Multi-target tracking method based on target confidence hierarchical association strategy

Abstract

The invention discloses a multi-target tracking method based on a target confidence hierarchical association strategy, and the method comprises the steps: inputting a video V, and segmenting the video V into independent frame sequences fk; obtaining a set D of all pedestrian targets in the frame fk; predicting the position of the existing track in the current frame fk by using a shielding target motion state prediction method based on the change trend of the detection frame; according to the predicted trajectory and the confidence hierarchical association strategy of the target, associating the predicted trajectory with the detection target; storing a track set Tmatched which is successfully matched, and for each track tk which is successfully matched in the current frame, updating to obtain a more accurate motion state Xk and a more accurate change speed Pk by utilizing an observed value of the matched target in the current frame; and processing all frame sequences in the video V, and outputting multi-target identification tracking. The method has the advantage of being capable of improving the accuracy and robustness of target tracking in a crowded complex dynamic scene.

Description

Technical Field

[0001] The invention relates to the technical field of image processing, and in particular to a multi-target tracking method based on a target confidence hierarchical association strategy. Background Art

[0002] The use of cameras in our daily lives is increasing day by day, building a ubiquitous digital eye network. These cameras are widely used in monitoring systems, unmanned driving systems and robot vision systems. However, one of the core aspects of the camera data support system for autonomous intelligent decision-making is to quickly and accurately identify and track potential targets in the scene, especially for systems with high real-time performance. In addition, the intelligence of intelligent robots is inseparable from machine vision technology. In complex and dynamic scenes with multiple people, the multi-target tracking technology (MOT) that accurately identifies and tracks specific targets is the core of ensuring that robots can achieve accurate behavior perception and monitoring, provide personalized human-like services and other autonomous decisions.

[0003] The multi-target tracking task is usually decomposed into two subtasks: target detection and data association. Thanks to the rapid development of current target detection technology, a good tracking speed has been achieved with the help of powerful detectors, and clues are combined in the data association task to assist in the association of targets and trajectories. In the prior art, the association ability of the tracking algorithm is improved by utilizing "weak clues" such as detection box confidence and height changes. In the data association stage, cascade matching is a commonly used method in MOT research. DeepSORT prioritizes matching younger trajectories with detection objects, while ByteTrack prioritizes matching high-confidence detection targets with existing trajectories. However, there are still the following problems: the scale changes of the target itself during the tracking process and the frequent overlap between targets lead to tracking loss and identity ID mismatching, resulting in poor accuracy and robustness of tracking targets in complex dynamic scenes. Summary of the invention

[0004] The purpose of the present invention is to overcome the above disadvantages and propose a multi-target tracking method based on a target confidence hierarchical association strategy that can improve the accuracy and robustness of tracking targets in crowded, complex and dynamic scenes.

[0005] The present invention provides a multi-target tracking method based on a target confidence hierarchical association strategy, which comprises the following steps:

[0006] Step 1: Input video V and split it into separate frame sequences, each frame is denoted as f k , where k represents the frame number;

[0007] Step 2: For the current frame f k , using the target detector to k Processing is performed to obtain frame f kThe set D of all pedestrian targets in k , set D k Each target d k The detection confidence including the target detection box is recorded;

[0008] Each target d k , and the detection confidence and the preset detection confidence threshold τ det Compare; if the target d k The detection confidence is greater than or equal to the threshold τ det , then the target is divided into the high confidence target set D high ; If the target d k The detection confidence is less than the threshold τ det , then the target is divided into the low confidence target set D low ;

[0009] Step 3: Motion state prediction: Use the motion state prediction method of the occluded target based on the detection frame change trend to predict the existing trajectory in the current frame f k The position in the k-1th frame is recorded as T. k-1 , the specific steps include:

[0010] Step 3.1: For the set T k-1 Each existing trajectory t k-1 , using the ten-tuple vector Model the motion state of the detection box corresponding to the target of the predicted trajectory, where x, y represent the center coordinates of the detection box corresponding to the target of the predicted trajectory in the image plane, w and s represent the width and area of ​​the detection box respectively, and c represents the detection confidence. They represent the speed of the corresponding variables respectively, and the ten-tuple vector is input into the Kalman filter to predict the motion state of the existing trajectory in the current frame;

[0011] Step 3.2: For each current frame, the predicted trajectory The prediction confidence and the preset trajectory confidence threshold τ tracklet Compare; if The prediction confidence is greater than or equal to the threshold τ tracklet , then divide this predicted trajectory into a high confidence trajectory set T high ;if The prediction confidence is less than the threshold τ tracklet , then the target is divided into a set of low-confidence trajectories T low ;

