An object tracking method, device, apparatus, and storage medium

Abstract

The application discloses an object tracking method, device and equipment and a storage medium. The method comprises the following steps: acquiring object information in a preset range of a target vehicle and historical trajectory information associated with the target vehicle; the historical trajectory information is trajectory information of a plurality of historical objects; the trajectory information of each historical object comprises historical position information of each historical object in a historical period; based on the first position information and the historical position information, a matching process is performed on a first quantity of first objects and a plurality of historical objects, so as to obtain a second quantity of first matching pairs; the trajectory information of a first target historical object in the first target matching pair is updated by using the first position information corresponding to a first target object in the first target matching pair. The application avoids the problem that the trajectory is lost due to the object being blocked, and improves the accuracy of object tracking.

Description

Technical Field

[0001] This application relates to the field of object tracking technology, and in particular to an object tracking method, apparatus, device and storage medium. Background Technology

[0002] Machine vision is a common function in the current field of autonomous driving. Video target tracking algorithms, as a practical and important algorithm in machine vision, have a wide range of applications, such as intelligent monitoring, robot vision systems, virtual reality (human tracking), and medical diagnosis (cell state tracking).

[0003] Target tracking algorithms suffer from real-time performance issues in practical applications due to external factors (such as complex application environments, changes in lighting conditions, occlusion, etc.) and changes in the target object itself (such as changes in appearance, size, speed, etc.). Therefore, existing technologies typically extract the target object again by fusing features with different weights to increase the target object's confidence level. However, this introduces multiple complex operations, reducing the system's real-time performance and hindering its application in low-latency scenarios such as autonomous driving. Summary of the Invention

[0004] To address the aforementioned technical issues, this application discloses an object tracking method that matches position information by using the trajectory information of each historical object associated with the target vehicle and the first position information of the first object. This avoids the problem of trajectory loss due to object occlusion and improves the accuracy of object tracking.

[0005] To achieve the above-mentioned objectives, this application provides an object tracking method, the method comprising:

[0006] The system acquires object information within a preset range of the target vehicle and historical trajectory information associated with the target vehicle. The object information includes first location information corresponding to a first number of first objects, where the first objects are objects within the preset range of the target vehicle that are obscured by occluders. The historical trajectory information consists of trajectory information for multiple historical objects, where each historical object is an object within the preset range of the target vehicle during a historical time period. The trajectory information for each historical object includes the historical location information of each historical object during the historical time period.

[0007] Based on the first location information and the historical location information, a matching process is performed on the first number of first objects and the plurality of historical objects to obtain a second number of first matching pairs, wherein the second number is less than or equal to the first number.

[0008] The trajectory information of the first target historical object in the first target matching pair is updated using the first location information corresponding to the first target object in the first target matching pair; the first target matching pair is any one of the first matching pairs; the first target object is one of the first objects, and the first target historical object is one of the multiple historical objects.

[0009] In some implementations, the object information further includes second location information corresponding to each of the third number of second objects; the second object is an object within a preset range of the target vehicle that is not obscured by any obstruction; the matching process based on the first location information and the historical location information to obtain a second number of matching pairs for the first number of first objects and the plurality of historical objects includes:

[0010] Based on the second location information and the historical location information, the second number of second objects and the plurality of historical objects are matched to obtain a fourth number of second matching pairs; the fourth number is less than or equal to the third number.

[0011] When the fourth number is less than the number of historical objects, based on the first location information and the historical location information corresponding to the first historical object, the first number of first objects and at least one first historical object are matched to obtain a second number of matching pairs; the first historical object is a historical object other than the historical object in the fourth number of second matching pairs among the plurality of historical objects.

[0012] In some embodiments, the method further includes:

[0013] If the fourth quantity is less than the third quantity, the trajectory information of the second target object is updated based on the second location information corresponding to the second target object; the second target object is the object in the second object that has not formed the second matching pair with the historical object.

