Open AccessResearch on Target Tracking Algorithm Based on context Multi-feature Fusion
Author(s) -
Yurong Zhao,
Ling Yao,
Peng Xia,
Qianqian Xu
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1678/1/012097
Subject(s) - tracking (education) , clutter , artificial intelligence , histogram , computer science , context (archaeology) , feature (linguistics) , computer vision , algorithm , pattern recognition (psychology) , radar , image (mathematics) , psychology , telecommunications , pedagogy , paleontology , linguistics , philosophy , biology
In traditional target tracking algorithms, cosine window is often used to suppress the boundary effect and expand the search range when the target is located, which will reduce the available background information. Besides, when a single feature is used, the representation of the target appearance is not strong. When the challenge factors such as background clutter and occlusion occur to the target, the target will drift, which will reduce the accuracy of target tracking and even lead to tracking failure. To solve this problem, this paper proposes a context-based target tracking algorithm that fuses multiple features, using directional gradient histogram features and color name features as input features. To solve the occlusion problem, the occlusion mechanism of average peak correlation energy and maximum response fraction value is designed to judge the updating of the model. When both values are higher than a certain historical mean, the model is updated; Otherwise, stop updating. Finally, experiments show that the tracking algorithm proposed in this paper is more robust than some traditional correlation filtering algorithms.