標題: Trajectory Based Jump Pattern Recognition in Broadcast Volleyball Videos
作者: Hsu, Chun-Chieh
Chen, Hua-Tsung
Chou, Chien-Li
Ho, Chien-Peng
Lee, Suh-Yin
交大名義發表
資訊工程學系
National Chiao Tung University
Department of Computer Science
關鍵字: Sport video analysis;pattern recognition;camera calibration;object localization;trajectory analysis
公開日期: 1-Jan-2014
摘要: Jump actions are typically accompanied by spiking and imply significant events in volleyball matches. In this paper, we propose an effective system capable of jump pattern recognition in player moving trajectories from long broadcast volleyball videos. First, the entire video is segmented into clips of rallies by shot segmentation and whistle detection. Then, camera calibration is adopted to find the correspondence between coordinates in the video frames and real-world coordinates. With the homographic transformation matrix computed, real-world player moving trajectories can be derived by a sequence of tracked player locations in video frames. Jump patterns are recognized from the player moving trajectory by using a sliding window scheme with physics-based validation and context constraint. Finally, the jump locations can be estimated and jump tracks can be separated from the planar moving tracks. The experiments conducted on broadcast volleyball videos show promising results.
URI: http://dx.doi.org/10.1145/2647868.2654985
http://hdl.handle.net/11536/152904
ISBN: 978-1-4503-3063-3
DOI: 10.1145/2647868.2654985
期刊: PROCEEDINGS OF THE 2014 ACM CONFERENCE ON MULTIMEDIA (MM'14)
起始頁: 1117
結束頁: 1120
Appears in Collections:Conferences Paper