A novel moving cast shadow detection of vehicles in traffic scene

  • Authors:

  • Yuhong Jia;Xiaoxi Yu;Jiangyan Dai;Wanjun Hu;Jun Kong;Miao Qi

  • Affiliations:

  • Department of Information Engineering, Jilin Business and Technology College, Changchun, China;School of Computer Science and Information Technology, Northeast Normal University, Key Laboratory of Intelligent Information Processing of Jilin Universities, Changchun, China;School of Computer Science and Information Technology, Northeast Normal University, Key Laboratory of Intelligent Information Processing of Jilin Universities, Changchun, China;School of Computer Science and Information Technology, Northeast Normal University, Key Laboratory of Intelligent Information Processing of Jilin Universities, Changchun, China;School of Computer Science and Information Technology, Northeast Normal University, Key Laboratory of Intelligent Information Processing of Jilin Universities, Changchun, China;School of Computer Science and Information Technology, Northeast Normal University, Key Laboratory of Intelligent Information Processing of Jilin Universities, Changchun, China

  • Venue:
  • IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

In the traffic video scene, the existence of shadows might generate negative effect on pattern analysis. This paper proposes a novel approach which adequately considers color space information to detect moving cast shadows of vehicles in traffic videos. Firstly, RGB component ratios between frame and background as well as blue and red colors ratio (B/R ratio) are taken into account to detect shadows respectively. Then we combine the two results for a refined shadow candidate. Finally, to improve the accuracy of shadow detection, post processing is adopted to correct the false detected pixels. Experimental results on several databases indicate that our approach not only achieves both high shadow detection and discrimination rates but takes on better performance than some state-of-the-art methods.