[0012] Step 4: Associating the predicted trajectory with the detected target: According to the confidence layered association strategy of the predicted trajectory and the target, the predicted trajectory is associated with the detected target. The specific steps are as follows:

[0013] Step 4.1: High confidence matching: Construct a high confidence prediction trajectory set T high And the high confidence detection target set D high The cost matrix C between stage1 , based on the intersection over union (IoU) distance between the detection box and the trajectory prediction box to calculate the cost; using the Hungarian algorithm based on C stage1 In T high and D high Match between them to determine the trajectory of the foreground target in the video frame; retain the unmatched trajectory as T remain , the detection target that was not successfully matched is D remain ;

[0014] Step 4.2: Low confidence matching: Construct a low confidence prediction trajectory set T low And the detection target D that was not successfully matched in the previous stage remain The cost matrix C between stage2 , the IoU distance and the confidence difference between the current frame and the previous frame are combined when calculating the cost to improve the matching accuracy; the unmatched trajectories are merged into T remain , the unmatched detection targets are merged into D remain ;

[0015] Step 4.3: Matching of remaining targets: Constructing the trajectory T that was not successfully matched in the first two stages remain And the low confidence detection target set D low The cost matrix C between stage3 , the cost is calculated based on the IoU distance between the detection box and the trajectory prediction box for matching, ensuring that all possible targets are considered to avoid omissions;

[0016] Step 5: Save the successfully matched trajectory set T matched , for each successfully matched trajectory t in the current frame k , using the observation value of the matched target in the current frame, update the more accurate motion state X k and the change speed P k ; The detected targets that are not successfully matched will be initialized as new trajectories and tracked in the next frame;

[0017] Step 6: Loop through steps 2 to 5 until all frame sequences in the video V are processed and perform multi-target recognition and tracking.

[0018] The above-mentioned multi-target tracking method based on target confidence hierarchical association strategy, wherein: in step 2, the target detector is the YOLOX algorithm.

[0019] The above multi-target tracking method based on target confidence hierarchical association strategy, wherein: in step 2, each target d k The center coordinates, width, height, and detection confidence of the target detection box are recorded.

[0020] The above-mentioned multi-target tracking method based on target confidence hierarchical association strategy, wherein: in step 2, the preset detection confidence threshold τ det is 0.6.

[0021] The above multi-target tracking method based on target confidence hierarchical association strategy, wherein: in step 3.1, the motion state of the detection frame is modeled as a ten-tuple vector input Kalman filter to predict the motion state of the existing trajectory in the current frame, let X = [x, y, w, s, c] T is the directly observed motion state; let Indicates the speed of change of the corresponding state; in the kth frame, the motion state of the previous frame is used to predict the motion state of the current frame. The calculation formula is:

[0022]

[0023] in, and X k-1 They represent the predicted state of the trajectory in the current k-th frame and the motion state observed in the k-1th frame respectively; F k It is the state transfer matrix of the kth frame under the assumption that the movement between detection frames is linear motion; and P k-1 They represent the state change speed of the trajectory in the kth frame and the k-1th frame respectively; Q k is the noise matrix of the system, and the calculation formula is:

[0024]

[0025] in, and They represent the predicted width and predicted area of ​​the detection box corresponding to the target in the k-1th frame, σ p Take 0.05, σ v Take 0.00625.

[0026] The above-mentioned multi-target tracking method based on the target confidence hierarchical association strategy, wherein: in step 3.2, the preset trajectory confidence threshold τ tracklet According to the comparative experimental results under different values, it is set to 0.8.

[0027] The above-mentioned multi-target tracking method based on the target confidence hierarchical association strategy, wherein: in step 4.2, the IoU distance and the confidence difference between the current frame and the previous frame are combined when calculating the cost, and the formula is:

[0028]

[0029] Among them, c k The target d detected by the target detector k The confidence value at the kth frame, is the trajectory sequence T of the Kalman filter up to the k-1th frame k-1 The historical confidence value is used to predict its confidence value at the kth frame.

[0030] The above-mentioned multi-target tracking method based on target confidence hierarchical association strategy, wherein: in step 5, the set of trajectories T that save the successful matching matched , for each successfully matched trajectory t in the current frame k , using the observation value of the matched target in the current frame, update the more accurate motion state X k and the change speed P k , the calculation formula is:

[0031]

[0032] Among them, K k is the Kalman gain, which is used to estimate the importance of the error; R k is the noise matrix of the detector; H k is the measurement matrix, and the predicted value of the motion state is Mapped to the detection space, combined with the observation value z k Calculating the error between the predicted value and the predicted value and using the current observed value to correct the predicted value is conducive to gradually improving the accuracy of target position estimation.

