Abstract
A method for temporal segmentation and recognition of team activities in sports, based on a new activity feature extraction, is presented. Given the positions of team players from a plan view of the playground at any given time, we generate a smooth distribution on the whole playground, termed the position distribution of the team. Computing the position distribution for each frame provides a sequence of distributions, which we process to extract motion features for activity recognition. We can classify six different team activities in European handball and eight different team activities in field hockey datasets. The field hockey dataset is a new, large and challenging dataset that is presented for the first time for continuous segmentation of team activities. Our approach is different from other trajectory-based methods. These methods extract activity features using the explicitly defined trajectories, where the players have specific positions. In our work, given the specific positions of the team players at a frame, we construct a position distribution for the team on the whole playground and process the sequence of position distribution images to extract activity features. Extensive evaluation and results show that our approach is effective.
Similar content being viewed by others
References
Aggarwal, J.K., Ryoo, M.S.: Human activity analysis: a review. ACM Comput. Surv. 43(3), 16 (2011)
Kong, Y., Zhang, X., Wei, Q., Hu, W., Jia, Y.: Group action recognition in soccer videos. In: Proceedings of ICPR, pp. 1–4 (2008)
Kong, Y., Hu, W., Zhang, X., Wang, H., Jia, Y.: Learning group activity in soccer videos from local motion. In: Proceedings of ACCV, pp. 103–112 (2009)
Wei, Q., Zhang, X., Kong, Y., Hu, W., Ling, H.: Group action recognition using space time interest points. Int. Symp. Adv. Vis. Comput. 2, 757–766 (2009)
Li, R., Chellappa, R., Zhou, S.K.: Learning multi-modal densities on discriminative temporal interaction manifold for group activity recognition. In: CVPR, pp. 2450–2457 (2009)
Swears, E., Hoogs, A.: Learning and recognizing complex multi-agent activities with applications to american football plays. In: IEEE Workshop on Applications of Computer Vision (WACV), pp. 409–416 (2012)
Ibrahim, M.S., Deng, Z., Muralidharan, S., Vahdat, A., Mori, G.: A hierarchical deep temporal model for group activity recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1971–1980 (2016)
Shu, T., Todorovic, S., Zhu, S.-C.: CERN: Confidence-energy recurrent network for group activity recognition. In: IEEE Conference on Computer Vision Pattern Recognition (To appear in proc. of CVPR 2017) (2017)
Fani, M., Neher, H., Clausi, D.A., Wong, A., Zelek, J.: Hockey action recognition via integrated stacked hourglass network. In: IEEE International Workshop on Computer Vision in Sports at CVPR (2017)
Tsunoda, T., Komori, Y., Matsugu, M., Harada, T.: Football action recognition via hierarchical LSTM. In: IEEE International Workshop on Computer Vision in Sports at CVPR (2017)
Intille, S.S., Bobick, A.F.: Recognizing planned, multiperson action. CVIU 81(3), 414–445 (2001)
Blunsden, S., Fisher, R.B., Andrade, E.L.: Recognition of coordinated multi agent activities, the individual vs the group. In: ECCV Workshop on Computer Vision Based Analysis in Sport Environments (CVBASE), pp. 61–70 (2006)
Perse, M., Kristan, M., Kovacic, S., Vuckovic, G., Pers, J.: A trajectory-based analysis of coordinated team activity in a basketball game. CVIU 113(5), 612–621 (2009)
Perse, M., Kristan, M., Pers, J., Music, G., Vuckovic, G., Kovacic, S.: Analysis of multi-agent activity using petri nets. Pattern Recognit. 43(4), 1491–1501 (2010)
Hervieu, A., Bouthemy, P., Cadre, J.P.L.: Trajectory-based handball video understanding. In: International Conference on Image and Video Retrieval, vol. 43, pp. 1–8 (2009)
Dao, M.S., Masui, K., Babaguchi, N.: Event tactic analysis in sports video using spatio-temporal pattern. In: Proceedings of ICIP, pp. 1497–1500 (2010)
Li, R., Chellappa, R.: Recognizing offensive strategies from football videos. In: Proceedings of ICIP, pp. 4585–4588 (2010)
Varadarajan, J., Atmosukarto, I., Ahuja, S., Ghanem, B., Ahuja, N.: A topic model approach to represent and classify american football plays. In: British Machine Vision Conference (BMVC) (2013)
Montoliu, R., Martin-Felez, R., Torres-Sospedra, J., Rodrguez-Prez, S.: ATM-based analysis and recognition of handball team activities. Neurocomputing 150, 189–199 (2015)
CVBASE’06 dataset, in workshop on computer vision based analysis in sport environments. http://vision.fe.uni-lj.si/cvbase06/downloads.html (2006)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems Conference, pp. 1097–1105 (2012)
Direkoglu, C., O’Connor, N.E.: Team behavior analysis in sports using the Poisson equation. In: IEEE International Conference on Image Processing (ICIP), pp. 2693–2696 (2012)
Direkoglu, C., O’Connor, N.E.: Team activity recognition in sports. In: European Conference on Computer Vision (ECCV), vol. 7578, pp. 69–83 (2012)
Braun, M.: Differential Equations and Their Applications. Springer, Berlin (1993)
Simchony, T., Chellappa, R., Shao, M.: Direct analytical methods for solving Poisson equations in computer vision problems. T-PAMI 12(5), 435–446 (1990)
Horn, B.K.P., Schunck, B.G.: Determining optical flow. Artif. Intell. 17, 185–203 (1981)
Kim, K., Grundmann, M., Shamir, A., Matthews, I., Hodgins, J., Essa, I.: Motion fields to predict play evolution in dynamic sport scenes. In: CVPR, pp. 840–847 (2010)
Efros, A.A., Berg, A.C., Berg, E.C., Mori, G., Malik, J.: Recognizing action at a distance. In: Proceedings of ICCV, pp. 726–733 (2003)
Janez, M.K., Kovacic, S.: Multiple interacting targets tracking with application to team sports. In: International Symposium on Image and Signal Processing and Analysis, pp. 322–327 (2005)
Ward, J.A., Lukowicz, P., Gellersen, H.W.: Performance metrics for activity recognition. ACM Trans. Intell. Syst. Technol. 2(1), 6 (2011)
GPSports Systems Limited, Australia. http://gpsports.com/
Statsports Company, Northern Ireland. http://www.statsports.ie/
MacLeod, H., Morris, J., Nevill, A., Sunderland, C.: The validity of a non-differential global positioning system for assessing player movement patterns in field hockey. J. Sport Sci. 27(2), 121–128 (2009)
Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)
Chen, J., Liu, Y.: Locally linear embedding: a survey. Artif. Intell. Rev. 36(1), 29–48 (2011)
Onderwater, M.: Outlier Detection Matlab Toolbox. http://www.martijn-onderwater.nl/bmi-thesis/
Acknowledgements
This work is supported by Science Foundation Ireland under Grant 07/CE/I114. The authors would like to acknowledge Disney Research Pittsburgh for their help in constructing the camera network around the field hockey playground in Ireland. We also would like to thank Statsports for supplying us GPS sensors, and finally, we thank Irish Hockey Association for their collaboration to collect the field hockey dataset.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Direkoǧlu, C., O’Connor, N.E. Temporal segmentation and recognition of team activities in sports. Machine Vision and Applications 29, 891–913 (2018). https://doi.org/10.1007/s00138-018-0944-9
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-018-0944-9