Open AccessRobust correlation filter that combined temporal regularization with spatial weight L1 constraint
Author(s) -
Xin He,
Shukai Duan,
Lidan Wang
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 - 10.1088/1742-6596/1550/4/042076
Subject(s) - regularization (linguistics) , robustness (evolution) , computer science , algorithm , mathematics , minification , correlation , artificial intelligence , computational complexity theory , pattern recognition (psychology) , computer vision , mathematical optimization , biochemistry , chemistry , geometry , gene
The parameter optimization of the Object tracking algorithms has achieved excellent performance based on parameter regularization. Adaptive spatial regularization correlation filter can obtain the optimal weight coefficient for a specific target. Inspired by this, we propose a filter combined temporal regularity with spatial L1 regularization (LTASRCF). The time regularizer is used to remember the data of the previous frame to update the current target position. It performs well in the process of occlusion, deformation and motion blur. Meanwhile, L1 regularization of spatial weights reduces the computational complexity of the coefficients, and improves the robustness of the spatial weight matrix. We have conducted comparative experiments on the OTB-2015 dataset, and the proposed LTASRCF model ranks first among the five popular algorithms, which outperforms by 9.2% and 18.9% than KCF, respectively, and reaches real-time performance.