Automatic line mark recognition and its application in camera calibration in soccer video

  • Authors:

  • Jiang Bu; Songyang Lao; Liang Bai

  • Affiliations:

  • Sci. & Technol. on Inf. Syst. Eng. Lab., Nat. Univ. of Defense Technol., Changsha, China;Sci. & Technol. on Inf. Syst. Eng. Lab., Nat. Univ. of Defense Technol., Changsha, China;Sci. & Technol. on Inf. Syst. Eng. Lab., Nat. Univ. of Defense Technol., Changsha, China

  • Venue:
  • ICME '11 Proceedings of the 2011 IEEE International Conference on Multimedia and Expo
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

The white line marks on the soccer playfield can convey the positional information of the ongoing match. In this paper, we propose a new algorithm for automatic, robust line mark recognition for soccer video and its application in camera calibration is also investigated. The line mark recognition consists of four steps, playfield region detection, playfield area analysis, edge pixel detection and repairing, line mark location. The preliminary experiment shows that the line marks (including curved lines) can be located reliably (precision$\gt$90%), and its application in camera calibration is also effective especially when there are not enough straight lines.