Action Recognition in Sports Videos Using Stacked Auto Encoder and HOG3D Features
- 18 Downloads
Sports analytics is an emerging area of research with applications to personalized training and entertainment. In this work, an approach for sports action recognition using stacked autoencoder and HOG3D features is presented. We demonstrate that actions in sports videos can be recognized by 2D interpretation of HOG3D features, extracted from the bounding box of the player as input to a deep learning model. The ability of a stacked autoencoder to learn the underlying global patterns associated with each action is used to recognize human actions. We demonstrate the efficacy of the proposed classification system for action recognition on ACASVA dataset.
KeywordsStacked autoencoder (SAE) Sports action recognition HOG3D features
- 2.Simard, P.Y., D. Steinkraus, J.C. Platt. 2003. Best practices for convolutional neural networks applied to visual document analysis. In ICDAR’03 Proceedings of the Seventh International Conference on Document Analysis and Recognition, vol. 2, 958, Washington, DC, USA: IEEE Computer Society. http://dl.acm.org/citation.cfm?id=938980.939477.
- 3.Ijjina, Paul E., and Mohan, Krishna C. 2017. Human Behavioral Analysis Using Evolutionary Algorithms and Deep Learning. Chap. 7, 165–186. Wiley. https://doi.org/10.1002/9781119242963.ch7.
- 6.Klaser, A., M. Marszalek, and C. Schmid. 2008. A Spatio-Temporal Descriptor Based on D-Gradients. In BMVC 2008—19th British Machine Vision Conference, vol. 275, eds. M. Everingham, C. Needham, and R. Fraile, 1–10. UK: British Machine Vision Association, Leeds. https://hal.inria.fr/inria-00514853.
- 8.De Campos, T., M. Barnard, Mikolajczyk, K., Kittler, J., Yan, F., Christmas, W., Windridge, D. 2011. An Evaluation of Bags-of-Words and Spatio-Temporal Shapes for Action Recognition. In IEEE Workshop on Applications of Computer Vision (WACV), 344–351. https://doi.org/10.1109/WACV.2011.5711524.
- 9.FarajiDavar, N., T. De Campos, J. Kittler, F. Yan. 2011. Transductive Transfer Learning for Action Recognition in Tennis Games. In IEEE International Conference on Computer Vision Workshops (ICCV Workshops), 1548–1553.Google Scholar
- 10.Farajidavar, N., T. De Campos, D. Windridge, J. Kittler, W. Christmas. 2011. Domain Adaptation in the Context of Sport Video Action Recognition. In Domain Adaptation Workshop, in Conjunction with NIPS, 1–6.Google Scholar
- 11.Tran, D., L. Torresani. 2013. EXMOVES: Classifier-Based Features for Scalable Action Recognition. CoRR abs/1312.5785.Google Scholar
- 12.FarajiDavar, N., De Campos, T. 2018. Adaptive Cognition for Automated Sports Video Annotation (ACASVA). Accessed 5 Oct 2018. http://www.cvssp.org/acasva/Downloads.