Target tracking method, device, equipment, medium and product

Abstract

The invention provides a target tracking method and device, equipment, a medium and a product, and relates to the field of image processing, and the method comprises the steps: obtaining a to-be-processed image, carrying out the target detection of the to-be-processed image, and obtaining at least one candidate target, the to-be-processed image being a scene image, and the scene image being an image obtained through the imaging of a tracking scene; respectively extracting target features of each candidate target in the to-be-processed image, and determining to-be-matched features corresponding to the tracking target based on the target features of the tracking target in a scene image before the to-be-processed image, the target features of the target in the image comprise features of the target after the difference between the brightness of the target in the image and a preset brightness value is reduced; and determining a tracking target in the candidate targets based on the target features of each candidate target in the to-be-processed image and the to-be-matched features corresponding to the tracking target. According to the method, in the feature extraction process, the influence of brightness on feature extraction is reduced, and the success rate of target tracking in a scene with sharp light change is improved.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to a target tracking method, device, equipment, medium and product. Background Art

[0002] Target tracking technology is an important research direction in the field of computer vision and pattern recognition. Its main task is to continuously track and locate one or more target objects in a video sequence. Target tracking technology has a wide range of applications in video surveillance, autonomous driving, human-computer interaction, virtual reality and other fields. Target tracking technology requires extracting the feature information of the target and tracking based on the feature information. However, in actual application scenarios, the ambient brightness often changes dramatically. At this time, the color and texture of the target in the image change dramatically, which will lead to tracking failure. Summary of the invention

[0003] The present invention provides a target tracking method, device, equipment, medium and product, which are used to solve the defect of the prior art that drastic changes in ambient brightness lead to target tracking failure, and improve the target tracking success rate.

[0004] The present invention provides a target tracking method, comprising: Acquire an image to be processed, perform target detection on the image to be processed, and obtain at least one candidate target, wherein the image to be processed is a scene image, and the scene image is an image obtained by imaging a tracking scene; Extracting target features of each candidate target in the image to be processed respectively, determining the features to be matched corresponding to the tracked target based on the target features in the scene image before the tracked target in the image to be processed, wherein the target features of the target in the image include the features of the target after reducing the difference between the brightness of the target in the image and a preset brightness value; The tracking target is determined from the candidate targets based on the target features of each candidate target in the image to be processed and the features to be matched corresponding to the tracking target.

[0005] According to a target tracking method provided by the present invention, the target feature includes a first feature; and the step of respectively extracting the target features of each candidate target in the image to be processed includes: Performing background segmentation on the image to be processed based on the candidate target, removing the background portion of the candidate target in the image to be processed, and obtaining a segmented area image; Adjusting the brightness of the segmented area image based on the preset brightness value to obtain an adjusted image; The adjusted image is input into a trained feature extraction model to obtain the first feature of the candidate target in the image to be processed output by the feature extraction model.

[0006] According to a target tracking method provided by the present invention, the brightness of the segmented region image is adjusted based on the preset brightness value to obtain an adjusted image, including: Obtaining the brightness mean of the segmented area image; Determining an adjustment coefficient based on the preset brightness value and the brightness average value; The pixel values ​​of the segmented region image are weighted based on the adjustment coefficient to obtain the adjusted image.

[0007] According to a target tracking method provided by the present invention, the target feature further includes a second feature, and the step of respectively extracting the target features of each candidate target in the image to be processed includes: Cropping the image to be processed based on the candidate target to obtain an image of the region to be processed, wherein the image of the region to be processed includes the candidate target; The image of the area to be processed is input into a trained feature extraction model to obtain the second feature of the candidate target in the image to be processed output by the feature extraction model.

[0008] According to a target tracking method provided by the present invention, the feature to be matched includes a first feature to be matched and a second feature to be matched, the first feature to be matched is determined based on the first feature of the tracking target in the scene image before the image to be processed, and the second feature to be matched is determined based on the second feature of the tracking target in the scene image before the image to be processed; The determining the tracking target from the candidate targets based on the target features of each candidate target in the image to be processed and the features to be matched corresponding to the tracking target includes: Matching the second to-be-matched feature corresponding to the tracking target with the second feature corresponding to each of the candidate targets respectively; When the matching result meets a preset condition, obtaining the candidate target with the highest matching degree as the tracking target, wherein the preset condition is that the matching degree between the second feature corresponding to the candidate target and the second feature to be matched corresponding to the tracking target is higher than a preset matching degree threshold; When the matching result does not meet the preset condition, the first to-be-matched feature corresponding to the tracking target is matched with the first feature corresponding to each of the candidate targets respectively to determine the tracking target.