[0014] In some embodiments, the method further includes:

[0015] If the second quantity equals a preset threshold, delete the trajectory information and the first location information corresponding to the first historical object.

[0016] In some embodiments, after performing matching processing on the second number of second objects and the plurality of historical objects based on the second location information and the historical location information to obtain a fourth number of second matching pairs, the method further includes:

[0017] The trajectory information of the second target historical object in the second target matching pair is updated using the second location information corresponding to the third target object in the second target matching pair; the second target matching pair is any one of the second matching pairs; the third target object is one of the second objects, and the second target historical object is one of the multiple historical objects.

[0018] In some implementations, the step of matching the first number of first objects and the plurality of historical objects based on the first location information and the historical location information to obtain a second number of first matching pairs includes:

[0019] Based on the historical location information, the predicted location information corresponding to each of the multiple historical objects is determined;

[0020] Based on the first location information and the predicted location information, the first number of first objects and the plurality of historical objects are matched to obtain a second number of first matching pairs.

[0021] In some implementations, obtaining object information within a preset range of the target vehicle includes:

[0022] Acquire image information and a preset neural network model within a preset range of the target vehicle;

[0023] The image information is input into the preset neural network model to obtain the object information in the image information.

[0024] This application also provides an object tracking device, the device comprising:

[0025] The information acquisition module is used to acquire object information within a preset range of the target vehicle and historical trajectory information associated with the target vehicle. The object information includes first location information corresponding to a first number of first objects, where the first objects are objects within the preset range of the target vehicle that are obscured by obstructions. The historical trajectory information is the trajectory information of multiple historical objects, where the historical objects are objects within the preset range of the target vehicle during a historical time period. The trajectory information of each historical object includes the historical location information of each historical object during the historical time period.

[0026] The matching processing module is used to perform matching processing on the first number of first objects and the plurality of historical objects based on the first location information and the historical location information to obtain a second number of first matching pairs, wherein the second number is less than or equal to the first number;

[0027] The update module is used to update the trajectory information of the first target historical object in the first target matching pair using the first location information corresponding to the first target object in the first target matching pair; the first target matching pair is any one of the first matching pairs; the first target object is one of the first objects, and the first target historical object is one of the multiple historical objects.

[0028] This application also provides an object tracking device, the device including a processor and a memory, the memory storing at least one instruction or at least one program segment, the at least one instruction or the at least one program segment being loaded and executed by the processor to implement the object tracking method as described above.

[0029] This application also provides a computer-readable storage medium storing at least one instruction or at least one program segment, which is loaded by a processor and executed as described above in the object tracking method.

[0030] Implementing the embodiments of this application has the following beneficial effects:

[0031] The object tracking method of this application matches the position information by matching the trajectory information of each historical object associated with the target vehicle with the first position information of the first object. This avoids the problem of trajectory loss due to object occlusion and improves the accuracy of object tracking. Attached Figure Description

[0032] To more clearly illustrate the object tracking method, apparatus, device, and storage medium described in this application, the accompanying drawings required for the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 A schematic diagram illustrating the implementation environment of an object tracking method provided in this application embodiment;

[0034] Figure 2 A flowchart illustrating an object tracking method provided in an embodiment of this application;

[0035] Figure 3 A flowchart illustrating a specific object tracking method provided in an embodiment of this application;

[0036] Figure 4a and 4b This application provides a schematic diagram of a specific scenario at different times.

[0037] Figure 5This is a schematic diagram of the structure of an object tracking device provided in an embodiment of this application;

[0038] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0039] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0040] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or server 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 devices.

[0041] Please see Figure 1 It illustrates a schematic diagram of the implementation environment provided in the embodiments of this application, which may include:

[0042] At least one terminal 01 and at least one server 02. The at least one terminal 01 and the at least one server 02 can communicate data via a network.

