Abstract
In this chapter we propose a method for automatic classification of five different sports types. The approach is based only on occupancy heatmaps produced from position data and is robust to detection noise. To overcome privacy issues when capturing video in public sports arenas we use thermal imaging only. This image modality also facilitates easier detection of humans; the detection algorithm is based on automatic thresholding of the image. After a few occlusion handling procedures, the positions of people on the court are calculated using homography. Heatmaps are produced by summarising Gaussian distributions representing people over 10-minute periods. Before classification the heatmaps are projected to a low-dimensional discriminative space using the principle of Fisherfaces. We test our approach on 2 weeks of video and get promising results with a correct classification of 89.64 %. In addition, we get correct classification on a publicly available handball dataset.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Barris S, Button C (2008) A review of vision-based motion analysis in sport. Sports Med 38(12):1025–1043
Belhumeur P, Hespanha J, Kriegman D (1997) Eigenfaces vs. Fisherfaces: recognition using class specific linear projection. PAMI 19(7):711–720. doi:10.1109/34.598228
Bialkowski A, Lucey P, Carr P, Denman S, Matthews I, Sridharan S (2013) Recognising team activities from noisy data. In: IEEE conference on computer vision and pattern recognition workshops. doi:10.1109/CVPRW.2013.143
Duda RO, Hart PE, Stork DG (2001) Pattern classification, 2nd edn. Wiley-Interscience, New York
Gade R, Moeslund TB (2013) Thermal cameras and applications: a survey. Mach Vis Appl. doi:10.1007/s00138-013-0570-5
Gade R, Jørgensen A, Moeslund TB (2012) Occupancy analysis of sports arenas using thermal imaging. In: Proceedings of the international conference on computer vision and applications
Gade R, Jørgensen A, Moeslund TB (2013) Long-term occupancy analysis using graph-based optimisation in thermal imagery. In: CVPR
Gibert X, Li H, Doermann D (2003) Sports video classification using HMMS. In: International conference on multimedia and expo (ICME). doi:10.1109/ICME.2003.1221624
Janez Pers MB, Vuckovic G (2006) CVBASE 06 dataset. http://vision.fe.uni-lj.si/cvbase06/dataset.html
Kapur J, Sahoo P, Wong A (1985) A new method for gray-level picture thresholding using the entropy of the histogram. Comput Vis Graph Image Process 29(3):273–285. doi:10.1016/0734-189X(85)90125-2. http://www.sciencedirect.com/science/article/pii/0734189X85901252
Krishna Mohan C, Yegnanarayana B (2010) Classification of sport videos using edge-based features and autoassociative neural network models. Signal, Image Video Process 4:61–73
Lee JY, Hoff W (2007) Activity identification utilizing data mining techniques. In: IEEE workshop on motion and video computing (WMVC). doi:10.1109/WMVC.2007.4
Li R, Chellappa R (2010) Recognizing offensive strategies from football videos. In: IEEE international conference on image processing
Li R, Chellappa R, Zhou S (2009) Learning multi-modal densities on discriminative temporal interaction manifold for group activity recognition. In: IEEE conference on computer vision and pattern recognition
Li L, Zhang N, Duan LY, Huang Q, Du J, Guan L (2009) Automatic sports genre categorization and view-type classification over large-scale dataset. In: 17th ACM international conference on multimedia (MM). doi:10.1145/1631272.1631380
Mutchima P, Sanguansat P (2012) TF-RNF: a novel term weighting scheme for sports video classification. In: IEEE international conference on signal processing, communication and computing (ICSPCC). doi:10.1109/ICSPCC.2012.6335651
Sigari M, Sureshjani S, Soltanian-Zadeh H (2011) Sport video classification using an ensemble classifier. In: 7th Iranian machine vision and image processing (MVIP). doi:10.1109/IranianMVIP.2011.6121538
Steiner H, Butzke M (1988) CASA computer aided sports analysis. In: Krause B, Schreiner A (eds) Hector. Springer, Berlin, pp 182–185
Varadarajan J, Atmosukarto I, Ahuja S, Ghanem B, Ahujad N (2013) A topic model approach to representing and classifying football plays. In: British machine vision conference
Wang J, Xu C, Chng E (2006) Automatic sports video genre classification using Pseudo-2D-HMM. In: 18th international conference on pattern recognition (ICPR). doi:10.1109/ICPR.2006.308
Wang DH, Tian Q, Gao S, Sung WK (2004) News sports video shot classification with sports play field and motion features. In: International conference on image processing (ICIP). doi:10.1109/ICIP.2004.1421545
Watcharapinchai N, Aramvith S, Siddhichai S, Marukatat S (2007) A discriminant approach to sports video classification. In: International symposium on communications and information technologies (ISCIT). doi:10.1109/ISCIT.2007.4392081
Xu M, Park M, Luo S, Jin J (2008) Comparison analysis on supervised learning based solutions for sports video categorization. In: IEEE 10th workshop on multimedia signal processing. doi:10.1109/MMSP.2008.4665134
Yuan Y, Wan C (2004) The application of edge feature in automatic sports genre classification. In: IEEE conference on cybernetics and intelligent systems. doi:10.1109/ICCIS.2004.1460749
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this chapter
Cite this chapter
Gade, R., Moeslund, T.B. (2014). Classification of Sports Types Using Thermal Imagery. In: Moeslund, T., Thomas, G., Hilton, A. (eds) Computer Vision in Sports. Advances in Computer Vision and Pattern Recognition. Springer, Cham. https://doi.org/10.1007/978-3-319-09396-3_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-09396-3_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09395-6
Online ISBN: 978-3-319-09396-3
eBook Packages: Computer ScienceComputer Science (R0)