Visual tracking using super-pixel local weighted measure and inverse sparse model

doi:10.1109/CompComm.2017.8322891

CORC > 兰州理工大学 > 兰州理工大学 > 党委教师工作部（人事处、教师发展中心）

	Visual tracking using super-pixel local weighted measure and inverse sparse model
	Liu, Weirong 1; Wu, Hailong 1; Zhao, Junqi 1; Liu, Jie 3; Liu, Chaorong 2
	2017-07-02
会议日期	December 13, 2017 - December 16, 2017
会议地点	Chengdu, China
关键词	Inverse problems Confidence maps Double threshold Human body postures Illumination changes Local Weight Precise tracking Sparse representation Visual Tracking
卷号	2018-January
DOI	10.1109/CompComm.2017.8322891
页码	2020-2024
英文摘要	Recently, sparse representation and super-pixel mid-level cues have been applied to visual tracking with demonstrated success. The authors propose an efficient and precise tracking algorithm, it has three features: super-pixel local weight, a novel sparse model and double threshold scheme to determine weight update. In the super-pixel local weight, the authors segment the surrounding target regions into super-pixels in stage of training, and then apply mean-shift on the surrounding target regions super-pixels to obtain clusters. A confidence map is calculated according to the clusters. After that, we combine the template super-pixels with the confidence map to compute the initial super-pixel local weight. The inverse sparse model is adopted to improve the tracking efficiency. For double threshold super-pixel updates, we compare the super-pixels update areas with the double threshold to decision update or not. Experimental results show that our method is robust to illumination change, human body posture change and heavy occlusion. © 2017 IEEE.
会议录	2017 3rd IEEE International Conference on Computer and Communications, ICCC 2017
会议录出版者	Institute of Electrical and Electronics Engineers Inc.
语种	英语
内容类型	会议论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/117991]
专题	党委教师工作部（人事处、教师发展中心）电气工程与信息工程学院
作者单位	1.College of Electrical and Information Engineering, Lanzhou University of Technology, China; 2.Key Laboratory of Gansu Advanced Control for Industrial Processes, Lanzhou University of Technology, Lanzhou, China 3.National Demonstration Center for Experimental Electrical and Control Engineering Education, Lanzhou University of Technology, China;
推荐引用方式 GB/T 7714	Liu, Weirong,Wu, Hailong,Zhao, Junqi,et al. Visual tracking using super-pixel local weighted measure and inverse sparse model[C]. 见:. Chengdu, China. December 13, 2017 - December 16, 2017.