[0009] According to a target tracking method provided by the present invention, determining the to-be-matched features corresponding to the tracked target based on the target features in the scene image before the image to be processed includes: A weighted average process is performed on the target features of the tracked target in N images of the scene before the image to be processed to obtain the features to be matched corresponding to the tracked target, where N is a positive integer greater than 1.

[0010] The present invention also provides a target tracking device, comprising: An image acquisition module is used to acquire an image to be processed, perform target detection on the image to be processed, and obtain at least one candidate target, wherein the image to be processed is a scene image, and the scene image is an image obtained by imaging the tracking scene; A feature extraction module is used to extract target features of each candidate target in the image to be processed, and determine the features to be matched corresponding to the tracked target based on the target features in the scene image before the tracked target in the image to be processed, wherein the target features of the target in the image include the features of the target after reducing the difference between the brightness of the target in the image and a preset brightness value; A feature matching module is used to determine the tracking target among the candidate targets based on the target features of each candidate target in the image to be processed and the features to be matched corresponding to the tracking target.

[0011] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, any of the target tracking methods described above is implemented.

[0012] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the target tracking method described in any one of the above is implemented.

[0013] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements any of the target tracking methods described above.

[0014] The target tracking method, device, equipment, medium and product provided by the present invention obtain target features by reducing the difference between the brightness of the candidate target in the image to be processed and the preset brightness value when extracting features of the target in the image to be processed, obtain the to-be-matched features of the tracking target by the target features of the tracking target in the scene image before the image to be processed, determine the tracking target in each candidate target based on the target features of the candidate target and the to-be-matched features of the tracking target, and track the tracking target. In the process of feature extraction, the present invention reduces the influence of brightness on feature extraction, thereby improving the success rate of target tracking in scenes with rapid changes in light. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0016] Figure 1 It is a flow chart of the target tracking method provided by the present invention.

[0017] Figure 2 It is a logic block diagram of the target tracking method provided by the present invention.

[0018] Figure 3 It is a structural schematic diagram of the target tracking device provided by the present invention.

[0019] Figure 4 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Combine the following Figure 1-Figure 2 The target tracking method provided by the present invention is described. Figure 1 As shown, the target tracking method includes the steps of: S110, acquiring an image to be processed, performing target detection on the image to be processed, and obtaining at least one candidate target, wherein the image to be processed is a scene image, and the scene image is an image obtained by imaging the tracking scene; S120, respectively extracting target features of each candidate target in the image to be processed, and determining features to be matched corresponding to the tracking target based on target features in the scene image before the image to be processed, wherein the target features of the target in the image include features of the target after reducing the difference between the brightness of the target in the image and a preset brightness value; S130 , determining a tracking target from among the candidate targets based on target features of each candidate target in the image to be processed and features to be matched corresponding to the tracking target.

[0022] The method provided by the present invention obtains target features by reducing the difference between the brightness of the candidate target in the image to be processed and the preset brightness value when extracting features of the target in the image to be processed, obtains the to-be-matched features of the tracking target by the target features of the tracking target in the scene image before the image to be processed, determines the tracking target among the candidate targets based on the target features of the candidate targets and the to-be-matched features of the tracking target, and tracks the tracking target. In the process of feature extraction, the present invention reduces the influence of brightness on feature extraction, thereby improving the success rate of target tracking in scenes with rapid changes in light.

[0023] The image to be processed may be a frame of an image in a video obtained by shooting the tracking scene. By processing the image frame in the video stream as the image to be processed, determining the tracking target and tracking it, continuous and smooth tracking of the tracking target can be achieved.

[0024] In a possible implementation, an RGB-D camera (RGB-depth camera) can be used to image the tracking scene to obtain an RGB image and a depth map. For example, an RGB-D camera is set on a tracking robot to shoot the tracking scene to obtain an RGB image and a depth map. The RGB image is processed as a to-be-processed image, and the depth map can provide information such as the distance between the object in the image and the camera, thereby providing position information for target tracking. Therefore, an RGB image and a depth map can be obtained by an RGB camera and a depth camera, respectively, and the RGB image and the depth map are aligned. The aligned RGB image and depth map can be published through a ROS (Robot Operating System) node, and the RGB image and the depth map are subscribed from the node. The RGB image is used as a to-be-processed image for feature extraction, the tracking target is determined, and the tracking target is tracked based on the depth map.

