A target tracking method, device, medium, and product
By constructing a dead reckoning (DR) mileage cache queue and a target matching algorithm, the problem of inaccurate inter-frame data correlation was solved, improving the accuracy and stability of target tracking in the autonomous driving perception system.
Patent Information
- Application Number
- CN202611273709.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-21
- Publication Date
- 2026-11-17
AI Technical Summary
In autonomous driving perception systems, insufficient accuracy in inter-frame data association leads to unstable target tracking and high ID switching frequency, affecting the accuracy of target tracking.
By constructing a dead reckoning (DR) mileage cache queue, the pose coordinate changes of the current and historical frames are obtained. Combined with the current target detection results and the initial positions of historical targets, target matching is performed using the Hungarian algorithm and Mahalanobis distance to reduce the uncertainty of motion prediction.
It improves the accuracy of target tracking, reduces the uncertainty of motion prediction, and enhances the stability of target tracking.
Smart Images

Figure CN123118693A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present invention relate to the field of vehicle technology, and in particular to a target tracking method, device, medium and product. Background Technology
[0002] In autonomous driving perception systems, target tracking relies on establishing target correspondences between consecutive frames, specifically determining which target in a historical frame corresponds to the target detected in the current frame. This process, known as inter-frame data association, directly impacts the stability of target tracking and the frequency of ID switching. Therefore, improving the accuracy of inter-frame data association, and consequently enhancing target tracking accuracy, is a pressing issue that needs to be addressed. Summary of the Invention
[0003] This invention provides a target tracking method, device, medium, and product that can improve the accuracy of target tracking.
[0004] According to one aspect of the present invention, a target tracking method is provided, comprising: Construct a dead reckoning (DR) mileage cache queue, wherein the DR mileage cache queue includes: multiple historical frames, and the historical frames include: the change in pose coordinates of the current vehicle relative to the previous frame; Obtain the current target detection result corresponding to the current frame, wherein the current target detection result includes: the position of the current target; The initial position of a historical target is obtained, wherein the initial position of the historical target includes: the target detection result of a historical frame and / or the target prediction result of a historical frame, wherein the target prediction result of the historical frame is determined based on the change in pose coordinates of the current vehicle relative to the previous frame. The matching result is determined based on the current target's position, the initial position of the historical target, and the change in pose coordinates of the current vehicle relative to the previous frame in the historical frame. Target tracking is performed based on the matching results.
[0005] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and a memory communicatively connected to said at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the target tracking method according to any embodiment of the present invention.
[0006] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the target tracking method according to any embodiment of the present invention.
[0007] According to another aspect of the present invention, a computer program product is provided, which, when executed by a processor, implements the target tracking method as described in any of the embodiments of the present invention.
[0008] This invention constructs a dead reckoning (DR) mileage cache queue, which includes: multiple historical frames, each historical frame including the change in pose coordinates of the current vehicle relative to the previous frame; obtaining the current target detection result corresponding to the current frame, wherein the current target detection result includes the position of the current target; obtaining the initial position of a historical target, wherein the initial position of the historical target includes the target detection result and / or the target prediction result of the historical frame, the target prediction result of the historical frame being determined based on the change in pose coordinates of the current vehicle relative to the previous frame corresponding to the historical frame; determining a matching result based on the position of the current target, the initial position of the historical target, and the change in pose coordinates of the current vehicle relative to the previous frame corresponding to the historical frame; and performing target tracking based on the matching result. By calculating the vehicle pose coordinate change rate based on the DR mileage cache queue, and processing the target detection result and / or target prediction result of the historical frame based on the vehicle pose coordinate change rate before matching, the uncertainty of motion prediction can be reduced, thereby improving the accuracy of target tracking.
[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description
[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.
[0011] Figure 1 This is a flowchart of a target tracking method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0012] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.
[0013] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0014] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.
[0015] Example 1 Figure 1 This is a flowchart illustrating a target tracking method provided in an embodiment of the present invention. This embodiment is applicable to target tracking situations. The method can be executed by the target tracking device in this embodiment of the invention, which can be implemented in software and / or hardware, such as... Figure 1 As shown, the method specifically includes the following steps: S110, construct a dead reckoning (DR) mileage cache queue.
[0016] The DR mileage cache queue includes multiple historical frames, each of which includes the change in pose coordinates of the current vehicle relative to the previous frame.
