Visual Tracking Using L2 Minimization
Department of Electronic Engineering, Tianjin University of Technology and Education, Tianjin, China
a Corresponding author: email@example.com
Visual tracking has been an active research topic in the computer vision applications. By modeling the target appearance with a sparse approximation over a template set, sparse representation has been applied to the visual tracker, which called L1 tracker. Due to the need to solve the L1 norm related minimization problem for many times, this L1 tracker is very computationally demanding. Although various fast numerical solver is developed to solve the resulting L1 norm related minimization problem, the framework is still a L1 norm related minimization model. Similar to the face recognition problem, sparse approximations may not deliver the desired robustness and a simple L2 approach to the visual tracking problem is not only robust, but also much faster. It may be possible to apply the L2 minimization, instead of L1 minimization, to the visual tracking problems, which has been verified by experiments on challenging sequences in the paper.
© Owned by the authors, published by EDP Sciences, 2016
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.