Object tracking method and device, electronic equipment and storage medium
By obtaining and matching multiple object data to be tracked within the monitoring range during object tracking, the target loss problem caused by dressing up or makeup during object tracking is solved, and the effect of accurately tracking and avoiding target loss is achieved.
Patent Information
- Application Number
- CN202411425080.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-12
- Publication Date
- 2025-02-28
AI Technical Summary
During object tracking, if there are factors such as tracking object dressing or makeup that interfere with facial recognition, it will lead to loss of tracking targets.
When it is detected that the matching degree between the target tracking object data within the monitoring range of the target monitoring device and the stored target tracking feature data is less than the preset matching degree, multiple object data to be tracked and historical tracking feature data within the monitoring range are obtained and matched to generate a matching result. When the matching result is a preset matching result, it is determined that the target tracking object data matches the target tracking feature data.
It is implemented to use global matching to accurately track the target tracking object when the target tracking object matches fail to match, so as to avoid loss of tracking targets.
Smart Images
Figure CN119541013A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to an object tracking method and device, electronic equipment, and storage medium. Background Art
[0002] Currently, object tracking is usually achieved by collecting image data through monitoring equipment for face recognition. However, in the actual tracking process, if there are factors that interfere with facial recognition such as the tracked object changing clothes or putting on makeup, the tracking target will be lost. Summary of the invention
[0003] In view of the above problems, a method and device for object tracking, an electronic device, and a storage medium are proposed to overcome the above problems or at least partially solve the above problems, including:
[0004] An object tracking method, the method comprising:
[0005] When it is detected that the matching degree between the target tracking object data within the monitoring range of the target monitoring device and the stored target tracking feature data is less than a preset matching degree, acquiring a plurality of to-be-tracked object data and historical tracking feature data within the monitoring range including the target tracking object data;
[0006] Matching the plurality of to-be-tracked object data with the historical tracking feature data to generate a matching result;
[0007] If the matching result is a preset matching result, it is determined that the target tracking object data matches the target tracking feature data.
[0008] Optionally, when the preset matching result is that the target object data to be tracked except the target tracking object data and the historical tracking feature data except the target tracking feature data are all matched successfully.
[0009] Optionally, matching the plurality of to-be-tracked object data with the historical tracking feature data comprises:
[0010] Extracting object feature data for each object data to be tracked according to the feature type of the historical tracking feature data;
[0011] The object feature data is matched with the historical tracking feature data.
[0012] Optionally, matching the object feature data with the historical tracking feature data includes:
[0013] When there are multiple pieces of object feature data, determining a matching order of the multiple pieces of object feature data;
[0014] The object feature data is matched with the historical tracking feature data according to the matching order.
[0015] Optionally, it also includes:
[0016] When the target tracking object data matches the target tracking feature data, determining an object identifier corresponding to the target tracking feature data;
[0017] The target tracking object data is marked with the object identifier in the monitoring video data collected by the preset monitoring device.
[0018] Optionally, it also includes:
[0019] When it is detected that the target tracking object moves out of the monitoring range of the preset monitoring device, the object identifier is deleted from the monitoring video data.
[0020] Optionally, it also includes:
[0021] When it is detected that the matching degree between the target tracking object data within the monitoring range of the preset monitoring device and the stored target tracking feature data is greater than or equal to the preset matching degree, it is determined that the target tracking object data matches the target tracking feature data.
[0022] An object tracking device, the device comprising:
[0023] A tracking data acquisition module, configured to acquire a plurality of to-be-tracked object data and historical tracking feature data within the monitoring range of the target monitoring device, when it is detected that the matching degree between the target tracking object data and the stored target tracking feature data is less than a preset matching degree;
[0024] A tracking data matching module, used for matching the plurality of to-be-tracked object data with the historical tracking feature data to generate a matching result;
[0025] A matching success module is used to determine that the target tracking object data matches the target tracking feature data if the matching result is a preset matching result.
[0026] An electronic device comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein the computer program implements the target object tracking method as described above when executed by the processor.
[0027] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the target object tracking method described above is implemented.
