Learning Structured Visual Dictionary for Object Tracking

Fan Yang1,3, Huchuan Lu1 and Ming-Hsuan Yang2

1 School of Information and Communication Engineering, Dalian University of Technology, Dalian, China
2 Electrical Engineering and Computer Science, University of California at Merced, Merced, United States
3 Department of Computer Science, University of Maryland, College Park, United States

Abstract

In this paper, we propose a visual tracking algorithm by incorporating the appearance information gathered from two collaborative feature sets and exploiting its geometric structures. A structured visual dictionary (SVD) can be learned from both appearance and geometric structure, thereby enhancing its discriminative strength between the foreground object and the background. Experimental results show that the proposed tracking algorithm using SVD (SVDTrack) performs favorably against the state-of-the-art methods.

Experimental Results

To be uploaded.

Code and Datasets

The MATLAB implementation can be downloaded from here (version 1.1). Please see README for more details.
Datasets to be uploaded.

Publications