[0043] In an optional embodiment, terminal 01 may be the executor of the object tracking method. Terminal 01 may be, but is not limited to, electronic devices such as in-vehicle terminals, smartphones, desktop computers, tablets, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices. The operating system running on terminal 01 may include, but is not limited to, Android, iOS, Linux, Windows, and Unix.

[0044] Server 02 can provide terminal 01 with historical trajectory information associated with the target vehicle. Optionally, server 02 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.

[0045] Please refer to Figure 2 The diagram illustrates a flowchart of an object tracking method provided in this application. This specification provides the operational steps of the method described in the embodiments or flowchart, but based on conventional or non-inventive methods, more or fewer operational steps may be included. The order of steps listed in the embodiments is merely one possible execution order among many steps and does not represent the only execution order. The object tracking method can be executed according to the method order shown in the embodiments or drawings. Specifically, as shown in the attached diagram... Figure 2 As shown, the method includes:

[0046] S201, Obtain object information within a preset range of the target vehicle and historical trajectory information associated with the target vehicle.

[0047] In this embodiment, object information can refer to the association information of a preset object. The preset object can be an object with mobility itself and an attached object to an object with mobility. For example, the preset object can include motor vehicles, non-motor vehicles, pedestrians, animals, and backpacks worn by pedestrians. The association information can include location information and identification information. The object information can include the first location information corresponding to a first number of first objects; wherein, the first number can be a natural number greater than or equal to 1. The object information can also include the identification information of the first object. The first object can be an object occluded by an obstruction within a preset range of the target vehicle. The obstruction can be an object that obstructs the first object; for example, the obstruction can include motor vehicles, non-motor vehicles, traffic signs, trees, etc. The preset range can refer to the sensing range of a pre-set sensing device; wherein, the sensing device can be a device capable of detecting preset objects within the preset range of the target vehicle; for example, the sensing device can include a camera, radar, etc. The first location information can refer to the area containing the edge line of the first object. For example, it can be the area enclosed by a long frame line.

[0048] Historical trajectory information can be the trajectory information of multiple historical objects; historical objects are objects within a preset range of the target vehicle during a historical time period; the trajectory information of each historical object can include its historical location information during the historical time period; the duration of the historical time period can be preset; the end time of the historical time period can be the same as the time when the object information was acquired. The target vehicle can be a vehicle with autonomous driving capabilities. The object information within the preset range of the target vehicle can include object information in front of and to the side of the target vehicle.

[0049] In this embodiment of the application, the object information may further include second location information corresponding to each of the third number of second objects; the second objects are objects within a preset range of the target vehicle that are not obscured by any obstruction; wherein, the third number can be a natural number greater than or equal to 0. For example, such as Figure 4a and 4b The diagram shown is a specific scenario illustration provided by an embodiment of this application at different times; in Figure 4a In the diagram, the object information includes a second object, the second object's second location information, and identification information; for example, the third car from left to right in the image is the second object, and its identification information is id=200055. Figure 4b In the figure, the object information includes a first object and a second object, the first location information and identification information of the first object, and the second location information and identification information of the second object; for example, the third car from left to right in the figure is the first object, and its identification information is id=200055.

[0050] In some exemplary embodiments, image information and a preset neural network model within a preset range of the target vehicle can be acquired; the image information is input into the preset neural network model to obtain object information in the image information. The preset neural network model can be a CNN (Convolutional Neural Network) model.

[0051] In one example, image information of the target vehicle within a preset range can be obtained based on a monocular or binocular camera.

[0052] Specifically, image information acquired by a monocular camera can be input into the preset neural network model to extract deep learning convolutional features from the image information, and object information in the image information can be determined based on the deep learning convolutional features.

[0053] The image information acquired by the binocular camera can be preprocessed first, and then the preprocessed image information can be input into a preset neural network model to extract the deep learning convolutional features of the image information. Based on the deep learning convolutional features, the object information in the image information can be determined.

[0054] In another exemplary embodiment, point cloud information within a preset range of the target vehicle can be obtained, and object information within the preset range of the target vehicle can be determined based on the point cloud information.

