Sparse vs. Non-sparse: Which One Is Better for Practical Visual Tracking?
This work addresses a fundamental question for computer vision researchers and practitioners, but it is incremental as it builds on existing sparse tracking methods.
The paper tackled the problem of whether sparsity constraints are necessary for visual tracking by proposing a non-sparse tracker and comparing it to sparse methods. The result showed that the non-sparse tracker achieved competitive accuracy with faster speed, making it suitable for practical applications.
Recently, sparse representation based visual tracking methods have attracted increasing attention in the computer vision community. Although achieve superior performance to traditional tracking methods, however, a basic problem has not been answered yet --- that whether the sparsity constrain is really needed for visual tracking? To answer this question, in this paper, we first propose a robust non-sparse representation based tracker and then conduct extensive experiments to compare it against several state-of-the-art sparse representation based trackers. Our experiment results and analysis indicate that the proposed non-sparse tracker achieved competitive tracking accuracy with sparse trackers while having faster running speed, which support our non-sparse tracker to be used in practical applications.