enabling timely detection of incidents such as congestion and parking.

[0052] Millimeter-wave radar can accurately measure the distance, position, speed, and heading of vehicles on the road, and accurately present the vehicle's trajectory. However, in tunnels, due to the enclosed space, millimeter-wave radar detection is affected by multipath reflections, resulting in false target output, which affects the detection of real targets. Using only traditional traffic radar in tunnels significantly reduces the reliability of radar target output due to multipath interference, thus affecting the splicing of target trajectories.

[0053] In view of this, an embodiment of the present application provides a radar-based target segmentation tracking method, device, equipment and storage medium, the method including: a first detection radar acquires point cloud information to determine a target detection area; the point cloud information outside the target detection area is filtered out for a first time to obtain first target information; the noise within the target illumination blind spot is filtered out for a second time at least once; second target information is obtained; third target information within a short range is acquired through the first detection radar and the video detector; fourth target information within a long range is generated using twin software based on radar signal information within a long range; at least one second detection radar is set up to repeat the information acquisition step of the first detection radar; the target information within the track relay area is identified and matched through the edge computing unit to complete track splicing. By preprocessing the original point cloud information, this application can identify the reflected signals from tunnels or walls, shield and preprocess them, cluster and track the preprocessed point cloud information, and greatly reduce the impact of multipath interference signals on real target detection; this application uses segmented tracking and radar-vision fusion methods to use edge computing units to splice the target's trajectory, greatly improving the accuracy and stability of tracking.

[0054] In order to help those skilled in the art better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0055] Example 1

[0056] See also Figure 1 , which is a flow chart of a radar-based target segment tracking method provided by an embodiment of the present application, such as Figure 1 As shown, the radar-based target segmentation tracking method includes:

[0057] S110: The first detection radar acquires point cloud information and determines a target detection area; performs a first filtering on point cloud information outside the target detection area to obtain first target information;

[0058] S120: Calculate the target illumination blind area, and perform at least one second filtering on the noise points in the target illumination blind area to obtain second target information;

[0059] S130: Acquire information of a third target within a close range by using the first detection radar and the video detector;

[0060] S140: Generate fourth target information within the long range using twin software based on radar signal information within the long range;

[0061] S150: Set up at least one second detection radar and repeat the information acquisition step of the first detection radar; use the edge computing unit to identify and match the target information in the track relay area to complete track splicing.

[0062] The S110 includes:

[0063] S1101: The target detection area is a lane or tunnel area within the radar detection range, or an area with obstructions or walls on the side; the target detection area is marked and divided based on the calibration of the radar coordinate system and the world coordinate system.

[0064] S1102: The first target information includes the length, width and height information of the detected target within the target detection area

[0065] The S120 includes:

[0066] S1201: The second target information includes the length, width, and height information of the detected target after filtering out blind spot noise;

[0067] S1202: Calculate target illumination blind area, including:

[0068] Get radar hanging height and detection target height;

[0069] Obtaining the distance of the detection target relative to the radar position;

[0070] The target illumination blind area is determined according to the proportional relationship.

[0071] like Figure 3 As shown, the blind zone length l is:

[0072]

[0073] Among them, H is the radar hanging height, L is the distance between the front of the vehicle and the radar, and h is the vehicle height.

[0074] The S130 includes:

[0075] S1301: The third target information includes the ID number of the target detected by the first detection radar and the vehicle model structured information.

[0076] As a possible implementation, the video detector can be integrated with the first detection radar through radar-visual fusion, or the video detector can be a separate box camera or dome camera installed next to the first detection radar. Vehicle vehicle structured information is obtained through the combined detection of the radar detector and the video detector.

[0077] As a possible implementation manner, the short-range range is within 50m from the position of the first detection radar; the long-range range is within 50m-100m from the position of the first detection radar.

[0078] As a possible implementation, the radar accurately detects targets within 50 meters and generates target IDs and other identification information. Beyond 50 meters, no new target IDs are generated. This is because radar detection signal strength decreases with distance. Therefore, the radar focuses on generating target information at close range to ensure accurate detection of targets at close range. Target information at longer distances is generated through simulation or inference, thereby minimizing detection interference caused by multipath noise.

[0079] The S140 includes:

[0080] S1401: The fourth target information is generated by:

[0081] determining whether there is a certain radar signal within the long-range area;

[0082] If yes, the trajectory of the information in the long-range range is corrected according to the detected information and the third target information in the short-range range, that is, the fourth target information.

[0083] S1402: The fourth target information is generated by:

[0084] determining whether there is a certain radar signal within the long-range area;

[0085] If not, then based on the known target driving route information (lane information) and the speed of the target detected last time, a continuation trajectory of the third target information within a close range, namely the fourth target information, is generated.

