Target tracking based on hierarchical feature fusion of residual neural network

doi:10.1117/12.2547560

CORC > 光电技术研究所 > 中国科学院光电技术研究所 > 自适应光学技术研究室（八室）

	Target tracking based on hierarchical feature fusion of residual neural network
	Jin, Hui 1,2,3; Li, XinYang 1,2
	2019
会议日期	August 23, 2019 - August 25, 2019
会议地点	Shanghai, China
关键词	Target Tracking Residual Neural Network feature fusion addition layer OPE
卷号	11321
DOI	10.1117/12.2547560
页码	113211H
英文摘要	Feature expression is a crucial part of the target tracking process. The artificial feature is relatively simple and has strong real-time performance, but there is a problem of insufficient representation ability. It is prone to drift when dealing with problems such as rapid change and target occlusion. With the strong feature expression ability of deep neural network features in target detection and recognition tasks, deep neural network features are gradually used as feature extraction tools, but how to use and integrate these features is still worth studying. In this paper, the Residual Neural Network(ResNet) is the main researched object, and the influence of each layer on the target tracking performance is analyzed in detail. The feature fusion strategy of the convolutional layer and the addition layer is finally determined. We train a classifier separately for these layers. Then we search the multi-layer response maps to infer the target location in a coarse-to-fine fashion. The algorithm of this paper is verified on the OTB-50 dataset. The one-pass evalution(OPE) value can reach 0.612, which is better than the same type of algorithms. © 2019 SPIE.
会议录	Proceedings of SPIE 11321 - 2019 International Conference on Image and Video Processing, and Artificial Intelligence
会议录出版者	SPIE
文献子类	会议论文
语种	英语
ISSN号	0277-786X
WOS研究方向	Computer Science, Artificial Intelligence ; Optics ; Imaging Science & Photographic Technology
WOS记录号	WOS:000511402300051
内容类型	会议论文
源URL	[http://ir.ioe.ac.cn/handle/181551/9633]
专题	光电技术研究所_自适应光学技术研究室（八室）
作者单位	1.Key Laboratory on Adaptive Optics, Chinese Academy of Sciences, Chengdu, Sichuan; 610209, China; 2.Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, Sichuan; 610209, China; 3.University of Chinese Academy of Sciences, Beijing; 100049, China
推荐引用方式 GB/T 7714	Jin, Hui,Li, XinYang. Target tracking based on hierarchical feature fusion of residual neural network[C]. 见:. Shanghai, China. August 23, 2019 - August 25, 2019.