Robust Object Tracking using Sparse based Representative Dictionary Learning

被引:0
作者
Jansi, R. [1 ]
Amutha, R. [1 ]
Alice, R. [1 ]
Chitra, E. Mano [1 ]
Ros, G. M. Susmitha [1 ]
机构
[1] SSN Coll Engn, Dept ECE, Madras, Tamil Nadu, India
来源
2017 INTERNATIONAL CONFERENCE ON COMPUTATION OF POWER, ENERGY INFORMATION AND COMMUNICATION (ICCPEIC) | 2017年
关键词
appearance model; candidate; dictionary learning; object tracking; sparse; VISUAL TRACKING; COLLABORATIVE MODEL;
D O I
暂无
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
Inspired by the recent advances in sparse theory, we propose a new sparse based object tracking framework in this paper. In order to effectively detect the target object to be tracked, we formulate and present a new sparse based representative dictionary learning algorithm and candidate selection scheme for robust object tracking. Specifically, we have used Pearson's correlation based dictionary learning algorithm to engender a highly representative dictionary. This representative dictionary is then used for modeling an adaptive appearance model for the target, which is robust to challenges like partial occlusions, illumination, clutter scenes and pose changes. We also present a new Appearance Model Structural Similarity test algorithm for meticulously identifying the target from various candidates in the consecutive frames of video sequences. Results of extensive experimentations carried out using various publicly available datasets shows that our framework produces an exorbitant performance compared to many state-of-the-art works.
引用
收藏
页码:102 / 107
页数:6
相关论文
共 26 条
[1]  
Adam A., 2006, IEEE C COMPUTER VISI, V1, P798, DOI [DOI 10.1109/CVPR.2006.256, 10.1109/CVPR.2006.256]
[2]  
Babenko B, 2009, PROC CVPR IEEE, P983, DOI 10.1109/CVPRW.2009.5206737
[3]  
Bao CL, 2012, PROC CVPR IEEE, P1830, DOI 10.1109/CVPR.2012.6247881
[4]   Robust visual tracking based on hierarchical appearance model [J].
Bao, Hua ;
Lin, Mingqiang ;
Chen, Zonghai .
NEUROCOMPUTING, 2017, 221 :108-122
[5]   Discriminative local collaborative representation for online object tracking [J].
Chen, Si ;
Li, Shaozi ;
Ji, Rongrong ;
Yan, Yan ;
Zhu, Shunzhi .
KNOWLEDGE-BASED SYSTEMS, 2016, 100 :13-24
[6]   Sparse representation combined with context information for visual tracking [J].
Feng, Ping ;
Xu, Chunyan ;
Zhao, Zhiqiang ;
Liu, Fang ;
Yuan, Caihong ;
Wang, Tianjiang ;
Duan, Kui .
NEUROCOMPUTING, 2017, 225 :92-102
[7]  
Hann Guang, NEUROCOMPUTING, V184, P145
[8]  
Hare S, 2011, IEEE I CONF COMP VIS, P263, DOI 10.1109/ICCV.2011.6126251
[9]   Exploiting the Circulant Structure of Tracking-by-Detection with Kernels [J].
Henriques, Joao F. ;
Caseiro, Rui ;
Martins, Pedro ;
Batista, Jorge .
COMPUTER VISION - ECCV 2012, PT IV, 2012, 7575 :702-715
[10]   Object tracking using discriminative sparse appearance model [J].
Huang, Dandan ;
Sun, Yi .
SIGNAL PROCESSING-IMAGE COMMUNICATION, 2015, 37 :1-18