[0028] The embodiments of the present invention have the following advantages:
[0029] When it is detected that the matching degree between the target tracking object data within the monitoring range of the target monitoring device and the stored target tracking feature data is less than the preset matching degree, a plurality of to-be-tracked object data and historical tracking feature data including the target tracking object data within the monitoring range are obtained; the plurality of to-be-tracked object data are matched with the historical tracking feature data to generate a matching result; if the matching result is the preset matching result, it is determined that the target tracking object data matches the target tracking feature data, thereby achieving accurate tracking of the target tracking object by global matching when the target tracking object matching fails, and avoiding loss of the tracking target. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] In order to more clearly illustrate the technical solution of the present invention, the accompanying drawings required for use in the description of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.
[0031] Figure 1 is a flowchart of a method for object tracking provided by one embodiment of the present invention;
[0032] Figure 2 is a flowchart of another object tracking method provided by an embodiment of the present invention;
[0033] Figure 3 is a flowchart of another object tracking method provided by an embodiment of the present invention;
[0034] Figure 4 It is a schematic diagram of the structure of an object tracking device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0035] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0036] Reference Figure 1 , shows a flowchart of a method for object tracking provided by an embodiment of the present invention, which may specifically include the following steps:
[0037] Step S101, when it is detected that the matching degree between the target tracking object data within the monitoring range of the target monitoring device and the stored target tracking feature data is less than a preset matching degree, a plurality of to-be-tracked object data and historical tracking feature data including the target tracking object data within the monitoring range are acquired;
[0038] The object tracking method in the embodiment of the present invention is applied to an AI server connected to one or more target monitoring devices. In actual applications, the target monitoring device is only used to collect audio and video data and does not have computing power, while the AI server is a server with computing power. It can then perform analysis and calculation based on the target tracking data collected by one or more target monitoring devices to determine whether the target tracking object data is a tracking object that has appeared previously, so as to avoid the loss of the tracking object.
[0039] In practical applications, the target monitoring device may be distributed in or near the area to be detected. It should be noted that the monitoring range of the target monitoring device must include part or all of the area to be detected in order to facilitate monitoring of the area to be detected.
[0040] The target monitoring device can collect video image data within the monitoring range and send the video image data to the AI server. The AI server can then analyze the video image data frame by frame to determine the target tracking object data in the video image data. The target tracking object data is the object that first entered the monitoring range of the monitoring device but lost the corresponding tracking feature data during the tracking process. Furthermore, the target tracking feature data of the previously tracked or lost object stored in the AI server can be obtained.
[0041] Then, the target tracking object data and the target tracking feature data can be matched to determine the degree of matching between the target tracking object data and the target tracking feature data. When the degree of matching between the two is less than the preset degree of matching, the degree of matching between the target tracking object data and the target tracking feature data is low. At this time, in order to improve the tracking accuracy, multiple data of objects to be tracked and historical tracking feature data including the target tracking object data within the monitoring range can be further obtained for comprehensive matching to confirm the tracking feature data of the target tracking object.
[0042] The target tracking object data may be a lost object in the video image data, and the previous tracking data corresponding to the object is not determined. The object data to be tracked may be all objects within the monitoring range that have lost tracking feature data. The target tracking feature data may be the tracking feature data previously extracted and stored for the tracking object, and the historical tracking feature data may be the tracking feature data previously extracted and stored for the tracking object including the target tracking feature data. The feature types of the tracking feature data may include: any one or more of gender, age, face shape, facial features, and clothing. Among them, the gender type may be divided into male and female. Age may be divided into different age groups, such as 0-18, 19-30, 30-50, 50-100, etc. The face shape may be the facial contour features extracted based on face recognition. For example, the face shape may be specifically divided into oval face, square face, round face, square face, etc. The facial features may specifically be the distribution position of the facial features, and the clothing features may be specifically divided from the clothing classification.
