Multi-Task Object Tracking with Feature Selection

Xu CHENG  Nijun LI  Tongchi ZHOU  Zhenyang WU  Lin ZHOU  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E98-A   No.6   pp.1351-1354
Publication Date: 2015/06/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.E98.A.1351
Type of Manuscript: LETTER
Category: Image
visual tracking,  sparse representation,  multi-task learning,  feature selection,  

Full Text: PDF(2MB)>>
Buy this Article

In this paper, we propose an efficient tracking method that is formulated as a multi-task reverse sparse representation problem. The proposed method learns the representation of all tasks jointly using a customized APG method within several iterations. In order to reduce the computational complexity, the proposed tracking algorithm starts from a feature selection scheme that chooses suitable number of features from the object and background in the dynamic environment. Based on the selected feature, multiple templates are constructed with a few candidates. The candidate that corresponds to the highest similarity to the object templates is considered as the final tracking result. In addition, we present a template update scheme to capture the appearance changes of the object. At the same time, we keep several earlier templates in the positive template set unchanged to alleviate the drifting problem. Both qualitative and quantitative evaluations demonstrate that the proposed tracking algorithm performs favorably against the state-of-the-art methods.