Robust Visual Tracking via Inverse Nonnegative Matrix Factorization
This is an incremental improvement for visual tracking researchers, addressing the problem of robust target appearance modeling over time.
The paper tackles robust appearance modeling in visual tracking by proposing an inverse nonnegative matrix factorization method that incorporates foreground and background information with a local coordinate constraint, and reports effectiveness and robustness compared to seven state-of-the-art methods on several videos.
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.