[0043] In an embodiment of the present invention, when the tracked object enters the monitoring range for the first time, the AI server can extract the target tracking feature data of the tracked object and store the target tracking feature information, and then monitor the tracked object in real time and generate the movement trajectory of the tracked object. In this process, the tracked object is bound to the target tracking feature information. In the subsequent tracking process, if a preset event occurs and causes the target tracking object to lose tracking, that is, the target tracking object is unbound from the previous target tracking feature data, then matching can be performed based on the unbound target tracking object data and tracking feature data in the current state. Among them, the preset event can be an event that causes the loss of tracking, such as the object changing clothes, the object putting on makeup, etc.
[0044] It should be noted that the preset matching degree can be set according to actual scene requirements, and no excessive restrictions are imposed on this in the embodiments of the present invention.
[0045] For example, when the tracked object A enters the monitoring range, the video image data of the tracked object A can be captured by the target monitoring device, and then the video image data can be sent to the AI server for analysis to obtain the tracking feature data a related to the tracked object A. When the tracked object A moves within the monitoring range, the AI server can use the tracking feature data to match the tracked object A.
[0046] When the tracking object A changes clothes, the AI server matches the tracking objects within the monitoring range again. At this time, the matching degree between the tracking object A and the previous tracking feature data a is lower than the preset matching degree. Then the AI server's computing network analysis can be triggered, that is, the objects to be tracked within the monitoring range are obtained and matched one by one. When the matching degrees of other objects to be tracked are higher than the preset matching degree, and only the tracking object A and the tracking feature data a have a matching degree lower than the preset matching degree, it can be determined that the tracking object A and the tracking feature data a are matched, and the tracking object A is likely to have changed clothes.
[0047] In one embodiment of the present invention, when the stored target tracking feature data loses the tracking object, the location information of the last successful matching of the tracking object before the target tracking feature data can be determined, and then, the matching area can be determined based on the location information. The matching area can be determined according to the layout near the location information. For example, if the last location where the tracking object appeared is the door of a room indoors, then the next location where the tracking object appears is likely to be near the room area, and then the area around the room can be used as the matching area.
[0048] After determining the matching area, the target tracking object data appearing in the matching area can be extracted based on the monitoring video data uploaded by the target monitoring device, and then the target tracking object data can be matched with the target tracking feature data. When the matching degree between the target tracking object data and the stored target tracking feature data is less than the preset matching degree, multiple to-be-tracked object data and historical tracking feature data within the monitoring range can be obtained for large-scale matching, so as to further determine whether there is any previously stored tracking feature data for the target tracking object data.
[0049] For example, when tracking object A and tracking object B enter a room at the same time, the target monitoring device cannot monitor the interior of the room, so tracking object A and tracking object B lose tracking at the same time. When tracking object A changes clothes, it and tracking object B come out of the room one after another and enter the monitoring range of the target monitoring device again. At this time, tracking object A cannot match the currently stored target tracking feature data a.
[0050] After analysis by the AI server, the objects entering the room are only tracking objects A and tracking object B. If the tracking object B has matched the previously stored tracking feature data b at this time, the unmatched target tracking feature data a can be determined as the prior tracking feature data of tracking object A, that is, tracking object A matches the tracking feature data a.
[0051] In one embodiment of the present invention, the matching process of the target tracking object data and the stored target tracking feature data is as follows: extracting the first object feature data of the target tracking object data according to the feature type of the target tracking feature data, and then matching the first object feature data with the target tracking feature data to calculate the matching degree.
[0052] When the first object feature data is multiple, they can be matched in the order of the matching of the multiple feature data to obtain the sub-matching degree of each feature data, and then the total matching degree of the first object feature is calculated based on the multiple sub-matching degrees, so as to match according to the total matching degree and the preset matching degree.
[0053] Specifically, the first weight corresponding to each feature data can be pre-set in the AI server, and then the weighted sum is performed based on the first weight and the corresponding sub-matching degree to obtain the total matching degree. The sum of the weights of all feature data matching degrees is 1, and the first weight of each sub-matching degree is between 0 and 1. The specific data can be set according to the actual scenario.
[0054] That is, the total matching degree=sub-matching degree 1*the first weight of sub-matching degree 1+sub-matching degree 2*the first weight of sub-matching degree 2...+sub-matching degree n*the first weight of sub-matching degree n.