[0017] In this embodiment, the Dead Reckoning (DR) algorithm takes wheel speedometer and IMU sensor data as input, recursively infers the vehicle motion state based on the pose integral of the previous moment, and continuously updates the vehicle pose; the algorithm can output the vehicle pose coordinates and the change in the current vehicle pose coordinates relative to the previous frame.
[0018] In a specific example, the DR mileage cache queue includes 100 historical frames. The DR mileage cache queue is used to store data such as the identifier, timestamp, absolute pose coordinates, and pose coordinate changes relative to the previous frame for each frame.
[0019] S120, Obtain the current target detection result corresponding to the current frame.
[0020] The current target detection result includes: the current target's location.
[0021] In this embodiment, the method for obtaining the current target detection result corresponding to the current frame can be as follows: after obtaining the image frame captured by the vehicle camera, input the image frame into the visual perception model to obtain the target recognition result.
[0022] In this embodiment, the position of the current target is its position in the image pixel coordinate system.
[0023] S130, Obtain the initial position of the historical target.
[0024] The initial position of the historical target includes: the target detection result of the historical frame and / or the target prediction result of the historical frame. The target prediction result of the historical frame is determined based on the change in pose coordinates of the current vehicle relative to the previous frame.
[0025] In this embodiment, the target detection result of the historical frame is the position of the historical target in the image pixel coordinate system. The target prediction result of the historical frame can be the position of the historical target in the vehicle coordinate system or the position of the historical target in the image pixel coordinate system. This embodiment of the invention does not impose any restrictions on this.
[0026] S140, determine the matching result based on the current target's position, the initial position of the historical target, and the change in pose coordinates of the current vehicle relative to the previous frame corresponding to the historical frame.
[0027] In this embodiment, the matching results include: the current target and historical targets that the current target matched.
[0028] Optionally, the matching result is determined based on the current target's position, the initial position of the historical target corresponding to the historical frame, and the change in the current vehicle's pose coordinates relative to the previous frame, including: Based on the change in pose coordinates of the current vehicle relative to the previous frame in the historical frame, the initial position of the historical target in the historical frame is transformed to obtain the target position of the historical target.
[0029] The target position of the historical target is its position in the vehicle coordinate system.
[0030] The target is matched based on its current location and the historical target locations to obtain the matching result.
[0031] The current target's position is its position in the vehicle coordinate system.
[0032] In this embodiment, if the initial position of the historical target includes the target prediction result of the historical frame, and the target prediction result of the historical frame is the position of the historical target in the image pixel coordinate system, then the matching result can be determined based on the current target position, the initial position of the historical target corresponding to the historical frame, and the change in pose coordinates of the current vehicle relative to the previous frame. This can be achieved by: performing coordinate transformation on the target prediction result of the historical frame based on the change in pose coordinates of the current vehicle relative to the previous frame to obtain the target position of the historical target, where the target position of the historical target is the position in the vehicle coordinate system; and performing target matching based on the current target position and the target position of the historical target to obtain a matching result, where the current target position is the position in the vehicle coordinate system. The initial position of the historical target includes: the target detection result of the historical frame; the matching result is determined based on the current target position, the initial position of the historical target corresponding to the historical frame, and the change in pose coordinates of the current vehicle relative to the previous frame. The matching result can be determined by: performing coordinate transformation on the target detection result of the historical frame based on the change in pose coordinates of the current vehicle relative to the previous frame to obtain the target position of the historical target, wherein the target position of the historical target is the position in the vehicle coordinate system; and performing target matching based on the current target position and the target position of the historical target to obtain the matching result, wherein the current target position is the position in the vehicle coordinate system. If the initial position of the historical target includes the target detection result and the target prediction result of the historical frame, and the target prediction result of the historical frame is the position of the historical target in the image pixel coordinate system, then the matching result can be determined based on the position of the current target, the initial position of the historical target corresponding to the historical frame, and the change in pose coordinates of the current vehicle relative to the previous frame. This can be achieved by: performing coordinate transformation on the target prediction result and the target detection result of the historical frame based on the change in pose coordinates of the current vehicle relative to the previous frame to obtain the target position of the historical target, where the target position of the historical target is the position in the vehicle coordinate system; and performing target matching based on the position of the current target and the target position of the historical target to obtain the matching result, where the position of the current target is the position in the vehicle coordinate system.If the initial position of the historical target includes the target detection result and the target prediction result of the historical frame, and the target prediction result of the historical frame is the position of the historical target in the vehicle coordinate system, then the matching result can be determined based on the position of the current target, the initial position of the historical target corresponding to the historical frame, and the change in pose coordinates of the current vehicle relative to the previous frame. This can be achieved by: performing coordinate transformation on the target detection result of the historical frame based on the change in pose coordinates of the current vehicle relative to the previous frame; determining the target position of the historical target based on the transformed target detection result and the target prediction result of the historical frame, where the target position of the historical target is the position in the vehicle coordinate system; and performing target matching based on the position of the current target and the target position of the historical target to obtain the matching result, where the position of the current target is the position in the vehicle coordinate system.