[0033] Compared with the prior art, the present invention has obvious beneficial effects. It can be seen from the above scheme that in order to solve the problems of tracking loss and identity ID mismatch caused by the scale change of the target itself and the frequent overlap between targets during the tracking process, the present invention models the size of the target detection frame from the width and area, incorporates the detection confidence of the target into the motion state that needs to be modeled, and realizes the matching between the predicted trajectory and the detected target based on the IoU distance and confidence difference in the data association stage. At the same time, on the basis of constructing a confidence hierarchical association strategy for the predicted trajectory and the target, the tracker of the present invention is constructed in accordance with the tracking-by-detection paradigm, and the entire tracking task is regarded as the association problem between the current frame detection target and the existing trajectory, and a multi-target tracking method (ScoreMOT) based on the predicted trajectory and target confidence hierarchical association strategy is proposed.

[0034] Among them, in order to improve the positioning ability of occluded targets by using width, area and confidence to model the motion state of the detection frame, and then provide confidence difference information between the predicted trajectory and the detected target for the trajectory association of the occluded target, the present invention proposes an occluded target motion state prediction method (MPOBV) based on the detection frame change trend. In addition, taking the trajectory as the matching subject, the trajectory and the target are grouped according to the confidence level, so that the overlapping targets are divided into two levels: foreground and background. The present invention further proposes a confidence hierarchical association strategy (SHAS) for predicted trajectories and targets, so as to achieve matching of predicted trajectories and detected targets at different levels in frequently overlapping scenes. The main advantages of the present invention are:

[0035] 1) A multi-target tracking method based on a hierarchical association strategy of predicted trajectories and target confidence (ScoreMOT) is proposed. This method only uses motion information to achieve stable tracking of multiple targets in irregularly moving and dense scenes.

[0036] 2) A method for predicting the motion state of occluded targets based on the change trend of detection frames is proposed. This method uses width, area and confidence to model the motion state of detection frames to improve the positioning ability of occluded targets, and then provides confidence difference information between the predicted trajectory and the detected target for trajectory association of occluded targets.

[0037] 3) A confidence hierarchical association strategy for predicted trajectories and targets is proposed. This method takes trajectories as the matching subject and groups trajectories and targets according to the confidence level, thereby dividing overlapping targets into two levels: foreground and background, and matching predicted trajectories and detected targets at different levels in frequently overlapping scenes.

[0038] In summary, the present invention has the characteristics of being able to improve the accuracy and robustness of tracking targets in crowded, complex and dynamic scenes.

[0039] The beneficial effects of the present invention are further illustrated below through specific implementation modes. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 It is a schematic diagram of the multi-target tracking process of the present invention. DETAILED DESCRIPTION

[0041] The specific implementation method, features and efficacy of a multi-target tracking method based on a target confidence hierarchical association strategy proposed in the present invention are described in detail below in conjunction with the accompanying drawings and preferred embodiments.

[0042] See also Figure 1 The present invention provides a multi-target tracking method based on a target confidence hierarchical association strategy, which comprises the following steps:

[0043] Step 1: Input video V and split it into separate frame sequences, each frame is denoted as f k , where k represents the frame number;

[0044] Step 2: For the current frame f k , using the target detector YOLOX to detect f k Processing is performed to obtain frame f k The set D of all pedestrian targets in k , set D k Each target d k The center coordinates, width and height of the target detection box and its detection confidence are recorded;

[0045] Each target d k , and the detection confidence and the preset detection confidence threshold τ det Compare; if the target d k The detection confidence is greater than or equal to the threshold τ det , then the target is divided into the high confidence target set D high ; If the target d k The detection confidence is less than the threshold τ det , then the target is divided into the low confidence target set D low ;

[0046] Step 3: Motion state prediction: Use the motion state prediction method of the occluded target based on the detection frame change trend to predict the existing trajectory in the current frame f k The position in the k-1th frame is recorded as T. k-1 , the specific steps include:

[0047] Step 3.1: For the set T k-1 Each existing trajectory t k-1 , using the ten-tuple vector Model the motion state of the detection box corresponding to the target of the predicted trajectory, where (x, y) represents the center coordinates of the detection box corresponding to the target of the predicted trajectory in the image plane, w and s represent the width and area of ​​the detection box respectively, and c represents the detection confidence. Let X = [x, y, w, s, c] T , is the directly observed motion state; let Indicates the speed of change of the corresponding state. In the kth frame, the motion state of the previous frame is used to predict the motion state of the current frame. The calculation formula is:

[0048]

[0049] in, and X k-1 They represent the predicted state of the trajectory in the current k-th frame and the motion state observed in the k-1th frame, respectively.k is the state transfer matrix of the kth frame under the assumption that the detection frame moves linearly between frames. Similarly, and P k-1 They represent the state change speed of the trajectory in the kth frame and the k-1th frame, respectively, and Q k is the noise matrix of the system, and the calculation formula is:

[0050]

[0051] in, and They represent the predicted width and predicted area of ​​the detection box corresponding to the target in the k-1th frame, σ p Take 0.05, σ v Take 0.00625.

[0052] This implementation method is different from the usual motion prediction method of modeling motion states based on center position, width and aspect ratio. Considering that the change of the detection box area during the movement of the tracking target is more stable than the change of the aspect ratio, the center position, width and area are used for modeling. At the same time, according to the change law of detection confidence when the target is blocked, a "weak clue" such as detection confidence is added to assist in associating the trajectory with the detection target in the subsequent matching stage;

[0053] Step 3.2: For each current frame, the predicted trajectory The prediction confidence and the preset trajectory confidence threshold τ tracklet Compare; if The prediction confidence is greater than or equal to the threshold τ tracklet , then divide this predicted trajectory into a high confidence trajectory set T high ;if The prediction confidence is less than the threshold τ tracklet , then the target is divided into a set of low-confidence trajectories T low ;

[0054] Step 4: Associating the predicted trajectory with the detected target: According to the confidence layered association strategy of the predicted trajectory and the target, the predicted trajectory is associated with the detected target. The specific steps are as follows:

[0055] Step 4.1: High confidence matching: Construct a high confidence prediction trajectory set T high And the high confidence detection target set D high The cost matrix C between stage1 , based on the intersection over union (IoU) distance between the detection box and the trajectory prediction box to calculate the cost; using the Hungarian algorithm based on C stage1 In T high and D highMatch between them to determine the trajectory of the foreground target in the video frame; retain the unmatched trajectory as T remain , the detection target that was not successfully matched is D remain ;

[0056] Step 4.2: Low confidence matching: Construct a low confidence prediction trajectory set T low And the detection target D that was not successfully matched in the previous stage remain The cost matrix C between stage2 , the IoU distance and the confidence difference between the current frame and the previous frame are combined when calculating the cost to improve the matching accuracy; the unmatched trajectories are merged into T remain , the unmatched detection targets are merged into D remain ; The IoU distance and the confidence difference between the current frame and the previous frame are combined when calculating the cost. The formula is:

[0057]

[0058] Among them, c k The target d detected by the target detector k The confidence value at the kth frame, is the trajectory sequence T of the Kalman filter up to the k-1th frame k-1 The historical confidence value predicts its confidence value at the kth frame;

[0059] Step 4.3: Matching of remaining targets: Constructing the trajectory T that was not successfully matched in the first two stages remain And the low confidence detection target set D low The cost matrix C between stage3 , the cost is calculated based on the IoU distance between the detection box and the trajectory prediction box for matching, ensuring that all possible targets are considered to avoid omissions;

[0060] In the absence of depth information, the front and back relationships of overlapping people can be distinguished by detecting differences in confidence. Targets with higher confidence are more likely to be targets in the foreground of the current frame, while targets with lower confidence are more likely to be background targets. Targets with higher confidence are more likely to be tracked correctly, while targets with lower confidence are more likely to be lost and have association errors. Therefore, this embodiment first divides both trajectories and targets into two groups, high and low, according to confidence, so as to divide overlapping targets in the real world into two levels, foreground and background; then, the predicted trajectories and detected targets at different levels are matched separately to avoid mutual interference between overlapping targets;

[0061] Step 5: Save the successfully matched trajectory set T matched , for each successfully matched trajectory t in the current frame k, using the observation value of the matched target in the current frame, update the more accurate motion state X k and the change speed P k , the calculation formula is:

[0062]

[0063] Among them, K k is the Kalman gain, which is used to estimate the importance of the error; R k is the noise matrix of the detector; H k is the measurement matrix, and the predicted value of the motion state is Mapped to the detection space, combined with the observation value z k Calculating the error between the predicted value and the predicted value and using the current observed value to correct the predicted value is conducive to gradually improving the accuracy of target position estimation;

[0064] The detected targets that are not successfully matched will be initialized as new tracks and tracked in the next frame.

