Online Learning and Detection with Part-based Circulant Structure


Akin O., Mikolajczyk K.

22nd International Conference on Pattern Recognition (ICPR), Stockholm, Sweden, 24 - 28 August 2014, pp.4229-4233 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume:
  • Doi Number: 10.1109/icpr.2014.725
  • City: Stockholm
  • Country: Sweden
  • Page Numbers: pp.4229-4233

Abstract

Circulant Structure Kernel (CSK) has recently been introduced as a simple and extremely efficient tracking method. In this paper, we propose an extension of CSK that explicitly addresses partial occlusion problems which the original CSK suffers from. Our extension is based on a part-based scheme, which improves the robustness and localisation accuracy. Furthermore, we improve the robustness of CSK for long-term tracking by incorporating it into an online learning and detection framework. We provide an extensive comparison to eight recently introduced tracking methods. Our experimental results show that the proposed approach significantly improves the original CSK and provides state-of-the-art results when combined with online learning approach.