中国科学院重庆绿色智能技术研究院机构知识库

QQ客服 官方微博 反馈留言

	Visual tracking with complementary deep feature optimization
	Wang, Wei1,2; Chen, Zhaoming1; Shi, Mingquan1
	2018-07-01
摘要	The challenges of rotation, occlusion, and scale change in visual object tracking have been an urgent problem to be solved. In recent years, the online learning ability and discriminative power of convolutional neural network (CNN) features have gained great attention in many computer vision tasks. Previous studies have shown that individual layer CNN features can be used for dealing with specific tracking challenges, such as target accurate positioning, rotation, and deformation. However, tracking with single CNN features is not enough to deal with serious challenges, such as the above-mentioned. To handle this problem, we evaluate the contribution of specific CNN layers features in tracking tasks and present a complementary CNN features tracking framework, which treats tracking procedure as a deep CNN features optimizing. Our tracker does not merely fuse the CNN features but is a semantic level method, which adds a competition mechanism to optimize the target appearance encoding of CNN layers. Therefore, the proposed tracker is robust not only to target location but also to rotation and deformation. We also embed hard negative mining to enhance the discriminative power of the tracking model and use bounding box regression to refine the tracking result. Having compared our tracker performance with other state-of-the-art trackers, the obtained experimental results in a large-scale dataset demonstrate that the effectiveness of our proposed tracker outperforms state-of-the-art ones. (C) 2018 SPIE and IS&T
关键词	semantic tracking convolutional networks complementary convolutional feature optimization hard negative mining bounding box regression
DOI	10.1117/1.JEI.27.4.043052
发表期刊	JOURNAL OF ELECTRONIC IMAGING
ISSN	1017-9909
卷号	27期号:4页码:10
收录类别	SCI
WOS记录号	WOS:000445139400004
语种	英语