Kernel correlation filtering target tracking method based on feature fusion and Bayesian classification

Abstract

The invention provides a kernel correlation filtering target tracking method based on feature fusion and Bayesian classification. The method is characterized by comprising steps: firstly, the position and the scale information of an initial frame target are given; then, a standard target appearance model, a standard correlation filter and a standard color Bayesian model are built or updated; based on the target center point of a former frame, a search area is extracted; and a correlation filter of a Gaussian kernel is used for realizing target displacement estimation, the color Bayesian model is used for realizing target scale estimation, and the tracking result of the current frame is obtained further. Through sequentially processing each frame of video image, tracking of a moving target in the video is realized. The target tracking method can effectively solve the problem of precisely positioning the moving target in the video and can realize target scale estimation. In multiple challenging environments, the target can be tracked effectively, certain robustness is realized, and the tracking algorithm precision is improved.

Description

technical field [0001] The present invention relates to the technical field of target tracking, and more specifically relates to a kernel correlation filter target tracking method based on feature fusion and Bayesian classification. Background technique [0002] Target tracking algorithm is a popular research direction in the field of computer vision at present. Its main task is to continuously track the target of interest online in a given video sequence, so as to obtain information such as the position of the target in each frame of image. In recent years, object tracking technology has been widely used in many fields such as video surveillance, human-computer interaction, and video content analysis. Although so far, researchers have proposed many solutions. However, due to the need to consider various interference factors during the movement of the target, such as: self-deformation, illumination changes, background noise, occlusion, etc., it is still a considerable chall...

AI Technical Summary

Problems solved by technology

[0008] However, there are two deficiencies in the method based on correlation filtering. First, the features used by this type of algorithm are relatively simple, and the description of the target appearance is often insufficient; when the target appearance is disturbed, a single feature is easy to change, resulting in The overall performance of the algorithm is reduced; second, many tracking algorithms based on correlation filters fix the size of the target, so they cannot deal with the problem of target scale changes; in fact, due to the movement of the target or the change of the distance from the lens, the target scale will The change of the fixed scale algorithm is obviously not conducive to the accurate estimation of the target

Images