TLD particle swarm optimization target tracking using a sample deletion mechanism

doi:10.3788/OPE.20192705.1206

CORC > 长春光学精密机械与物理研究所 > 中国科学院长春光学精密机械与物理研究所

	TLD particle swarm optimization target tracking using a sample deletion mechanism
	S.-Q.Guo; T.Zhang; X.-K.Miao
刊名	Guangxue Jingmi Gongcheng/Optics and Precision Engineering
	2019
卷号	27 期号:5 页码:1206-1217
关键词	Target tracking,Clutter (information theory,Computational efficiency,Efficiency,Learning algorithms
ISSN号	1004924X
DOI	10.3788/OPE.20192705.1206
英文摘要	This study improved the tracking robustness and real-time performance of a tracking-learning-detection (TLD) algorithm for a wide range of scenarios by considering two important aspects, namely, the tracking and learning modules. The study proposed a TLD particle swarm optimization (PSO) target-tracking algorithm using a sample deletion mechanism. First, the original tracking module of a TLD algorithm was replaced by a color-feature-based PSO target-tracking algorithm, which enhanced the tracking performance of the TLD algorithm in terms of target non-rigid deformation, scale variation, rotation, and occlusion. Second, a sample deletion mechanism for the learning module of the TLD algorithm was introduced. During the tracking process, a threshold was set for the positive and negative samples. When both the positive and negative samples reach their respective thresholds, the sample deletion mechanism was initiated. The image blocks to be classified into the sample library were then graded, and those with a weak representation ability for both positive and negative samples were deleted. Finally, we matched the positive and negative samples in the sample library with the current target and delete the samples with low representational ability to the current target. Experiments on OTB2013 and OTB2015 datasets show that the one-pass evaluation (OPE) accuracy of the proposed algorithm reaches 0.687, the OPE success rate of the algorithm is 0.488, and the operation efficiency is improved by 25.64% on average. This essentially satisfies the robustness of target tracking in a wide range of scenarios and significantly improves the computational efficiency of the algorithm. 2019, Science Press. All right reserved.
URL标识	查看原文
内容类型	期刊论文
源URL	[http://ir.ciomp.ac.cn/handle/181722/63355]
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	S.-Q.Guo,T.Zhang,X.-K.Miao. TLD particle swarm optimization target tracking using a sample deletion mechanism[J]. Guangxue Jingmi Gongcheng/Optics and Precision Engineering,2019,27(5):1206-1217.
APA	S.-Q.Guo,T.Zhang,&X.-K.Miao.(2019).TLD particle swarm optimization target tracking using a sample deletion mechanism.Guangxue Jingmi Gongcheng/Optics and Precision Engineering,27(5),1206-1217.
MLA	S.-Q.Guo,et al."TLD particle swarm optimization target tracking using a sample deletion mechanism".Guangxue Jingmi Gongcheng/Optics and Precision Engineering 27.5(2019):1206-1217.