[0055] In one example, the association information of preset objects within a preset range of a vehicle can be determined based on point cloud information.

[0056] In some exemplary embodiments, the trajectory information of each historical object of the target vehicle within a historical period can be directly obtained, and the historical trajectory information associated with the target vehicle can be determined based on multiple trajectory information.

[0057] In one example, trajectory information can be generated dynamically; a collection of multiple trajectory information can be identified as the historical trajectory information associated with the target vehicle.

[0058] In another exemplary embodiment, the historical location information of each historical object associated with the target vehicle during the historical period can be obtained; based on the historical location information, the trajectory information corresponding to each historical object can be determined; and based on the multiple trajectory information, the historical trajectory information associated with the target vehicle can be determined.

[0059] In one example, trajectory information can be generated in real time based on historical location information; a collection of multiple trajectory information can be determined as the historical trajectory information associated with the target vehicle.

[0060] S203, based on the first location information and historical location information, perform matching processing on a first number of first objects and multiple historical objects to obtain a second number of first matching pairs.

[0061] In this embodiment, the first matching pair can be a matching pair obtained by matching a first object and a historical object; each matching pair includes a first target object and a first target historical object; the first target object is an object among the first objects, and the first target historical object is an object among the plurality of historical objects. The second quantity can be a natural number greater than or equal to 0, and the second quantity is less than or equal to the first quantity.

[0062] In this embodiment of the application, the object information further includes second position information corresponding to each of the third number of second objects; wherein, the third number can be a natural number greater than or equal to 0.

[0063] Optionally, when the third quantity is equal to 0, the first quantity of first objects and the plurality of historical objects can be directly matched based on the first location information and historical location information to obtain the second quantity of first matching pairs.

[0064] In some exemplary embodiments, predicted location information corresponding to each of the plurality of historical objects can be determined based on the historical location information; based on the first location information and the predicted location information, a matching process is performed on the first number of first objects and the plurality of historical objects to obtain a second number of first matching pairs.

[0065] In one example, a preset prediction model can be obtained; for each historical object, position prediction can be performed based on the preset prediction model and the trajectory information formed by the historical position information corresponding to that historical object, to obtain the predicted position information of that historical object at the target time. The target time can be the time corresponding to the first position information of the first object.

[0066] When the matching degree between the first location information and the predicted location information reaches a preset threshold, the first target object corresponding to the first location information and the first target historical object corresponding to the predicted location information are determined to form a first matching pair.

[0067] Specifically, the first target object and the first target historical object that form the first matching pair can be the same object.

[0068] Specifically, the degree of matching between the primary location information and the predicted location information can be calculated using the Hungarian algorithm.

[0069] In some other exemplary embodiments, the predicted trajectory information corresponding to each of the plurality of historical objects can be determined based on historical location information; based on the predicted trajectory information and the first location information, a first number of first objects and the plurality of historical objects are matched to obtain a second number of first matching pairs.

[0070] In one example, if there is an intersection between the predicted trajectory information and the first location information, it can be determined that the first target object corresponding to the first location information and the first target historical object corresponding to the predicted location information form a first matching pair.

[0071] Optionally, if the third quantity is greater than or equal to 0, the second quantity of second objects and the plurality of historical objects can be matched based on the second location information and the historical location information to obtain a fourth quantity of second matching pairs; the fourth quantity is less than or equal to the third quantity; if the fourth quantity is less than the quantity of historical objects, the first quantity of first objects and at least one first historical object can be matched based on the first location information and the historical location information corresponding to the first historical object to obtain a second quantity of matching pairs; the first historical object is a historical object other than the historical object in the fourth quantity of second matching pairs among the plurality of historical objects.

