Visual Tracking Using Super-pixel Local Weighted Measure and Inverse Sparse Model

	Visual Tracking Using Super-pixel Local Weighted Measure and Inverse Sparse Model
	Liu, Weirong 1; Wu, Hailong 1; Zhao, Junqi 1; Liu, Jie 2; Liu, Chaorong 3
	2017
关键词	sparse representation super pixel visual tracking local weight
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.
会议录	PROCEEDINGS OF 2017 3RD IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATIONS (ICCC)
会议录出版者	IEEE
会议录出版地	345 E 47TH ST, NEW YORK, NY 10017 USA
语种	英语
资助项目	National Natural Science Foundation of China[61461028] ; Natural Science Foundation of Gansu Province[1508RJZA092]
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS记录号	WOS:000440623602017
内容类型	会议论文
源URL	[http://119.78.100.223/handle/2XXMBERH/36203]
专题	电气工程与信息工程学院党委教师工作部（人事处、教师发展中心）
通讯作者	Liu, Weirong
作者单位	1.Lanzhou Univ Technol, Coll Elect & Informat Engn, Lanzhou 730050, Gansu, Peoples R China 2.Lanzhou Univ Technol, Natl Demonstrat Ctr Expt Elect & Control Engn Edu, Lanzhou 730050, Gansu, Peoples R China 3.Lanzhou Univ Technol, Key Lab Gansu Adv Control Ind Proc, Lanzhou 730050, Gansu, Peoples R 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:.