Robust Visual Tracking via Inverse Nonnegative Matrix Factorization
Abstract
The establishment of robust target appearance model over time is an overriding concern in visual tracking. In this paper, we propose an inverse nonnegative matrix factorization (NMF) method for robust appearance modeling. Rather than using a linear combination of nonnegative basis matrices for each target image patch in the conventional NMF, the proposed method is a reverse thought to conventional NMF tracker. It utilizes both the foreground and background information, and imposes a local coordinate constraint, where the basis matrix is sparse matrix from the linear combination of candidates with corresponding nonnegative coefficient vectors. Inverse NMF is used as a feature encoder, where the resulting coefficient vectors are fed into a SVM classifier for separating the target from the background. The proposed method is tested on several videos and compared with seven state-of-the-art methods. Our results have provided further support to the effectiveness and robustness of the proposed method.
Cite
@article{arxiv.1509.06003,
title = {Robust Visual Tracking via Inverse Nonnegative Matrix Factorization},
author = {Fanghui Liu and Tao Zhou and Keren Fu and Irene Y. H. Gu and Jie Yang},
journal= {arXiv preprint arXiv:1509.06003},
year = {2016}
}
Comments
This paper has been withdrawn by the author due to part-based representation. On one hand, not all data can be successfully identified as 'parts' by NMF. On the other hand, inverse sparse representation could not fit this situation. I will give a clearer explanation from clustering instead of part-based representation