[0072] In some exemplary embodiments, predicted location information corresponding to each of the plurality of historical objects can be determined based on the historical location information; based on the second location information and the predicted location information, a matching process is performed on the third number of second objects and the plurality of historical objects to obtain a fourth number of first matching pairs. When the third number is equal to 0, the fourth number is equal to 0. Correspondingly, the number of first historical objects is the same as the number of historical objects.

[0073] In some other exemplary embodiments, the predicted trajectory information corresponding to each of the plurality of historical objects can be determined based on historical location information; based on the predicted trajectory information and the second location information, a third number of second objects and the plurality of historical objects are matched to obtain a fourth number of first matching pairs.

[0074] S205, using the first position information corresponding to the first target object in the first target matching pair, update the trajectory information of the first target historical object in the first target matching pair; the first target matching pair is any of the first matching pairs.

[0075] Optionally, when the third quantity is 0, that is, when there is no second object, the trajectory information can be updated in the following way.

[0076] In some exemplary embodiments, when the second quantity exceeds a preset threshold, the trajectory information of the first target historical object in the first target matching pair is updated using the first location information corresponding to the first target object in the first target matching pair. The preset threshold is equal to 0.

[0077] In other exemplary embodiments, when the second quantity equals a preset threshold, the trajectory information corresponding to the first historical object and the first location information are deleted. Here, the second quantity equaling the preset threshold indicates that the first object corresponding to the first location information is a newly added occluded object; in this application, the method of not adding a trajectory for newly added occluded objects can reduce the tracking false detection rate.

[0078] In one example, the first location information corresponding to the first target object can be used as a new location for the trajectory information of the first target historical object to update the trajectory, thus obtaining the target trajectory of the first target historical object; that is, the trajectory of the first target object.

[0079] Optionally, when the third quantity is 0, that is, when a second object exists, the trajectory information can be updated in the following way.

[0080] The second object may include a second target object and a third target object; the second target object may be an object in the second object that does not form a second matching pair with a historical object. The third target object may be an object in the second object that forms a second matching pair with a historical object; wherein, the third target object may be an object in the second object other than the second target object.

[0081] In some exemplary embodiments, when the fourth quantity is less than the third quantity, the trajectory information of the second target object is updated based on the second location information corresponding to the second target object. The fourth quantity being less than the third quantity can indicate the presence of newly added, unoccluded objects. This approach can improve the comprehensiveness of object tracking.

[0082] In some other exemplary embodiments, when the fourth quantity is greater than 0, the trajectory information of the second target historical object in the second target matching pair can be updated using the second location information corresponding to the third target object in the second target matching pair; the second target matching pair is any of the second matching pairs; the third target object is one of the second objects, and the second target historical object is one of the plurality of historical objects.

[0083] In one example, the second location information corresponding to the third target object can be used as a new location for the trajectory information of the second target historical object to update the trajectory, thus obtaining the target trajectory of the second target historical object; that is, the trajectory of the third target object.

[0084] In this embodiment, the present application matches the location information by matching the trajectory information corresponding to each historical object associated with the target vehicle with the first location information of the first object, which can avoid the problem of trajectory loss due to object occlusion and improve the accuracy of object tracking.

[0085] In some exemplary embodiments, such as Figure 3 The diagram shown is a flowchart of a specific object tracking method provided in an embodiment of this application; the details are as follows.

[0086] S301, acquire object information within a preset range of the target vehicle and historical trajectory information associated with the target vehicle; the object information includes first location information corresponding to a first number of first objects and second location information corresponding to a third number of second objects, wherein the first objects are objects that are occluded within the preset range of the target vehicle; and the second objects are objects that are not occluded within the preset range of the target vehicle.

[0087] S303, based on the second location information and historical location information, a second number of second objects and multiple historical objects are matched to obtain a fourth number of second matching pairs; the fourth number is less than or equal to the third number.

[0088] S305, when the fourth quantity is less than the number of historical objects, based on the first location information and the historical location information corresponding to the first historical object, the first quantity of first objects and at least one first historical object are matched to obtain a second quantity of matching pairs; the first historical object is a historical object other than the historical object in the fourth quantity of the second matching pairs among the plurality of historical objects.

