Moving target tracking method based on multi-target characteristics and improved correlation filter

Abstract

The invention discloses a moving target tracking method based on multi-target characteristics and an improved correlation filter. The method comprises the following steps: inputting position information of a tracked target in a tracking video sequence and an initial frame; extracting multi-channel features of the target to achieve comprehensive information representation of the target; constructing a pixel reliability graph to perform constraint optimization on a correlation filter, and limiting the correlation filter in an image area suitable for tracking; reducing the number of parameters inthe model by using a linear dimension reduction operator, and training a compact sample classification model; performing secondary optimization on the correlation filter through a Gauss-Newton methodand a conjugate gradient method to obtain an optimal correlation filter; responding to the improved correlation filter and the extracted target features of the target search area, and determining theposition of a target tracking box; jointly updating the filter model and the pixel reliability diagram; and outputting a tracking result map. According to the method, moving targets in most scenes can be effectively tracked, and the method has good tracking precision and real-time performance.

Description

technical field [0001] The invention relates to image processing technology, in particular to a moving target tracking method based on multi-target features and an improved correlation filter. Background technique [0002] Vision-based moving target tracking technology takes video images as the processing object, and uses image processing algorithms as the core to track single or multiple moving targets. After decades of research, target tracking algorithms based on computer vision have successively developed many important algorithms at home and abroad, such as optical flow method, Kalman filter, correlation filter, etc., which have achieved better tracking accuracy. Vision-based moving target tracking technology is widely used in both military and civilian fields, such as military strikes, police security and so on. [0003] In the process of moving target tracking, due to reasons such as environment, camera rotation and camera carrier movement, shadow interference, lack ...

AI Technical Summary

Problems solved by technology

[0004] At present, the vision-based target tracking method still has a lot of room for improvement when dealing with the difficulty of target tracking. For example, the patent CN106530330B proposes a video target tracking method based on low-rank sparseness, which uses the statistical tracking method particle filter for state estimation. Low-rank sparse representation of targets and particles is established by establishing a dictionary to reduce computational complexity. Part of the particles are deleted in advance by using reconstruction errors, and then the difference score is calculated to finally determine the target of the next frame. This method requires a sufficient number of samples to be well approximated. The posterior probability density of the system cannot maintain the effectiveness and diversity of particles; the patent CN109828596A proposes a target tracking method, device and UAV, which controls the visible light camera to visually track the target and records the first position of the target in real time. One tracking information, control the infrared camera to perform infrared tracking on the target, and record the second tracking information of the target in real time, and determine that the visible light camera has lost the target, then control the visible light camera to re-lock the target according to the second tracking information and perform visual tracking, Visible light and infrared target features are not fused, alternate tracking does not update historical target information, and it is easy to lead to tracking loss; patent CN109729498A proposes a target tracking method and system based on Voronoi diagram for adaptive node selection, using Voronoi diagram As a network model, the nodes in the network are clustered. There are active nodes, dormant nodes and the only cluster head node in the cluster. According to the proposed node selection algorithm, the sensor nodes in the Voronoi diagram area are partially activated, and the extended Kalman Filtering is used for target tracking, the non-linear filtering method has poor stability and slow response to target maneuvering

The literature "Qi Yongfeng, Wang Mengyuan. Moving target tracking algorithm based on LBP and kernel correlation filter [J]. Infrared Technology, 2019, 41(6): 572-576" aims at the tracking error of kernel correlation filter under complex lighting conditions. Stable phenomenon, adding LBP processing method to the traditional algorithm, reducing the impact of illumination on feature extraction, the results show that the tracking performance in the case of complex illumination has been significantly improved, but no in-depth research has been done in other cases

Literature "Zhou Wei, Chen Tinghai, Qiu Baoxin. Research on Anti-Occlusion Target Tracking Method Introducing Feature Re-inspection [J]. Computer Engineering and Application. ISSN 1002-8331, CN 11-2127 / TP." Occlusion for Visual Target Tracking The problem is that on the basis of the TLD algorithm, the feature re-examination link is introduced, and the SIFT feature is selected for two-way matching to calibrate the target. The single feature causes when the target is blurred and similar to the background, the re-calibrated target is wrong, not the original occluded tracking target.

The literature "Li Jing, Huang Shan. Target Tracking Method Based on YOLOv3 [J]. Electro-optic and Control" takes advantage of the deep learning model in target feature extraction, and uses the regression-based YOLOv3 detection model to extract candidate targets, and combines the target color histogram feature and Local binary mode histogram features are used to screen targets to achieve target tracking. However, as the tracking process becomes longer, the extracted target feature parameters become huge and the tracking rate slows down.

Images