[0025] After obtaining the image to be processed, target detection is first performed on the image to be processed to obtain at least one candidate target. Target detection on the image to be processed can be implemented based on an existing target detection model, such as the YOLOv8 model. Figure 2As shown, it is determined whether there is a target of the target type to be tracked according to the detection result. For example, if the tracking target is a human body, it is determined whether there is a human body in the image to be processed. If the tracking target is an animal, it is determined whether there is an animal in the image to be processed. The following will be specifically described with the tracking target being a human body. For other types of tracking targets, the same process can be used for processing.

[0026] like Figure 2 As shown, if there is no human target in the image to be processed, it is determined whether the set end process time limit is exceeded, or the stop condition is met (for example, the user manually stops, or the upper-level application sends a stop command, etc.). If the end condition is met or the set end process time limit is exceeded, the information that there is no human target is returned to the upper-level caller and the following function process is ended. If the end condition is not met, a new frame of the image to be processed is reacquired.

[0027] If there are human targets in the image to be processed, these human targets are used as candidate targets to check whether the tracking target in this tracking process has been determined and stored. The tracking target is a specific target to be tracked. In the method provided by the present invention, the basis for tracking the tracking target is the target feature of the tracking target. If the human target to be tracked this time has not been determined and stored, a candidate target can be selected as the tracking target, for example, the candidate target closest to the center in the image to be processed is used as the tracking target, and its corresponding target features are extracted as the features to be matched and stored. When the tracking target is tracked later, the target features extracted this time are used as the basis for tracking.

[0028] In practical applications, there may be a situation where the light of the scene changes dramatically, such as from indoors to outdoors, from shade to sunlight, etc. When the scene light changes dramatically, the brightness of the tracking target in adjacent images to be processed will change dramatically. At this time, even for the same target, the features obtained by feature extraction in different images to be processed may change greatly, resulting in a failure to match and thus tracking failure. The method provided by the present invention, when extracting features of a candidate target based on an image including the candidate target, the extracted target features include the features of the candidate target in the image after reducing the difference between the brightness of the candidate target in the image and the preset brightness, that is, the target features of the candidate target extracted based on the image to be processed include the features of the candidate target in the image to be processed after reducing the difference between the brightness of the candidate target in the image to be processed and the preset brightness.

[0029] Specifically, the target feature includes a first feature, and the target features of each candidate target in the image to be processed are extracted respectively, including: Perform background segmentation on the image to be processed based on the candidate target, remove the background part of the candidate target in the image to be processed, and obtain a segmented area image; Adjusting the brightness of the segmented area image based on a preset brightness value to obtain an adjusted image; The adjusted image is input into the trained feature extraction model to obtain the first feature corresponding to the candidate target output by the feature extraction model.

[0030] The feature extraction model can be an existing feature extraction model, such as a ReID model. The ReID model is a model based on the ReID (Re-Identification) technology. The Re-Identification technology identifies and tracks individual identities through given images or video sequences. The main task is to extract the ReID features of human images from images or video sequences captured from multiple perspectives or multiple moments through a deep neural network model, and compare and match the features to identify the same person. The method provided by the present invention uses a feature extraction model to extract the target features of candidate targets for matching, thereby realizing the identification of the tracked target.

[0031] In order to reduce the impact of drastic changes in light on feature extraction, in the method provided by the present invention, the difference between the brightness value of the candidate target in the image to be processed and the preset brightness value is reduced before inputting into the feature extraction model to extract features. This can reduce the impact of brightness on the features used for matching, thereby reducing the impact of drastic changes in light on target tracking and improving the success rate of target tracking. First, the image to be processed is subjected to background segmentation based on the candidate target, and the background part in the image to be processed is removed to obtain a segmented area image to avoid interference of the background on the brightness calculation. Background segmentation can be implemented using an existing segmentation model such as the SAM segmentation model (Segment Anything Model). After background segmentation of the image to be processed, only the part of the candidate target is retained to obtain a segmented area image. The image is brightness adjusted and then input into the feature extraction model for feature extraction to obtain the first feature.

[0032] Specifically, adjusting the brightness of the segmented region image based on a preset brightness value to obtain an adjusted image includes: Get the brightness mean of the segmented area image; Determine an adjustment coefficient based on a preset brightness value and a brightness average value; The pixel values ​​of the segmented region image are weighted based on the adjustment coefficient to obtain an adjusted image.