[0089] S307, using the first location information corresponding to the first target object in the first target matching pair, update the trajectory information of the first target historical object in the first target matching pair; the first target matching pair is any one of the first matching pairs; the first target object is one of the first objects, and the first target historical object is one of the multiple historical objects.

[0090] In this embodiment, the application first matches the historical object corresponding to the historical trajectory associated with the target vehicle with the second object, and then matches it with the first object. This can minimize the loss of historical trajectory during object tracking and effectively improve the tracking accuracy of the same object.

[0091] This application also provides an object tracking device, such as... Figure 5 As shown, this is a schematic diagram of the structure of an object tracking device provided in an embodiment of this application; specifically, the device includes:

[0092] The information acquisition module 501 is used to acquire object information within a preset range of the target vehicle and historical trajectory information associated with the target vehicle. The object information includes first location information corresponding to a first number of first objects, where the first objects are objects within the preset range of the target vehicle that are obscured by obstructions. The historical trajectory information is the trajectory information of multiple historical objects, where the historical objects are objects within the preset range of the target vehicle during a historical time period. The trajectory information of each historical object includes the historical location information of each historical object during the historical time period.

[0093] Matching processing module 502 is used to perform matching processing on the first number of first objects and the plurality of historical objects based on the first location information and the historical location information to obtain a second number of first matching pairs, wherein the second number is less than or equal to the first number;

[0094] The update module 503 is used to update the trajectory information of the first target historical object in the first target matching pair using the first location information corresponding to the first target object in the first target matching pair; the first target matching pair is any one of the first matching pairs; the first target object is one of the first objects, and the first target historical object is one of the multiple historical objects.

[0095] In this embodiment of the application, the matching processing module 502 includes:

[0096] The first matching unit is configured to perform matching processing on the second number of second objects and the plurality of historical objects based on the second location information and the historical location information, to obtain a fourth number of second matching pairs; the fourth number is less than or equal to the third number.

[0097] The second matching unit is configured to, when the fourth number is less than the number of historical objects, perform matching processing on the first number of first objects and at least one first historical object based on the first location information and the historical location information corresponding to the first historical object, to obtain a second number of matching pairs; the first historical object is a historical object other than the historical object in the fourth number of second matching pairs among the plurality of historical objects.

[0098] In this embodiment of the application, it also includes:

[0099] The first update unit is used to update the trajectory information of the second target object based on the second location information corresponding to the second target object when the fourth quantity is less than the third quantity; the second target object is the object in the second object that has not formed the second matching pair with the historical object.

[0100] In this embodiment of the application, it also includes:

[0101] The second update unit is used to delete the trajectory information and the first location information corresponding to the first historical object when the second quantity is equal to a preset threshold.

[0102] In this embodiment of the application, it also includes:

[0103] The third update unit is used to update the trajectory information of the second target historical object in the second target matching pair using the second location information corresponding to the third target object in the second target matching pair; the second target matching pair is any one of the second matching pairs; the third target object is one of the second objects, and the second target historical object is one of the multiple historical objects.

[0104] In this embodiment of the application, the matching processing module 502 further includes:

[0105] The first determining unit is used to determine the predicted location information corresponding to each of the plurality of historical objects based on the historical location information;

[0106] The third matching unit is used to perform matching processing on the first number of first objects and the plurality of historical objects based on the first location information and the predicted location information to obtain a second number of first matching pairs.

[0107] In this embodiment of the application, the information acquisition module 501 includes:

[0108] The acquisition unit is used to acquire image information and a preset neural network model within a preset range of the target vehicle;

[0109] The processing unit is used to input the image information into the preset neural network model to obtain object information in the image information.

[0110] It should be noted that the apparatus and method embodiments described in the device embodiments are based on the same inventive concept.

