计算机工程与应用2019，Vol.55Issue(8)：157-163,7.DOI:10.3778/j.issn.1002-8331.1801-0020
DCNN深度特征与交替方向乘子的相关滤波跟踪
Correlation Filter Tracking Integrated DCNN Depth Feature with Alternating Direction of Mul-tipliers
摘要
Abstract
This paper is aiming at the bottleneck problem of discriminative target tracking using correlation filter. On the period of learning and updating on correlation filter, error is likely to be induced into filter, and fatal cumulation will finally cause tracker inefficiency. It is attributed to the boundary effect caused by the rapid movement of the target. Based on acquisition of depth learning features and sample similarity measure, an improved correlation filter target tracking algo-rithm with alternating direction method of multipliers is proposed in this paper. DCNN depth features are selected to effec-tively represent the initial state of the object to be tracked. The algorithm uses sample similarity matching with semi super-vised learning in online classification process. The above methods assist in solving the self-learning problem of the corre-lation filter in the learning process. The proposed object tracking algorithm is especially suited to machine learning pro-cess where samples are continually acquired and memory storage is limited. On the complicated scenes such as object speed drastically changing and object partially blocked, etc., success tracking rate is updated by importing the proposed object tracking algorithm. When target vehicle is partially blocked, the experiments on standard testing videos involving VOT2016 demonstrate that success tracking rate of the proposed DA-CFT tracking algorithm is raised to 85.6%~91.0%, compared with 60.4%~73.4% of CN algorithm, 67.2%~82.9% of SAMF algorithm and 80.9%~88.1% of STC algorithm.关键词
目标跟踪/相关滤波器/边界效应/深度特征/交替方向乘子/样本相似性Key words
object tracking/ correlation filter/ boundary effect/ depth feature/ alternating direction multiplier/ sample similarity分类
信息技术与安全科学引用本文复制引用
吴刚,曾晓勤,王池社,苏守宝..DCNN深度特征与交替方向乘子的相关滤波跟踪[J].计算机工程与应用,2019,55(8):157-163,7.基金项目
国家自然科学基金(No.61573266). （No.61573266）