[0033] Optionally, target matching can be performed based on the current target's location and historical target locations to obtain matching results, including: Based on the location of historical targets and the location of the current target, determine the historical targets that match the current target.
[0034] In this embodiment, the method for determining the historical target matching the current target based on the historical target's target position and the current target's position can be as follows: The Mahalanobis distance between the historical target and the current target is determined based on their respective positions. Historical targets whose Mahalanobis distance to the current target is less than a distance threshold are considered as matching historical targets.
[0035] Add historical targets that match the current target to the cost matrix of the current target.
[0036] It should be noted that the Mahalanobis distance between the historical targets and the current target in the cost matrix of the current target is less than the distance threshold.
[0037] Target matching is performed based on the Hungarian algorithm and the cost matrix of the current target to obtain the matching result.
[0038] The matching results include: the current target and historical targets that matched the current target.
[0039] In this embodiment, for an n×m cost matrix, the Hungarian algorithm is used to find the optimal allocation that minimizes the total cost. For a matching pair output by the Hungarian algorithm, if the Mahalanobis distance exceeds a distance threshold, the match is rejected.
[0040] In this embodiment, the matrix elements in the cost matrix represent the matching cost between historical and current targets, which can be quantified using spatial distance, intersection-union ratio (IOU), and motion consistency index. The Hungarian algorithm is used to find the optimal assignment solution, searching for the pairing scheme with the minimum global total cost under a one-to-one matching constraint, which is then taken as the final matching result.
[0041] Optionally, based on the target locations of historical targets and the current target location, determine historical targets that match the current target, including: Determine the Mahalanobis distance between the historical target and the current target based on their respective locations.
[0042] In this embodiment, the Mahalanobis distance between the historical target and the current target is determined by: determining the residual vector based on the historical target's location and the current target's location; and determining the Mahalanobis distance between the historical target and the current target based on the residual vector and its corresponding covariance matrix. Historical targets whose Mahalanobis distance to the current target is less than a distance threshold are considered as matching historical targets for the current target.
[0043] In this embodiment, the distance threshold can be a preset distance, and this embodiment does not impose any restrictions on it.
[0044] Optional, also includes: If a target is missing, its position is predicted based on the change in pose coordinates relative to the previous frame.
[0045] The lost target refers to a historical target that does not match the current target.
[0046] In this embodiment, if the Mahalanobis distance between the historical target and the current target is greater than or equal to the distance threshold, the historical target is identified as a lost target.
[0047] In this embodiment, the method for predicting the position of a lost target based on the change in pose coordinates relative to the previous frame can be as follows: if the lost target is stationary relative to the ground, the position of the lost target in the vehicle coordinate system is predicted based on the change in pose coordinates of the current vehicle relative to the previous frame and the position of the lost target in the previous frame; if the lost target is moving relative to the ground, the position is predicted based on Kalman filtering and the historical position of the lost target to obtain the predicted position, and the predicted position is transformed according to the change in pose coordinates relative to the previous frame to obtain the position of the lost target in the vehicle coordinate system.
[0048] The predicted location of the lost target is used as the target prediction result for the current frame.
[0049] It should be noted that for the detection of a new frame, the target prediction result of the current frame is the target prediction result of the historical frames.
[0050] Optionally, predicting the location of the lost target based on the change in pose coordinates relative to the previous frame includes: If the lost target is a static target, the location of the lost target is predicted based on the change in the pose coordinates of the current vehicle relative to the previous frame and the location of the lost target in the previous frame.
[0051] In this embodiment, the position of the lost target is transformed to obtain the position of the lost target in the world coordinate system; if the lost target is determined to be stationary relative to the ground based on the position of the lost target in the world coordinate system, then the target type of the lost target is determined to be a static target.
