Automatic annotation of tennis games: An integration of audio, vision, and learning

作者：

Highlights：

• Fully automatic annotation of real-world tennis video

• State-of-the-art tennis ball tracking algorithm

• An integration of computer vision, machine listening, and machine learning

• The only system that can annotate tennis game at such a detailed level

摘要

•Fully automatic annotation of real-world tennis video•State-of-the-art tennis ball tracking algorithm•An integration of computer vision, machine listening, and machine learning•The only system that can annotate tennis game at such a detailed level

论文关键词：Tennis annotation,Object tracking,Audio event classification,Sequence labelling,Structured output learning,Hidden Markov model

论文评审过程：Received 17 September 2013, Revised 7 June 2014, Accepted 4 August 2014, Available online 11 August 2014.

论文官网地址：https://doi.org/10.1016/j.imavis.2014.08.004