[0065] Step 6: Loop through steps 2 to 5 until all frame sequences in the video V are processed and perform multi-target recognition and tracking.

[0066] Performance Analysis:

[0067] ScoreMOT was implemented using the PyTorch framework on Ubuntu 20.04.6. To ensure a fair comparison with other methods, in all subsequent tests, the publicly available YOLOX was used as the detector of the model, and the same detector parameters as ByteTrack were used. The confidence threshold τ of the detection box was det Set to 0.6, the trajectory confidence threshold τ tracklet The θ is set to 0.8, and all experiments are run on a single NVIDIA A10 GPU with 24GB RAM.

[0068] The DanceTrack dataset mainly contains group dance videos. The main features are that the human appearance in the video is highly similar, the movement routes are varied, and the joint movements are complex.

[0069] In the comparison on the DanceTrack dataset, ScoreMOT is mainly compared with current SOTA online tracking methods such as ByteTrack, FairMOT, StrongSORT, GHOST, OC-SORT, etc.

[0070] From the data in Table 1, we can see that on the DanceTrack test set, the three main indicators of ScoreMOT, MOTA, IDF1 and HOTA, are 92.7, 55.2 and 55.5 respectively, achieving the best results among all the tracking methods based on CNN architectures compared. Among all the compared methods, ScoreMOT refreshed the MOTA indicator on the DanceTrack dataset with 92.7, and achieved the second best results in IDF1 and HOTA indicators with 55.2 and 55.5 respectively.

[0071] Table 1 Comparative performance results of the proposed method and other methods on the DanceTrack dataset

[0072]

[0073] In summary, in order to solve the problems of tracking loss and identity ID mismatch in scenes with dense crowds, similar appearances, and complex movements, the present invention proposes a simple and efficient online multi-target tracking method ScoreMOT. In the motion prediction module, ScoreMOT uses MPOBV to achieve target positioning when multiple similar targets are frequently intertwined, thereby providing useful clues for subsequent tracking and matching of occluded and overlapping targets. In the association stage, ScoreMOT uses SHAS to divide the predicted trajectory and the detected target into different levels for staged matching, which improves the accuracy of trajectory and target association in scenes where targets are frequently occluded and overlapped. In the overall structure, only a single deep network is used, which has a low amount of computation and is easy to deploy on edge devices.

[0074] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the technical solution of the present invention still falls within the scope of the technical solution of the present invention.

Claims

1. A multi-target tracking method based on target confidence hierarchical association strategy, characterized by: The steps include: Step 1: Input video V and split it into separate frame sequences, each frame is denoted as f k , where k represents the frame number; Step 2: For the current frame f k , using the target detector to k Processing is performed to obtain frame f k The set D of all pedestrian targets in k , set D k Each target d k The detection confidence including the target detection box is recorded; Each target d k , and its detection confidence and the preset detection confidence threshold τ det Compare; if the target d k The detection confidence is greater than or equal to the threshold τ det , then the target is divided into the high confidence target set D high ; If the target d k The detection confidence is less than the threshold τ det , then the target is divided into the low confidence target set D low ; Step 3: Motion state prediction: Use the motion state prediction method of the occluded target based on the detection frame change trend to predict the existing trajectory in the current frame f k The position in the k-1th frame is recorded as T. k-1 , the specific steps include: Step 3.1: For the set T k-1 Each existing trajectory t k-1 , using the ten-tuple vector Model the motion state of the detection box corresponding to the target of the predicted trajectory, where x and y represent the center coordinates of the detection box corresponding to the target of the predicted trajectory in the image plane, w and s represent the width and area of ​​the detection box respectively, and c represents the detection confidence. They represent the speed of the corresponding variables respectively, and the ten-tuple vector is input into the Kalman filter to predict the motion state of the existing trajectory in the current frame; Step 3.2: For each current frame, the predicted trajectory The prediction confidence and the preset trajectory confidence threshold τ tracklet Compare; if The prediction confidence is greater than or equal to the threshold τ tracklet , then divide this predicted trajectory into a high confidence trajectory set T high ;if The prediction confidence is less than the threshold τ tracklet , then the target is divided into a low confidence trajectory set T low ; Step 4: Associating the predicted trajectory with the detected target: According to the confidence layered association strategy of the predicted trajectory and the target, the predicted trajectory is associated with the detected target. The specific steps are as follows: Step 4.1: High confidence matching: Construct a set of high confidence prediction trajectories T high And the high confidence detection target set D high The cost matrix C between stage1 , based on the intersection over union (IoU) distance between the detection box and the trajectory prediction box to calculate the cost; using the Hungarian algorithm based on C stage1 In T high and D high Match between them to determine the trajectory of the foreground target in the video frame; retain the unmatched trajectory as T remain , the detection target that was not successfully matched is D remain ; Step 4.2: Low confidence matching: Construct a set of low confidence prediction trajectories T low And the detection target D that was not successfully matched in the previous stage remain The cost matrix C between stage2 , the IoU distance and the confidence difference between the current frame and the previous frame are combined when calculating the cost to improve the matching accuracy; the unmatched trajectories are merged into T remain , the unmatched detection targets are merged into D remain ; Step 4.3: Matching of remaining targets: Construct the trajectory T that was not successfully matched in the first two stages remain And the low confidence detection target set D low The cost matrix C between stage3 , the cost is calculated based on the IoU distance between the detection box and the trajectory prediction box for matching, ensuring that all possible targets are considered to avoid omissions; Step 5: Save the successfully matched trajectory set T matched , for each successfully matched trajectory t in the current frame k , using the observation value of the matched target in the current frame, update the more accurate motion state X k and the change speed P k ; The detected targets that are not successfully matched will be initialized as new trajectories and tracked in the next frame; Step 6: Loop through steps 2 to 5 until all frame sequences in the video V are processed, and then perform multi-target recognition and tracking.