[0033] The mean brightness of the segmented area image can be calculated by the following formula: ; in, is the mean brightness, is the width and height of the segmented area image, and R, G, and B are the three-channel pixel values ​​of the pixel points.

[0034] According to the image properties of RGB images, the brightness mean The value range should be .

[0035] The adjustment coefficient is the ratio of the preset brightness value to the average brightness value, which can be obtained by the formula Calculated, where is the preset brightness value.

[0036] The preset brightness value is a preset brightness value that is beneficial to the retention of information used for target recognition, such as 180. That is, the image under the preset brightness value will not be too dark or too bright, resulting in the image losing color, target details, and texture information. Of course, it is understandable that different preset brightness values ​​can be set according to different target recognition scenes and target categories, and the setting basis can be manual experience or experimental data.

[0037] In getting the adjustment coefficient After that, the pixel values ​​of the image in the segmented area are weighted based on the adjustment coefficient to obtain the adjusted image. The process can be expressed as: ,in, represents the pixel value matrix of the adjusted image, is the pixel value matrix of the segmented area image.

[0038] It can be seen from the above description that the process of extracting the first feature needs to go through the process of background segmentation, brightness adjustment, and feature extraction, which consumes certain resources and has poor real-time performance. In the method provided by the present invention, in order to further ensure the success rate of target tracking, the target features of the candidate targets also include the second feature, and the target features of each candidate target in the image to be processed are extracted respectively, and also include: The image to be processed is cropped based on the candidate target to obtain an image of the region to be processed, wherein the image of the region to be processed includes the candidate target; The image of the area to be processed is input into the trained feature extraction model to obtain the second feature of the candidate target in the image to be processed output by the feature extraction model.

[0039] When extracting the second feature, the brightness is not adjusted, and the feature extraction is directly performed on the image of the area to be processed including the candidate target to obtain the second feature. Since the processing steps of the second feature are relatively simple, it can have good real-time performance. Combining the second feature with the first feature can ensure the success rate of target tracking.

[0040] After obtaining the target features of each candidate target in the image to be processed, the target features of each candidate target are matched with the features to be matched of the tracking target respectively, and the tracking target is determined among the candidate targets.

[0041] The features to be matched of the tracking target are obtained based on the scene image before the image to be processed. The scene image before the image to be processed refers to the scene image whose acquisition time is earlier than that of the image to be processed. When the image to be processed is the first frame in the video stream, that is, there is no scene image before the image to be processed, as described above, the most central target in the image to be processed can be specified or automatically used as the tracking target, and the target features can be extracted as the features to be matched. In the case where there is a scene image before the image to be processed, in one possible implementation, the target features of the tracking target in the scene image of the previous frame of the image to be processed can be used as the features to be matched of the tracking target, but the robustness of this method is low. In order to improve the robustness of the matching and further improve the tracking success rate, in another possible implementation, the features to be matched corresponding to the tracking target are determined based on the target features of the tracking target in the scene image before the image to be processed, including: Perform weighted averaging on the target features of the tracking target in N scene images before the image to be processed to obtain the features to be matched corresponding to the tracking target, where N is a positive integer greater than 1.

[0042] Through weighted average processing, the target features of the tracked target in N scene images before the processed image can be fused to obtain more robust and accurate features of the tracked target, thereby improving the tracking success rate.

[0043] The features to be matched of the tracking target include a first feature to be matched and a second feature to be matched, the first feature to be matched is determined based on a first feature of the tracking target in a scene image before the image to be processed, the second feature to be matched is determined based on a second feature of the tracking target in a scene image before the image to be processed, and the tracking target is determined from the candidate targets based on the target features of each candidate target in the image to be processed and the features to be matched corresponding to the tracking target, including: Matching the second to-be-matched feature corresponding to the tracking target with the second feature corresponding to each candidate target respectively; When the matching result meets the preset condition, the candidate target with the highest matching degree is obtained as the tracking target, and the preset condition is that the matching degree between the second feature corresponding to the candidate target and the second feature to be matched corresponding to the tracking target is higher than the preset matching degree threshold; When the matching result does not meet the preset condition, the first to-be-matched feature corresponding to the tracking target is matched with the first features corresponding to each candidate target that meets the preset condition to determine the tracking target.

