Action Recognition in Tennis Videos using Optical Flow and Conditional Random Fields
F. Manera, Jonathan Vainstein, Claudio Augusto Delrieux, Ana Gabriela Maguitman, Baha Blanca · 2013
The aim of Action Recognition is the automated analysis and interpretation of events in video sequences. As result of the ap- plications that can be developed, and the widespread availability and popularization of digital video (security cameras, monitoring, social net- works, among many other), this area is currently the focus of a strong and wide research interest in various domains such as video security, human- computer interaction, patient monitoring and video retrieval, among oth- ers. Our long-term goal is to develop automatic action identication in video sequences using Conditional Random Fields (CRFs). In this work we focus, as a case of study, in the identication of a limited set of ten- nis shots during tennis matches. Three challenges have been addressed: player tracking, player movements representation and action recognition. Video processing techniques are used to generate textual tags in specic frames, and then the CRFs are used as a classier to recognise the ac- tions performed in those frames. The preliminary results appear to be quite promising.