[0052] If the lost target is a dynamic target, the position is predicted based on Kalman filtering and the historical position of the lost target. The predicted position is then transformed according to the change in pose coordinates relative to the previous frame to obtain the position of the lost target.
[0053] In this embodiment, the position of the lost target is transformed to obtain the position of the lost target in the world coordinate system; if the position of the lost target in the world coordinate system indicates that the lost target has moved relative to the ground, then the target type of the lost target is determined to be a dynamic target.
[0054] In this embodiment, the target coordinates of historical frames are transformed to the world coordinate system using DR projection, and static and dynamic targets are distinguished. Static targets maintain a constant position in the world coordinate system. During vehicle movement, the motion of static targets in the vehicle coordinate system is the inverse transformation of the vehicle's motion; that is, the position of the lost target is inversely derived based on the change in the vehicle's pose coordinates relative to the previous frame and the position of the lost target in the previous frame. For dynamic targets, an extended Kalman filter is used to maintain their motion state. When a target is lost, a Kalman filter prediction iteration is performed based on the stored historical position of the lost target to obtain the predicted position. The predicted position is then transformed according to the change in pose coordinates relative to the previous frame to obtain the position of the lost target in the vehicle coordinate system.
[0055] Optional, also includes: If the number of lost frames for the lost target exceeds a frame count threshold, then the tracking of the lost target is terminated.
[0056] In this embodiment, the frame count threshold can be a preset value. If the number of lost frames of the lost target is greater than the frame count threshold, it is considered that the target has left the field of view, and the tracking of the target is terminated.
[0057] S150, target tracking is performed based on the matching result.
[0058] In a specific example, the target tracking method includes: maintaining a fixed-length DR (Dash Detection) odometry cache array to store the ID, timestamp, absolute pose coordinates, and pose coordinate changes relative to the previous frame for each frame. After acquiring image frames from the vehicle-mounted camera, target identification is performed, and the current target detection result for the current frame is output. For each detected target, its ID, coordinates in the current frame, detection confidence, and type are recorded. For each historical target and current target, the Mahalanobis distance is calculated, and the historical target pair is included in the cost matrix only if the Mahalanobis distance is less than a distance threshold. For the cost matrix, the Hungarian algorithm is used to solve for the optimal allocation that minimizes the total cost. For matching pairs output by the Hungarian algorithm, if the Mahalanobis distance exceeds the gating threshold, the match is rejected. When a target is lost (unmatched), the target position is predicted using DR projection. The method for predicting the target position using DR projection can be as follows: if the target is stationary relative to the ground (static target), the static target's position remains unchanged in the world frame. When the vehicle moves forward, the motion of the static target in the vehicle coordinate system is exactly the inverse transformation of the vehicle's motion (the change in the vehicle's DR projection position cancels out). If the target is moving relative to the ground (dynamic target), an extended Kalman filter is used to maintain its motion state, i.e., a preliminary motion prediction is made for the moving target in the world coordinate system. Then, the target prediction result for the current frame in the vehicle coordinate system is obtained based on DR projection. For the detection of a new frame, in addition to regular matching with historical targets, matching is also performed with targets that are in a lost state. During re-association, the Mahalanobis distance between the current target and the lost target is calculated. If the Mahalanobis distance is less than a distance threshold, they are considered the same target, and tracking is resumed; otherwise, it is not resumed. It should be noted that when the number of frames lost by the target exceeds a frame number threshold, the target is considered to have left the field of view, and tracking of the target is terminated.
[0059] The technical solution of this embodiment constructs a dead reckoning (DR) mileage cache queue, which includes: multiple historical frames, each historical frame including the change in pose coordinates of the current vehicle relative to the previous frame; obtaining the current target detection result corresponding to the current frame, wherein the current target detection result includes the position of the current target; obtaining the initial position of the historical target, wherein the initial position of the historical target includes the target detection result and / or the target prediction result of the historical frame, the target prediction result of the historical frame being determined based on the change in pose coordinates of the current vehicle relative to the previous frame corresponding to the historical frame; determining a matching result based on the position of the current target, the initial position of the historical target, and the change in pose coordinates of the current vehicle relative to the previous frame corresponding to the historical frame; and performing target tracking based on the matching result. By calculating the vehicle pose coordinate change rate based on the DR mileage cache queue, and processing the target detection result and / or target prediction result of the historical frame based on the vehicle pose coordinate change rate before matching, the uncertainty of motion prediction can be reduced, thereby improving the accuracy of target tracking.
