For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Trajectory Estimation of the Players and Shuttlecock for the Broadcast Badminton Videos
Yen-Ju LIN Shiuh-Ku WENG
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2018/10/01
Online ISSN: 1745-1337
Type of Manuscript: LETTER
adaptive Kalman filter, trajectory confidence,
Full Text: PDF(2.1MB)
>>Buy this Article
To track the players and shuttlecock in broadcast badminton video is a challenge, especially for tracking the small size and fast moving shuttlecock. There are many situations that may cause occlusion or misdetection. In this paper, a method is proposed to track players and shuttlecock in broadcast badminton videos. We apply adaptive Kalman filter, trajectory confidence estimation and confidence-update (Location Similarity and Relative Motion Relation, RMR) to improve the accuracy of object trajectories. In our experiments, the proposed method significantly enhance the tracking success rate of players and shuttlecock.