[0055] The first weight of sub-matching degree 1+the first weight of sub-matching degree 2+...+the first weight of sub-matching degree n=1.
[0056] In one embodiment of the present invention, when it is detected that the matching degree between the target tracking object data within the monitoring range of the preset monitoring device and the stored target tracking feature data is greater than or equal to the preset matching degree, it is determined that the target tracking object data matches the target tracking feature data.
[0057] Step S102, matching multiple to-be-tracked object data with historical tracking feature data to generate a matching result;
[0058] After obtaining the object data to be tracked and the historical tracking feature data, matching may be performed to generate a matching result, wherein the matching result may include a matching success or matching failure result for each object data to be tracked.
[0059] In actual applications, when the matching degree between the object data to be tracked and the historical tracking feature data is greater than or equal to the preset matching degree, it is determined that the object data to be tracked and the historical tracking feature data match successfully; if the matching degree between the object data to be tracked and the historical tracking feature data is less than the preset matching degree, it is determined that the object data to be tracked and the historical tracking feature data match unsuccessfully.
[0060] In one embodiment of the present invention, the process of matching multiple to-be-tracked object data with historical tracking feature data may specifically include: extracting object feature data for each to-be-tracked object data according to the feature type of the historical tracking feature data; and matching the object feature data with the historical tracking feature data.
[0061] In practical applications, the feature type can be determined by first determining the historical tracking feature data, and then features can be extracted for each data to be tracked. Specifically, feature extraction can be performed according to the feature type to obtain object feature data, and the extracted object feature data can be matched with the historical tracking feature data to determine the matching result.
[0062] Specifically, matching the object feature data with the historical tracking feature data includes: when there are multiple pieces of object feature data, determining a matching order of the multiple pieces of object feature data; and matching the object feature data with the historical tracking feature data according to the matching order.
[0063] In actual applications, the AI server can define the matching order of multiple object feature data according to the actual scenario, and then match the object feature data and historical tracking feature data one by one according to the matching order to obtain the matching result of each feature data, and then the matching result of each special diagnosis data can be combined to determine the matching result of the object to be tracked.
[0064] For example, the matching order of each feature type may be defined as gender-age-face shape-facial features-clothing.
[0065] When the above five matches are completely consistent, it is 100%. When one of the above matches is unsuccessful, it does not affect the matching cycle. When at least two matches are unsuccessful, the matching degree is low, and the matching results of the two matching objects are determined to be unmatched.
[0066] In one example, a weight can be set for each object feature data, and the weight of each item is between 0 and 1. The sum of the weights of all object feature data is one. The specific weight data can be set according to the actual scenario, and no excessive restrictions are made on this in the embodiments of the present invention.
[0067] Therefore, after the cyclic matching is completed, a weighted calculation can be performed based on the matching degree of each item of object feature data and the weight of its object to obtain the matching degree of the data of the object to be tracked.
[0068] That is, the matching degree of the object data to be tracked = matching degree of feature 1 * weight of feature 1 + matching degree of feature 2 * weight of feature 2 ... + matching degree of feature n * weight of feature n.
[0069] Feature 1 weight + feature 2 weight + ... + feature n weight = 1.
[0070] Step S103: if the matching result is a preset matching result, it is determined that the target tracking object data matches the target tracking feature data.
[0071] Wherein, when the preset matching result is that the target object data to be tracked except the target tracking object data and the historical tracking feature data except the target tracking feature data are all matched successfully.
[0072] The embodiment of the present invention can be used for object tracking in a video network. By analyzing the target tracking object in combination with the global matching within the monitoring range when there is a preliminary mismatch, it is determined whether the target tracking object matches the target tracking feature data, thereby effectively improving security and avoiding the loss of the tracking target.
[0073] In one embodiment of the present invention, when the target tracking object data matches the target tracking feature data, the object identifier corresponding to the target tracking feature data is determined; and the target tracking object data is marked with the object identifier in the monitoring video data collected by the preset monitoring device.