[0060] Example 2 Figure 2 A schematic diagram of an electronic device 10 that can be used to implement embodiments 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 assistants, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.
[0061] like Figure 2 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory 12 or a random access memory 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the read-only memory 12 or loaded from storage unit 18 into the random access memory 13. The random access memory 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, read-only memory 12, and random access memory 13 are interconnected via a bus 14. An input / output interface 15 is also connected to the bus 14.
[0062] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.
[0063] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing units, graphics processing units, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as target tracking methods.
[0064] In some embodiments, the target tracking method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via read-only memory 12 and / or communication unit 19. When the computer program is loaded into random access memory 13 and executed by processor 11, one or more steps of the target tracking method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the target tracking method by any other suitable means (e.g., by means of firmware).
[0065] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), systems-on-a-chip (SoCs), payload programmable logic devices, computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.
[0066] Computer programs used to implement 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 executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.
[0067] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof.
[0068] 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 cathode ray tube or liquid crystal display) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).
[0069] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.
[0070] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to address the shortcomings of traditional physical hosts and virtual private servers, such as high management difficulty and weak business scalability.
[0071] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.
[0072] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the target tracking method according to any embodiment of the invention.
[0073] In the implementation of a computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages or a combination thereof. Programming languages include object-oriented programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0074] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.
Claims
1. A target tracking method characterized by, include: Construct a dead reckoning (DR) mileage cache queue, wherein the DR mileage cache queue includes: multiple historical frames, and the historical frames include: the change in pose coordinates of the current vehicle relative to the previous frame; Obtain the current target detection result corresponding to the current frame, wherein the current target detection result includes: the position of the current target; The initial position of a historical target is obtained, wherein the initial position of the historical target includes: the target detection result of a historical frame and / or the target prediction result of a historical frame, wherein the target prediction result of the historical frame is determined based on the change in pose coordinates of the current vehicle relative to the previous frame. The matching result is determined based on the current target's position, the initial position of the historical target, and the change in pose coordinates of the current vehicle relative to the previous frame in the historical frame. Target tracking is performed based on the matching results.
2. The method of claim 1, wherein, Based on the current target's position, the initial position of the historical target corresponding to the historical frame, and the change in the current vehicle's pose coordinates relative to the previous frame, the matching result is determined, including: Based on the change in pose coordinates of the current vehicle relative to the previous frame in the historical frame, the initial position of the historical target in the historical frame is transformed to obtain the target position of the historical target, wherein the target position of the historical target is the position in the vehicle coordinate system. Target matching is performed based on the current target's position and the target positions of historical targets to obtain a matching result, wherein the current target's position is its position in the vehicle coordinate system.
3. The method of claim 2, wherein, Target matching is performed based on the current target's location and historical target locations to obtain matching results, including: Based on the location of historical targets and the location of the current target, determine the historical targets that match the current target; Add historical targets that match the current target to the cost matrix of the current target; Target matching is performed based on the Hungarian algorithm and the cost matrix of the current target to obtain matching results, which include the current target and historical targets that match the current target.
4. The method of claim 3, wherein, Based on the location of historical targets and the location of the current target, identify historical targets that match the current target, including: Determine the Mahalanobis distance between the historical target and the current target based on their respective locations. Historical targets whose Mahalanobis distance to the current target is less than the distance threshold are used as historical targets to match the current target.
5. The method according to claim 3, characterized in that, Also includes: If there is a missing target, the position of the missing target is predicted based on the change in pose coordinates relative to the previous frame, wherein the missing target is a historical target that does not match the current target; The predicted location of the lost target is used as the target prediction result for the current frame.
6. The method according to claim 5, characterized in that, Predicting the location of a lost target based on the change in pose coordinates relative to the previous frame includes: If the lost target is a static target, the position of the lost target is predicted based on the change in the pose coordinates of the current vehicle relative to the previous frame and the position of the lost target in the previous frame. If the lost target is a dynamic target, the position is predicted based on Kalman filtering and the historical position of the lost target. The predicted position is then transformed according to the change in pose coordinates relative to the previous frame to obtain the position of the lost target.
7. The method according to claim 5, characterized in that, Also includes: If the number of lost frames for the lost target exceeds a frame count threshold, then the tracking of the lost target is terminated.
8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the target tracking method according to any one of claims 1-7.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the target tracking method according to any one of claims 1-7.
10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the target tracking method according to any one of claims 1-7.
