Abstract
Motion Vectors (MV) indicate the motion characteristics between two video frames, and has been widely used in the content-based sports video analysis. Previous works on sports video analysis have proved the effectiveness and efficiency of the MV-based methods. However, in the tennis video, the MV-based methods are seldom applied because the motion represented by MV is greatly deformed relative to the player’s true movement due to the camera’s diagonal shooting. In this paper, an algorithm of MV transformation is proposed to revise the deformed MV using a pinhole camera model. With the transformed MVs, we generate the temporal feature curves and employ Hidden Markov Models to classify two types of player’s basic actions. Evaluation on four hours live tennis videos shows very encouraging results.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Duan, L.Y., Xu, M., Chua, T.S., Tian, Q., Xu, C.S.: A Mid-level Representation Framework for Semantic Sports Video Analysis. In: Proc. of the 11th ACM International Conference on Multimedia, Berkeley, CA, USA, November 2-8, pp. 33–44 (2003)
Ma, Y.F., Zhang, H.J.: A New Perceived Motion based Shot Content Representation. In: Proc. of IEEE International Conference on Image Processing, Thessaloniki, Greece, October 7-10, vol. 3, pp. 426–429 (2001)
Xu, G., Ma, Y.F., Zhang, H.J., Yang, S.Q.: Motion based Event Recognition Using HMM. In: Proc. of the 16th International Conference on Pattern Recognition, Quebec, Canada, August 11-15, vol. 2, pp. 831–834 (2002)
Sudhir, G., Lee, J.C.M., Jain, A.K.: Automatic Classification of Tennis Video for High-Level Content-Based Retrieval. In: Proc. of 1998 International Workshop on Content-Based Access of Image and Video Databases, Bombay, India, January 03-03, pp. 81–90 (1998)
Pingali, G.S., Jean, Y., Carlbom, I.: Real Time Tracking for Enhanced Tennis Broadcasts. In: Proc. of1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Santa Barbara, CA, USA, June 23-25, pp. 260–265 (1998)
Miyamori, H.: Improving Accuracy in Behaviour Identification for Content-based Retrieval by Using Audio and Video Information. In: Proc. of the 16th International Conference on Pattern Recognition, Quebec, Canada, August 11-15, vol. 2, pp. 826–830 (2002)
Di, H.J., Wang, L., Xu, G.Y.: A Three-step Technique of Robust Line Detection with Modified Hough Transform. In: Proc. of SPIE Symposium on Multispectral Image Processing and Pattern Recognition, Beijing, China, October 20-22, pp. 835–838 (2003)
Rabiner, L.R., Juang, B.H.: An Introduction to Hidden Markov Models. IEEE Acoustics, Speech and Signal Processing Magzine 3, 4–16 (1986)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, P., Cai, R., Yang, SQ. (2004). Tennis Video Analysis Based on Transformed Motion Vectors. In: Enser, P., Kompatsiaris, Y., O’Connor, N.E., Smeaton, A.F., Smeulders, A.W.M. (eds) Image and Video Retrieval. CIVR 2004. Lecture Notes in Computer Science, vol 3115. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-27814-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-540-27814-6_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22539-3
Online ISBN: 978-3-540-27814-6
eBook Packages: Springer Book Archive