[0074] In practical applications, when the target tracking object data first enters the monitoring range of the monitoring device, a virtual object identifier (such as a virtual ID identifier) can be assigned to the target tracking object. When the target tracking object loses tracking, the virtual object identifier can be stored in the AI server in correspondence with the target tracking feature data. When the target tracking object data is found again, the target tracking object can be associated with the object identifier and the target tracking feature data again, and the target tracking object data can be marked with the object identifier in the monitoring video data collected by the preset monitoring device.
[0075] In another embodiment of the present invention, when it is detected that the target tracking object moves out of the monitoring range of the preset monitoring device, the object identifier is deleted in the monitoring video data.
[0076] In practical applications, when it is determined that the target tracking object moves out of the monitoring range, the object identifier in the video data can be removed synchronously to ensure the accuracy of the monitoring video data.
[0077] In one embodiment of the present invention, the object marking method of the target tracking object is to display the ID number on the video frame, and the ID can be classified and identified to intuitively display the details of the crowd within the monitoring range of the target monitoring device, such as the ratio of men to women, the ratio of age, etc.
[0078] In one embodiment of the present invention, the feature type includes any one or more of the following:
[0079] Gender, age, face shape, facial features, clothing.
[0080] Among them, gender type can be divided into male and female. Age can be divided into different age groups, such as 0-18, 19-30, 30-50, 50-100, etc. Face shape can be facial contour features extracted based on face recognition, for example, face shape can be specifically divided into oval face, square face, round face, square face, etc. Facial features can be specifically the distribution of facial features, and clothing features can be specifically divided from clothing categories.
[0081] In an embodiment of the present invention, when it is detected that the matching degree between the target tracking object data within the monitoring range of the target monitoring device and the stored target tracking feature data is less than a preset matching degree, a plurality of object data to be tracked and historical tracking feature data including the target tracking object data within the monitoring range are obtained; the plurality of object data to be tracked are matched with the historical tracking feature data to generate a matching result; if the matching result is a preset matching result, it is determined that the target tracking object data matches the target tracking feature data, thereby achieving accurate tracking of the target tracking object by global matching when the target tracking object data fails to match, thereby avoiding loss of the tracking target.
[0082] Reference Figure 2 , shows a flowchart of another object tracking method provided by an embodiment of the present invention, which may specifically include the following steps:
[0083] Step S201, when it is detected that the matching degree between the target tracking object data within the monitoring range of the target monitoring device and the stored target tracking feature data is less than a preset matching degree, a plurality of to-be-tracked object data and historical tracking feature data including the target tracking object data within the monitoring range are acquired;
[0084] Step S202, extracting object feature data according to the feature type of historical tracking feature data for each object data to be tracked;
[0085] The feature type of the tracking feature data may include any one or more of: gender, age, face shape, facial features, and clothing. Gender type may be divided into male and female. Age may be divided into different age groups, such as 0-18, 19-30, 30-50, 50-100, etc. The face shape may be the facial contour features extracted based on face recognition. For example, the face shape may be specifically divided into oval face, square face, round face, square face, etc. The facial features may specifically be the distribution of facial features, and the clothing features may be specifically divided from the clothing categories.
[0086] After obtaining the data of the object to be tracked and the historical tracking feature data, the feature type in the historical tracking feature data can be determined, and then the object feature data can be extracted from the data of the object to be tracked according to the feature type. For example, the AI server can determine the gender characteristics, age characteristics, face shape characteristics, facial features, clothing characteristics, etc. of the object to be tracked by analyzing the video image data uploaded by the target monitoring device frame by frame.
[0087] Step S203, matching the object feature data with the historical tracking feature data to generate a matching result;
[0088] After the AI server determines the object feature data, it can match the object feature data extracted in real time with the previous historical tracking feature data to obtain the matching results of each object data to be tracked.
[0089] Step S204: if the matching result is that the target object data to be tracked other than the target tracking object data and the historical tracking feature data other than the target tracking feature data are successfully matched, it is determined that the target tracking object data matches the target tracking feature data.
[0090] When tracking an object within the monitoring range, each tracked object has its corresponding tracking feature data. After the AI server completes the matching of the tracked object and the tracking feature data, if only the target tracking object data and the target tracking feature data are not successfully matched, it can be determined that the target tracking feature data is the tracking feature extracted from the target tracking object data during the previous tracking process and stored in the AI server.
