Multi-characteristic layered fusion correlation filtering robustness tracking method

Abstract

The invention relates to a multi-characteristic layered fusion correlation filtering robustness tracking method. In order to improve the robustness of target tracking, aiming at the multi-characteristic fusion problem in correlation filtering tracking, a multi-characteristic layered fusion strategy is provided. HOG characteristics, CN characteristics and color histogram characteristics are extracted from a target area and a surrounding background area respectively. A self-adaption weighting fusion strategy is adopted for integration of characteristic response diagrams of the HOG characteristics and the CN characteristics. A fusion result of a layer and the obtained characteristic response diagrams based on the color histogram characteristics are subjected to second-layer integration, a fixed parameter fusion strategy is adopted for fusion of the characteristic response diagrams. According to the method, under the premise that the tracking accuracy is guaranteed, the tracking robustnessis superior to other algorithms. When multiple characteristics are adopted for a correlation filtering tracking algorithm, the layered fusion strategy has certain reference.

Description

technical field [0001] The invention belongs to the field of target tracking and relates to a correlation filter robust tracking method for multi-feature layered fusion. Background technique [0002] Visual tracking is used to determine the continuous position of the object of interest in the video sequence. It is one of the hot issues in the field of computer vision and has extensive research and application value. At present, the main visual tracking algorithms include visual tracking algorithms based on online learning, visual tracking algorithms based on sparse representation, visual tracking algorithms based on correlation filtering and visual tracking algorithms based on convolutional neural networks. In recent years, the visual tracking algorithm based on correlation filter has achieved excellent results in the VOT visual tracking competition due to its advantages of good real-time performance and high tracking performance. [0003] The main factors affecting the per...

AI Technical Summary

Problems solved by technology

Different types of features are directly combined into multi-channel features. Although the fusion method is simple to implement, the fusion features are fixed and cannot be adaptively changed according to changes in the surrounding environment of the target to improve the salience of the fusion features.

Images