[0044] First, the second feature to be matched is matched with the second feature corresponding to each candidate target. In the absence of a drastic change in brightness, the tracking target can be directly determined from the candidate targets by matching the second feature to be matched with the second feature. Feature matching can be determined by calculating vector similarity. Specifically, the second feature to be matched is 1 The vector of M, the second features of K candidate targets form K M vector, calculate the similarity of two vectors, and you can get the similarity vector S, whose dimension is 1 K, each element in the similarity vector S represents the similarity value between the tracking target and the kth candidate target. When a candidate target with a value greater than the preset matching threshold (i.e., the similarity value is greater than the preset similarity threshold) appears, it means that the current scene light has not changed dramatically, and the candidate target with the highest matching degree is obtained as the tracking target. When there is no candidate target with a value greater than the preset matching threshold, it means that the current scene light has changed dramatically, and the first to-be-matched feature corresponding to the tracking target is further matched with the first feature corresponding to each candidate target. When a candidate target with a value greater than the preset matching threshold (i.e., the similarity value is greater than the preset similarity threshold) appears, the candidate target with the highest matching degree is used as the tracking target. If there is still no candidate target with a matching degree greater than the preset matching threshold after the second matching, it is determined that the tracking target is lost.

[0045] After the tracking target is determined among the candidate targets, the position of the tracking target in the image to be processed can be published. Based on the position, the position of the tracking target in the depth image aligned with the image to be processed can be obtained. Based on the depth value corresponding to the position, the actual distance from the tracking target to the camera can be converted. Therefore, the coordinates of the tracking target in the tracking robot coordinate system can be calculated according to the camera calibration parameters, and the control signal is output according to the predetermined tracking strategy. The motion interface of the tracking robot body is called to control the movement of the robot, thereby tracking the tracking target.

[0046] The target tracking device provided by the present invention is described below. The target tracking device described below and the target tracking method described above can be referred to in correspondence with each other. Figure 3 As shown, the target tracking device provided by the present invention comprises: An image acquisition module 310 is used to acquire an image to be processed, perform target detection on the image to be processed, and obtain at least one candidate target. The image to be processed is a scene image, and the scene image is an image obtained by imaging the tracking scene. The feature extraction module 320 is used to extract the target features of each candidate target in the image to be processed, and determine the features to be matched corresponding to the tracking target based on the target features in the scene image before the image to be processed, wherein the target features of the target in the image include the features of the target after reducing the difference between the brightness of the target in the image and the preset brightness value; The feature matching module 330 is used to determine the tracking target from among the candidate targets based on the target features of each candidate target in the image to be processed and the features to be matched corresponding to the tracking target.

[0047] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor 410, a communication interface 420, a memory 430 and a communication bus 440, wherein the processor 410, the communication interface 420 and the memory 430 communicate with each other through the communication bus 440. The processor 410 may call the logic instructions in the memory 430 to execute the target tracking method, which includes: acquiring an image to be processed, performing target detection on the image to be processed, and obtaining at least one candidate target, wherein the image to be processed is a scene image, and the scene image is an image obtained by imaging the tracking scene; extracting target features of each candidate target in the image to be processed respectively, determining the features to be matched corresponding to the tracking target based on the target features in the scene image before the image to be processed of the tracking target, and the target features of the target in the image include the features of the target after reducing the difference between the brightness of the target in the image and the preset brightness value; determining the tracking target among the candidate targets based on the target features of each candidate target in the image to be processed and the features to be matched corresponding to the tracking target.

[0048] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0049] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the target tracking method provided by the above methods, which includes: acquiring an image to be processed, performing target detection on the image to be processed, and obtaining at least one candidate target, wherein the image to be processed is a scene image, and the scene image is an image obtained by imaging the tracking scene; respectively extracting target features of each candidate target in the image to be processed, and determining features to be matched corresponding to the tracking target based on target features in the scene image before the image to be processed of the tracking target, wherein the target features of the target in the image include features of the target after reducing the difference between the brightness of the target in the image and a preset brightness value; determining the tracking target among the candidate targets based on the target features of each candidate target in the image to be processed and the features to be matched corresponding to the tracking target.