[0091] In an embodiment of the present invention, when the degree of match between the target tracking object and the stored target tracking feature data is less than a preset degree of match, a computing power analysis is performed on multiple objects to be tracked within the monitoring range to accurately determine whether the target tracking object and the target tracking feature data match.
[0092] Reference Figure 3 , shows a flowchart of another object tracking method provided by an embodiment of the present invention, which may specifically include the following steps:
[0093] (1) Real-time monitoring by surveillance cameras:
[0094] In practical applications, surveillance cameras can collect video data within the monitoring range.
[0095] (2) Data upload to the computing network
[0096] The collected video data is uploaded to the computing network (i.e., the AI server in the embodiment of the present invention).
[0097] (3) Targeting a specific person
[0098] In the computing network, the target tracking object and the object feature data of the target tracking object are extracted based on the collected video data, and then the object feature data can be matched with the target tracking feature data of the unbound object stored previously. If the matching degree between the two is less than the preset matching degree, the target tracking object is locked.
[0099] (4) Analysis of the computing network
[0100] A plurality of objects to be tracked in the video data and pre-stored historical tracking feature data are obtained, and the plurality of objects to be tracked are matched one by one with the historical tracking feature data.
[0101] When the matching result is the preset matching result that the target object data to be tracked except the target tracking object data and the historical tracking feature data except the target tracking feature data are successfully matched, it can be determined that the target tracking object data and the target tracking feature data match.
[0102] Among them, the above-mentioned scheme in the embodiment of the present invention can be a technical scheme implemented in the visual network, so that a certain person within the coverage area can be monitored in real time through the visual network monitoring equipment and the visual network APP, making full use of the real-time and structural security of the visual network and the fast computing speed of the computing power network.
[0103] Based on the above technical solution and the computing network operation, when a person avoids monitoring equipment and appears in the monitoring coverage after a while after changing clothes or putting on makeup, the computing network operation can calculate the user ID that disappeared during this period of time and the user ID that appeared, and perform fuzzy matching. Even if the person changes his clothes, the user can still be analyzed, thereby avoiding the loss of the tracking target and strengthening security.
[0104] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.
[0105] Reference Figure 4 , shows a schematic diagram of the structure of an object tracking device provided by an embodiment of the present invention, which may specifically include the following modules:
[0106] The tracking data acquisition module 401 is used to acquire a plurality of to-be-tracked object data and historical tracking feature data within the monitoring range of the target monitoring device, when it is detected that the matching degree between the target tracking object data and the stored target tracking feature data is less than a preset matching degree;
[0107] A tracking data matching module 402, configured to match the plurality of to-be-tracked object data with the historical tracking feature data to generate a matching result;
[0108] The matching success module 403 is used to determine whether the target tracking object data matches the target tracking feature data if the matching result is a preset matching result.
[0109] In an embodiment of the present invention, when the preset matching result is that the target object data to be tracked other than the target tracking object data and the historical tracking feature data other than the target tracking feature data are all matched successfully.
[0110] In an embodiment of the present invention, the tracking data matching module 402 may include:
[0111] An object feature data extraction submodule, configured to extract object feature data for each object data to be tracked according to the feature type of the historical tracking feature data;
[0112] The feature data matching submodule is used to match the object feature data with the historical tracking feature data.
[0113] In one embodiment of the present invention, the feature data matching submodule may include:
[0114] A matching order determining unit, used to determine the matching order of the multiple pieces of object feature data when there are multiple pieces of object feature data;
[0115] The matching subunit is used to match the object feature data with the historical tracking feature data according to the matching order.
[0116] In one embodiment of the present invention, the device may further include:
[0117] an object identification determination module, configured to determine the object identification corresponding to the target tracking feature data when the target tracking object data matches the target tracking feature data;
[0118] The tracking object marking module is used to mark the target tracking object data using the object identifier in the monitoring video data collected by the preset monitoring device.
[0119] In one embodiment of the present invention, the device may further include:
[0120] The marking removal module is used to delete the object identification in the monitoring video data when it is detected that the target tracking object moves out of the monitoring range of the preset monitoring device.