[0086] As a possible implementation, the twin software may be traffic twin software, which specifically simulates and generates a similar trajectory information through the detected radar data. Because the information is similar, it is called a twin.

[0087] The S150 includes:

[0088] S1501: Identifying and matching target information within the track relay area using an edge computing unit includes:

[0089] S150A: Calibrate the longitude and latitude of the first detection radar and the second detection radar to unify the coordinate system so that the targets detected by the two radars are at the same coordinates in the same coordinate system;

[0090] S150B: Set the target position difference threshold Δd0 and speed difference threshold Δv0 detected by the two radars;

[0091] S150C: After the first target detected by the first detection radar enters the track relay area, the edge computing unit calculates a position difference Δd1 and a speed difference Δv1 between the first target detected by the first detection radar and the second target detected by the second detection radar.

[0092] S150D: If the value is less than a threshold, determining that the first target and the second target are the same target;

[0093] S150E: The edge computing unit assigns the ID number of the first target detected by the first detection radar to the second target detected by the second detection radar, and deletes the first radar target to remove duplication.

[0094] As a possible implementation manner, the first detection radar and the second detection radar are installed at the tail of the detection target to track the direction of the target.

[0095] As a possible implementation manner, the first detection radar and the second detection radar have a common detection area which is a trajectory relay area.

[0096] Millimeter wave (mmWave) is a specialized radar technology that uses short-wavelength electromagnetic waves. The electromagnetic wave signal emitted by the radar system is blocked by objects in its transmission path and then reflected. By capturing the reflected signal, the radar system can determine the object's distance, speed, and angle. In recent years, with the country's emphasis on automobile safety and the popularization of ADAS and autonomous driving technologies, millimeter wave radar has gradually become a rising star in the field of smart transportation, gaining widespread application in both on-board and roadside detection.

[0097] Example 2

[0098] See also Figure 4 , which is a schematic diagram of the relationship between the various units of the radar-based target segmented tracking device provided in an embodiment of the present application; Figure 4 As shown, this embodiment provides a radar-based target segment tracking device, including:

[0099] S210: A first target information determining unit is configured to obtain point cloud information from a first detection radar, determine a target detection area, and perform a first filtering of point cloud information outside the target detection area.

[0100] S220: A second target information determining unit is configured to calculate a target illumination blind area and perform at least one second filtering on noise points in the target illumination blind area;

[0101] S230: a third target information determining unit, configured to obtain third target information within a close range, specifically by using the first detection radar and the video detector;

[0102] S240: a fourth target information determining unit, configured to generate fourth target information within the long-range range using twin software according to radar signal information within the long-range range;

[0103] S250: The target information identification and matching unit performs target identification and trajectory matching on the target information in the trajectory relay area through the edge computing unit.

[0104] Example 3

[0105] This embodiment provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the radar-based target segmentation tracking method as described in Example 1 of the present application is implemented.

[0106] Figure 5A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0107] like Figure 5 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11. The memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. Various programs and data required for the operation of the electronic device 10 can also be stored in the RAM 13. The processor 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0108] Multiple components in the electronic device 10 are connected to the I / O interface 15, including an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0109] The processor 11 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any other suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the radar-based foreign object intrusion detection method.

[0110] In some embodiments, the radar-based foreign object intrusion detection method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the radar-based foreign object intrusion detection method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the radar-based foreign object intrusion detection method in any other appropriate manner (for example, by means of firmware).

[0111] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chip systems (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0112] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer program is executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer program may be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0113] In the context of the present invention, computer-readable storage media can be tangible media that can contain or store a computer program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Computer-readable storage media can include but are not limited to electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, computer-readable storage media can be machine-readable signal media. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0114] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0115] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0116] A computing system may include clients and servers. The clients and servers are typically remote from each other and typically interact via a communication network. This client-server relationship arises through computer programs running on the respective computers, creating a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host. This server is a hosting product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosting and VPS services.

[0117] Although several specific implementation details are included in the above discussion, these should not be construed as limiting the scope of this application. Certain features described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented in multiple embodiments individually or in any suitable sub-combination.

[0118] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure in this application is not limited to the technical solutions formed by a specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.