[0111] This application provides an object tracking device, which includes a processor and a memory. The memory stores at least one instruction or at least one program. The processor loads and executes the at least one instruction or at least one program to implement the object tracking method as described in the above method embodiments.

[0112] Furthermore, Figure 6 A schematic diagram of the hardware structure of an electronic device for implementing the object tracking method provided in the embodiments of this application is shown. The electronic device may participate in or include the object tracking apparatus provided in the embodiments of this application. Figure 6 As shown, the electronic device 60 may include one or more processors 602 (shown as 602a, 602b, ..., 602n in the figure) (processor 602 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 604 for storing data, and a transmission device 606 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 6 The structure shown is for illustrative purposes only and does not limit the structure of the electronic device described above. For example, electronic device 60 may also include... Figure 6 The more or fewer components shown, or having the same Figure 6 The different configurations shown.

[0113] It should be noted that the aforementioned one or more processors 602 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be wholly or partially integrated into any other element within the electronic device 60 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0114] The memory 604 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the object tracking method described in the embodiments of this application. The processor 602 executes various functional applications and data processing by running the software programs and modules stored in the memory 604, thereby realizing the object tracking method described above. The memory 604 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 instances, the memory 604 may further include memory remotely located relative to the processor 602, and these remote memories can be connected to the electronic device 60 via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0115] The transmission device 606 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the electronic device 60. In one example, the transmission device 606 includes a network interface controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In one embodiment, the transmission device 606 may be a radio frequency (RF) module for wireless communication with the Internet.

[0116] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows a user to interact with the user interface of an electronic device 60 (or a mobile device).

[0117] Embodiments of this application also provide a computer-readable storage medium, which can be disposed in an electronic device to store at least one instruction or at least one program related to implementing an object tracking method in the method embodiments. The at least one instruction or the at least one program is loaded and executed by the processor to implement the object tracking method provided in the above method embodiments.

[0118] Optionally, in this embodiment, the storage medium may be located at at least one of the multiple network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0119] It should be noted that the order of the embodiments described above is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, the above description focuses on specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired results. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired results. In some implementations, multitasking and parallel processing are also possible or may be advantageous.

[0120] According to one aspect of this application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the methods provided in the various alternative implementations described above.

[0121] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the device and electronic device embodiments are basically similar to the method embodiments, so the descriptions are relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0122] Those skilled in the art will understand that all or part of the steps of the above embodiments can be implemented by hardware or by a program instructing related hardware. The program can be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0123] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An object tracking method, characterized in that, The method includes: The system acquires object information within a preset range of the target vehicle and historical trajectory information associated with the target vehicle. The object information includes first location information corresponding to a first number of first objects and second location information corresponding to a third number of second objects. The first objects are objects within the preset range of the target vehicle that are obscured by objects; the second objects are objects within the preset range of the target vehicle that are not obscured by objects. The historical trajectory information consists of trajectory information for multiple historical objects, which are objects within the preset range of the target vehicle during a historical time period. The trajectory information for each historical object includes its historical location information during the historical time period. The first location information refers to the area containing the edge line of the first object. Based on the second location information and the historical location information, the third number of second objects and the plurality of historical objects are matched to obtain a fourth number of second matching pairs; the fourth number is less than or equal to the third number. Based on the first location information and the historical location information, a first number of first objects and the plurality of historical objects are matched to obtain a second number of first matching pairs, wherein the second number is less than or equal to the first number; wherein, the step of matching the first number of first objects and the plurality of historical objects based on the first location information and the historical location information to obtain a second number of first matching pairs includes: when the fourth number is less than the number of historical objects, matching the first number of first objects and at least one first historical object based on the historical location information corresponding to the first historical object to obtain a second number of first matching pairs; the first historical object is a historical object other than the historical object in the fourth number of second matching pairs among the plurality of historical objects; when the third number is equal to 0, determining the predicted location information corresponding to each of the plurality of historical objects based on the historical location information; and matching the first number of first objects and the plurality of historical objects based on the first location information and the predicted location information to obtain a second number of first matching pairs; When the second quantity equals a preset threshold, the trajectory information and the first location information corresponding to the first historical object are deleted; the second quantity equaling the preset threshold indicates that the first object corresponding to the first location information is a newly added occluded object; The trajectory information of the first target historical object in the first target matching pair is updated using the first location information corresponding to the first target object in the first target matching pair; the first target matching pair is any one of the first matching pairs; the first target object is one of the first objects, and the first target historical object is one of the multiple historical objects.