[0121] In one embodiment of the present invention, the device further comprises:
[0122] The second matching success module is used to determine that the target tracking object data matches the target tracking feature data when it is detected that the matching degree between the target tracking object data within the monitoring range of the preset monitoring device and the stored target tracking feature data is greater than or equal to the preset matching degree.
[0123] In an embodiment of the present invention, when it is detected that the matching degree between the target tracking object data and the stored target tracking feature data within the monitoring range of the target monitoring device is less than a preset matching degree, a plurality of object data to be tracked and historical tracking feature data including the target tracking object data within the monitoring range are obtained; the plurality of object data to be tracked are matched with the historical tracking feature data to generate a matching result; if the matching result is a preset matching result, it is determined that the target tracking object data matches the target tracking feature data, thereby achieving accurate tracking of the target tracking object by global matching when a single matching fails, thereby avoiding loss of the tracking target.
[0124] An embodiment of the present invention further provides an electronic device, which may include a processor, a memory, and a computer program stored in the memory and capable of running on the processor, and the computer program implements the above object tracking method when executed by the processor.
[0125] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the object tracking method as described above is implemented.
[0126] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0127] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0128] Those skilled in the art will appreciate that the embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the embodiments of the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0129] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0130] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0131] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0132] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.
[0133] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.
[0134] The object tracking method and device, electronic device, and storage medium provided above are introduced in detail. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for general technical personnel in this field, according to the idea of the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.
Claims
1. An object tracking method, characterized in that: The method comprises: When it is detected that the matching degree between the target tracking object data within the monitoring range of the target monitoring device and the stored target tracking feature data is less than a preset matching degree, acquiring a plurality of to-be-tracked object data and historical tracking feature data within the monitoring range including the target tracking object data; Matching the plurality of to-be-tracked object data with the historical tracking feature data to generate a matching result; If the matching result is a preset matching result, it is determined that the target tracking object data matches the target tracking feature data.
2. The method according to claim 1, characterized in that When the preset matching result is that the target object data to be tracked except the target tracking object data and the historical tracking feature data except the target tracking feature data are successfully matched.
3. The method according to claim 1, characterized in that The matching of the plurality of to-be-tracked object data with the historical tracking feature data comprises: Extracting object feature data for each object data to be tracked according to the feature type of the historical tracking feature data; The object feature data is matched with the historical tracking feature data.
4. The method according to claim 3, characterized in that The matching of the object feature data with the historical tracking feature data includes: When there are multiple pieces of object feature data, determining a matching order of the multiple pieces of object feature data; The object feature data is matched with the historical tracking feature data according to the matching order.
5. The method according to claim 1, characterized in that Also includes: When the target tracking object data matches the target tracking feature data, determining an object identifier corresponding to the target tracking feature data; The target tracking object data is marked with the object identifier in the monitoring video data collected by the preset monitoring device.
6. The method according to claim 5, characterized in that Also includes: When it is detected that the target tracking object moves out of the monitoring range of the preset monitoring device, the object identifier is deleted from the monitoring video data.
7. The method according to any one of claims 1 to 6, characterized in that Also includes: When it is detected that the matching degree between the target tracking object data within the monitoring range of the preset monitoring device and the stored target tracking feature data is greater than or equal to the preset matching degree, it is determined that the target tracking object data matches the target tracking feature data.
8. An object tracking device, characterized in that: The device comprises: A tracking data acquisition module, configured to acquire a plurality of to-be-tracked object data and historical tracking feature data within the monitoring range of the target monitoring device, when it is detected that the matching degree between the target tracking object data and the stored target tracking feature data is less than a preset matching degree; A tracking data matching module, used for matching the plurality of to-be-tracked object data with the historical tracking feature data to generate a matching result; A matching success module is used to determine that the target tracking object data matches the target tracking feature data if the matching result is a preset matching result.
9. An electronic device, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and capable of running on the processor, wherein when the computer program is executed by the processor, the object tracking method according to any one of claims 1 to 7 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the object tracking method according to any one of claims 1 to 7 is implemented.