Trajectory Based Jump Pattern Recognition in Broadcast Volleyball Videos

檔案

本條目沒有附加檔案。

至出版者網站查看(DOI) ›

日期

2014-01-01

期刊名稱

PROCEEDINGS OF THE 2014 ACM CONFERENCE ON MULTIMEDIA (MM'14)

卷期與頁次

頁 1117–1120

ISBN

978-1-4503-3063-3

語言

英文

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.

所屬典藏

會議論文
顯示完整詮釋資料 統計資料

引用此條目

Hsu, C.-C., Chen, H.-T., Chou, C.-L., Ho, C.-P., & Lee, S.-Y. (2014). Trajectory Based Jump Pattern Recognition in Broadcast Volleyball Videos. PROCEEDINGS OF THE 2014 ACM CONFERENCE ON MULTIMEDIA (MM'14), 1117–1120. https://doi.org/10.1145/2647868.2654985

BibTeX RIS

引用文字依 APA 第 7 版格式自動產生,使用前請再核對。

分享

永久網址:https://ir.lib.nycu.edu.tw/handle/11536/152904