Claims

1. A radar-based target segmentation tracking method, characterized in that: include: The first detection radar obtains point cloud information and determines the target detection area; Perform a first filtering on the point cloud information outside the target detection area to obtain the first target information; Calculating a target illumination blind area, and filtering out at least one second of the noise points in the target illumination blind area; obtaining second target information; Acquiring information of a third target within a close range by using the first detection radar and the video detector; Based on the radar signal information within the long range, twin software is used to generate the fourth target information within the long range; At least one second detection radar is provided, and the information acquisition step of the first detection radar is repeated; The edge computing unit identifies and matches the target information in the track relay area to complete track splicing; The identification and matching specifically includes: Calibrate the longitude and latitude of the first detection radar and the second detection radar to unify the coordinate system so that the targets detected by the two radars are at the same coordinates in the same coordinate system; Set the target position difference threshold detected by two radars and speed difference threshold ; After the first target detected by the first detection radar enters the track relay area, the edge computing unit calculates the position difference between the first target detected by the first detection radar and the second target detected by the second detection radar. and speed difference ; If it is less than a threshold, it is determined that the first target and the second target are the same target; The edge computing unit assigns the ID number of the first target detected by the first detection radar to the second target detected by the second detection radar, and deletes the first radar target to remove duplication.

2. The method according to claim 1, characterized in that The target detection area is the area in the lane or tunnel within the radar detection range, or the area with obstructions or walls on the side; the target detection area is divided into areas based on the calibration of the radar coordinate system and the world coordinate system.

3. The method according to claim 1, characterized in that The first target information includes length, width and height information of the detection target within the target detection area.

4. The method according to claim 1, wherein The second target information includes the length, width and height information of the detection target after filtering out blind spot noise.

5. The method according to claim 1, wherein The third target information includes the ID number of the target detected by the first detection radar and the vehicle type structured information.

6. The method according to claim 1, characterized in that The fourth target information is generated by a method comprising: determining whether there is a certain radar signal within the long-range area; If yes, the trajectory of the information in the long-range range is corrected according to the detected information and the third target information in the short-range range, that is, the fourth target information.

7. The method according to claim 1, characterized in that The fourth target information is generated by a method comprising: determining whether there is a certain radar signal within the long-range area; If not, a continuation track of the third target information within a short distance is generated according to the known target driving route information and the speed at which the target was last detected, that is, the fourth target information.

8. The method according to claim 1, characterized in that The calculating target illumination blind area includes: Get radar hanging height and detection target height; Obtaining the distance of the detection target relative to the radar position; The target illumination blind area is determined according to the proportional relationship.

9. The method according to claim 1, characterized in that The first detection radar and the second detection radar are installed at the tail of the detection target to track the direction of the target.

10. The method according to claim 1, characterized in that The first detection radar and the second detection radar have a common detection area which is a track relay area.

11. The method according to claim 1, wherein The identifying and matching target information within the track relay area by the edge computing unit includes: Calibrate the longitude and latitude of the first detection radar and the second detection radar to unify the coordinate system so that the targets detected by the two radars are at the same coordinates in the same coordinate system; Set the target position difference threshold detected by two radars and speed difference threshold ; After the first target detected by the first detection radar enters the track relay area, the edge computing unit calculates the position difference between the first target detected by the first detection radar and the second target detected by the second detection radar. and speed difference ; If it is less than a threshold, it is determined that the first target and the second target are the same target; The edge computing unit assigns the ID number of the first target detected by the first detection radar to the second target detected by the second detection radar, and deletes the first radar target to remove duplication.

12. A radar-based target segment tracking device, characterized in that: include: A first target information determination unit is used to obtain point cloud information of the first detection radar and determine a target detection area; Perform the first filtering of point cloud information outside the target detection area; A second target information determination unit is configured to calculate a target illumination blind area and perform at least a second filtering of noise points within the target illumination blind area; a third target information determining unit, configured to obtain third target information within a close range, specifically by using the first detection radar and the video detector; a fourth target information determination unit, configured to generate fourth target information within the long-range range using twin software based on radar signal information within the long-range range; At least one second detection radar is provided, and the information acquisition step of the first detection radar is repeated; The target information recognition and matching unit uses the edge computing unit to perform target recognition and trajectory matching on the target information in the trajectory relay area; The target recognition and trajectory matching specifically include: Calibrate the longitude and latitude of the first detection radar and the second detection radar to unify the coordinate system so that the targets detected by the two radars are at the same coordinates in the same coordinate system; Set the target position difference threshold detected by two radars and speed difference threshold ; After the first target detected by the first detection radar enters the track relay area, the edge computing unit calculates the position difference between the first target detected by the first detection radar and the second target detected by the second detection radar. and speed difference ; If it is less than a threshold, it is determined that the first target and the second target are the same target; The edge computing unit assigns the ID number of the first target detected by the first detection radar to the second target detected by the second detection radar, and deletes the first radar target to remove duplication.

13. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the radar-based target segmentation tracking method according to any one of claims 1 to 11 is implemented.

14. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed on a terminal device, the terminal device executes the radar-based target segment tracking method according to any one of claims 1 to 11.

Images