[0050] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the target tracking method provided by the above-mentioned methods, the method comprising: acquiring an image to be processed, performing target detection on the image to be processed, and obtaining at least one candidate target, wherein the image to be processed is a scene image, and the scene image is an image obtained by imaging the tracking scene; extracting target features of each candidate target in the image to be processed respectively, and determining features to be matched corresponding to the tracking target based on target features in the scene image before the image to be processed of the tracking target, the target features of the target in the image comprising features of the target after reducing the difference between the brightness of the target in the image and a preset brightness value; determining the tracking target among the candidate targets based on the target features of each candidate target in the image to be processed and the features to be matched corresponding to the tracking target.

[0051] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0052] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0053] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A target tracking method, characterized in that: include: Acquire an image to be processed, perform target detection on the image to be processed, and obtain at least one candidate target, wherein the image to be processed is a scene image, and the scene image is an image obtained by imaging a tracking scene; Extracting target features of each candidate target in the image to be processed respectively, determining the features to be matched corresponding to the tracked target based on the target features in the scene image before the tracked target in the image to be processed, wherein the target features of the target in the image include the features of the target after reducing the difference between the brightness of the target in the image and a preset brightness value; The tracking target is determined from the candidate targets based on the target features of each candidate target in the image to be processed and the features to be matched corresponding to the tracking target.

2. The target tracking method according to claim 1, characterized in that: The target feature includes a first feature; The step of respectively extracting target features of each candidate target in the image to be processed includes: Performing background segmentation on the image to be processed based on the candidate target, removing the background portion of the candidate target in the image to be processed, and obtaining a segmented area image; Adjusting the brightness of the segmented area image based on the preset brightness value to obtain an adjusted image; The adjusted image is input into a trained feature extraction model to obtain the first feature of the candidate target in the image to be processed output by the feature extraction model.

3. The target tracking method according to claim 2, characterized in that: The step of adjusting the brightness of the segmented region image based on the preset brightness value to obtain an adjusted image includes: Obtaining the brightness mean of the segmented area image; Determining an adjustment coefficient based on the preset brightness value and the brightness average value; The pixel values ​​of the segmented region image are weighted based on the adjustment coefficient to obtain the adjusted image.

4. The target tracking method according to claim 2, characterized in that: The target feature also includes a second feature, and the step of respectively extracting the target features of each candidate target in the image to be processed includes: Cropping the image to be processed based on the candidate target to obtain an image of the region to be processed, wherein the image of the region to be processed includes the candidate target; The image of the area to be processed is input into a trained feature extraction model to obtain the second feature of the candidate target in the image to be processed output by the feature extraction model.

5. The target tracking method according to claim 4, characterized in that: The features to be matched include a first feature to be matched and a second feature to be matched, the first feature to be matched is determined based on the first feature of the tracking target in the scene image before the image to be processed, and the second feature to be matched is determined based on the second feature of the tracking target in the scene image before the image to be processed; The determining the tracking target from the candidate targets based on the target features of each candidate target in the image to be processed and the features to be matched corresponding to the tracking target includes: Matching the second to-be-matched feature corresponding to the tracking target with the second feature corresponding to each of the candidate targets respectively; When the matching result meets a preset condition, obtaining the candidate target with the highest matching degree as the tracking target, wherein the preset condition is that the matching degree between the second feature corresponding to the candidate target and the second feature to be matched corresponding to the tracking target is higher than a preset matching degree threshold; When the matching result does not meet the preset condition, the first to-be-matched feature corresponding to the tracking target is matched with the first feature corresponding to each of the candidate targets respectively to determine the tracking target.

6. The target tracking method according to claim 1, characterized in that: The determining the to-be-matched feature corresponding to the tracking target based on the target feature in the scene image before the image to be processed includes: A weighted average process is performed on the target features of the tracked target in N images of the scene before the image to be processed to obtain the features to be matched corresponding to the tracked target, where N is a positive integer greater than 1.

7. A target tracking device, characterized in that: include: An image acquisition module is used to acquire an image to be processed, perform target detection on the image to be processed, and obtain at least one candidate target, wherein the image to be processed is a scene image, and the scene image is an image obtained by imaging the tracking scene; A feature extraction module is used to extract target features of each candidate target in the image to be processed, and determine the features to be matched corresponding to the tracked target based on the target features in the scene image before the tracked target in the image to be processed, wherein the target features of the target in the image include the features of the target after reducing the difference between the brightness of the target in the image and a preset brightness value; A feature matching module is used to determine the tracking target among the candidate targets based on the target features of each candidate target in the image to be processed and the features to be matched corresponding to the tracking target.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the target tracking method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the target tracking method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the target tracking method according to any one of claims 1 to 6 is implemented.

Images