2. The multi-target tracking method based on target confidence hierarchical association strategy as claimed in claim 1, characterized in that: In step 2, the object detector is YOLOX.

3. The multi-target tracking method based on target confidence hierarchical association strategy as claimed in claim 1, characterized in that: In step 2, each target d k The center coordinates, width, height, and detection confidence of the target detection box are recorded.

4. The multi-target tracking method based on target confidence hierarchical association strategy as claimed in claim 1, characterized in that: In step 2, the preset detection confidence threshold τ det is 0.

6.

5. The multi-target tracking method based on target confidence hierarchical association strategy as claimed in claim 1, characterized in that: In step 3.1, the motion state of the detection box is modeled as a ten-tuple vector input Kalman filter to predict the motion state of the existing trajectory in the current frame, let X = [x, y, w, s, c] T is the directly observed motion state; let Indicates the speed of change of the corresponding state; in the kth frame, the motion state of the previous frame is used to predict the motion state of the current frame. The calculation formula is: in, and X k-1 They represent the predicted state of the trajectory in the current k-th frame and the motion state observed in the k-1th frame respectively; F k It is the state transfer matrix of the kth frame under the assumption that the detection frame δ moves in linear motion; and P k-1 They represent the state change speed of the trajectory in the kth frame and the k-1th frame respectively; Q k is the noise matrix of the system, and the calculation formula is: in, and They represent the predicted width and predicted area of ​​the detection box corresponding to the target in the k-1th frame, σ p Take 0.05, σ v Take 0.00625.

6. The multi-target tracking method based on target confidence hierarchical association strategy as claimed in claim 1, characterized in that: In step 3.2, the preset trajectory confidence threshold τ tracklet According to the comparative experimental results under different values, it is set to 0.

8.

7. The multi-target tracking method based on target confidence hierarchical association strategy as claimed in claim 1, characterized in that: In step 4.2, the IoU distance and the confidence difference between the current frame and the previous frame are combined when calculating the cost, and the formula is: Among them, c k The target d detected by the target detector k The confidence value at the kth frame, is the trajectory sequence T of the Kalman filter up to the k-1th frame k-1 The historical confidence value is used to predict its confidence value at the kth frame.

8. A multi-target tracking method based on a target confidence hierarchical association strategy according to any one of claims 1 to 7, characterized in that: In step 5, the set of successfully matched trajectories T is saved. matched , for each successfully matched trajectory t in the current frame k , using the observation value of the matched target in the current frame, update the more accurate motion state X k and the change speed P k , the calculation formula is: Among them, K k is the Kalman gain, which is used to estimate the importance of the error; R k is the noise matrix of the detector; H k is the measurement matrix, and the predicted value of the motion state is Mapped to the detection space, combined with the observation value z k Calculating the error between the predicted value and the predicted value and using the current observed value to correct the predicted value is conducive to gradually improving the accuracy of target position estimation.

Images