2. The object tracking method according to claim 1, characterized in that, The method further includes: If the fourth quantity is less than the third quantity, the trajectory information of the second target object is updated based on the second location information corresponding to the second target object; the second target object is the object in the second object that has not formed the second matching pair with the historical object.

3. The object tracking method according to claim 1, characterized in that, After performing matching processing on the third number of second objects and the plurality of historical objects based on the second location information and the historical location information to obtain a fourth number of second matching pairs, the method further includes: The trajectory information of the second target historical object in the second target matching pair is updated using the second location information corresponding to the third target object in the second target matching pair; the second target matching pair is any one of the second matching pairs; the third target object is one of the second objects, and the second target historical object is one of the multiple historical objects.

4. The object tracking method according to claim 1, characterized in that, The acquisition of object information within a preset range of the target vehicle includes: Acquire image information and a preset neural network model within a preset range of the target vehicle; The image information is input into the preset neural network model to obtain the object information in the image information.

5. An object tracking device, characterized in that, The device includes: The information acquisition module is used to acquire object information within a preset range of the target vehicle and historical trajectory information associated with the target vehicle. The object information includes first location information corresponding to a first number of first objects and second location information corresponding to a third number of second objects. The first objects are objects within the preset range of the target vehicle that are obscured by obstructions; the second objects are objects within the preset range of the target vehicle that are not obscured by obstructions. The historical trajectory information consists of trajectory information for multiple historical objects, which are objects within the preset range of the target vehicle during a historical time period. The trajectory information of each historical object includes the historical location information of each historical object during the historical time period. The first location information refers to the area containing the edge line of the first object. A matching processing module is configured to perform matching processing on a third number of second objects and a plurality of historical objects based on second location information and the historical location information to obtain a fourth number of second matching pairs; the fourth number is less than or equal to the third number; and to perform matching processing on a first number of first objects and a plurality of historical objects based on the first location information and the historical location information to obtain a second number of first matching pairs, the second number being less than or equal to the first number; wherein, the step of performing matching processing on a first number of first objects and a plurality of historical objects based on the first location information and the historical location information to obtain a second number of first matching pairs includes: when the fourth number is less than the number of historical objects, performing matching processing on a first number of first objects and at least one first historical object based on the historical location information corresponding to the first historical object based on the first location information to obtain a second number of first matching pairs; the first historical object is a historical object other than the historical object in the fourth number of second matching pairs among the plurality of historical objects; when the third number is equal to 0, determining the predicted location information corresponding to each of the plurality of historical objects based on the historical location information; and performing matching processing on a first number of first objects and a plurality of historical objects based on the first location information and the predicted location information to obtain a second number of first matching pairs; The update module is used to delete the trajectory information and the first location information corresponding to the first historical object when the second quantity equals a preset threshold; the second quantity equals the preset threshold, indicating that the first object corresponding to the first location information is a newly added occluded object; and to update the trajectory information of the first target historical object in the first target matching pair using the first location information corresponding to the first target object in the first target matching pair; the first target matching pair is any one of the first matching pairs; the first target object is one of the first objects, and the first target historical object is one of the plurality of historical objects.

6. An object tracking device, characterized in that, The device includes a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or the at least one program being loaded and executed by the processor to implement the object tracking method as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The storage medium stores at least one instruction or at least one program segment, which is loaded and executed by a processor according to any one of claims 1 to 4.

Images