A low-cost performance analysis and coaching system for tennis

ABSTRACT In this paper we present an innovative and novel system fortennis performance analysis that allows coaches to reviewa player’s match performance and provide detailed audio-visual feedback to the athlete. The system utilises a simplenetwork of low-cost IP cameras that encompass the tenniscourt. A graphical user interface provides coaches with videoplayback feeds from multiple viewpoints, a range of intuitivetools for 2D and 3D annotation, real-time game statisticsand the facility for a coach to record audio commentary.This system is specifically designed with non-professionalsports clubs in mind, with an emphasis on low-cost equip-ment. While we focus on tennis in this work, we believe oursystem can be generalised to a wide range of other sports. Categories and Subject Descriptors I.4.8 [IMAGE PROCESSING AND COMPUTER VI-SION]: Scene Analysis—Object recognition, Tracking; H.3.3[Information Storage and Retrieval]: Information Searchand Retrieval General Terms Design, Experimentation, Human Factors

[1]  Takeo Kanade,et al.  A Multiple-Baseline Stereo , 1993, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Noel E. O'Connor,et al.  TennisSense: A platform for extracting semantic information from multi-camera tennis data , 2009, 2009 16th International Conference on Digital Signal Processing.

[3]  Xiaojun Wu,et al.  Real-time dynamic 3-D object shape reconstruction and high-fidelity texture mapping for 3-D video , 2004, IEEE Transactions on Circuits and Systems for Video Technology.

[4]  Noel E. O'Connor,et al.  A comparative evaluation of interactive segmentation algorithms , 2010, Pattern Recognit..

[5]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[6]  Richard I. Hartley,et al.  In Defense of the Eight-Point Algorithm , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Yang Wang,et al.  Three-dimensional object reconstruction from orthogonal projections , 1975, Pattern Recognit..

[8]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[9]  Noel E. O'Connor,et al.  Vision-based analysis of pedestrian traffic data , 2008, 2008 International Workshop on Content-Based Multimedia Indexing.