Abstract
This paper presents us with a framework for the automatic player position detection (APPD) in the game of basketball. Court players are detected in the images broadcasted via television stations. In them, at any point of time, the view is from only one camera. This makes the detection process much more difficult. The player detection is based on the mixture of non-oriented pictorial structures. The detection of body parts is performed by the Support Vector Machine (SVM) algorithm. The results of these detections are combined together with constraints on their locations, which specify the position of one body part with respect to the parent body part. In order to train the whole model, we used a latent form of SVM called the latent SVM (LSVM). Such approach generated the statistical accuracy of about 82 %, which represents one of the best results in basketball player detection framework. Beside players, the algorithm detected a certain number of false positive objects. These are mostly people from the audience and the referees as well. This paper contains a simple and robust solution to remove them all, based on the play court boundaries and the histogram comparison. Separating players in different teams is done by k-means clustering. The inputs to this algorithm are saturation histograms calculated on the jerseys. A spatial transformation is determined by the detected play court boundaries and the actual court measures. Using this transformation, points representing the location of detected players in TV images are mapped to the actual location of players on the court, which was the main goal of our research. The proposed solution is sound and efficient. In addition, it is backed up by the experimental results obtained using the model of the actual footage of basketball games.
Similar content being viewed by others
References
Alahi A, Boursier Y, Jacques L, Vandergheynst P (2009) Sport players detection and tracking with a mixed network of planar and omnidirectional cameras. In: ACM/IEEE International conference on distributed smart cameras, pp 1–8
Amit Y, Trouve A (2007) POP: patchwork of parts models for object recognition. Int J Comput Vis 75(2):267–282
Andrews S, Tsochantaridis I, Hofmann T (2003) Support vector machines for multiple-instance learning. In: Advances in neural information processing systems, pp 561–568
Bar-Hillel A, Weinshall D (2008) Efficient learning of relational object class models. Int J Comput Vis 77(1):175–198
Bernstein E, Amit Y (2005) Part-based statistical models for object classification and detection. In: IEEE conference on computer vision and pattern recognition
Bishop CM (2006) Pattern recognition and machine learning. Springer, New York
Bourdev L, Malik J (2009) Poselets: Body part detectors trained using 3d human pose annotations. In: International conference on computer vision (ICCV), pp 1365–1372
Cai Y, de Freitas N, Little JJ (2006) Robust visual tracking for multiple targets. In: European conference on computer vision (ECCV)
Chang MH, Tien MC, Wu JL (2009) WOW: wild open warning for broadcast basketball video based on player trajectory. In: ACM International conference on multimedia, pp 821–824
Cootes T, Edwards G, Taylor C (2001) Active appearance models. IEEE Trans Pattern Anal Mach Intell 23(6):681–685
Coughlan J, Yuille A, English C, Show D (2000) Efficient deformable template detection and localization without user initialization. Comput Vis Image Under 78(3):303–319
Crandall D, Felzenszwalb P, Huttenlocher D (2005) Spatial priors for part-based recognition using statistical models. Comput Vis Pattern Recogn (CVPR) 1:10–17
Dalal N, Triggs B (2005) Histogram of oriented gradients for human detection. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 886–893
Daniyal F, Taj M, Cavallaro A (2010) Content and task-based view selection from multiple video streams. Multimed Tools Appl 46:235–258
Ekin A, Tekalp AM (2003) Robust dominant color region detection with applications to sports video analysis. In: International conference on image processing
Felzenszwalb P, Girshick R, McAllester D, Ramanan D (2010) Object detection with discriminatively trained part based models. IEEE Trans Pattern Anal Mach Intell 32(9):1627–1645
Felzenszwalb P, Huttenlocher D (2005) Pictorial structures for object recognition. Int J Comput Vis 61(1):55–79
Fergus V, Perona P, Ziserman A (2003) Object class recognition by unsupervised scale-invariant learning. In: IEEE computer society conference on computer vision and pattern recognition
Holub A, Perona P (2005) A discriminative framework for modelling object classes. In: IEEE conference on computer vision and pattern recognition (CVPR)
Huang CL, Shih HC, Chen CL (2006) Shot and scoring events identification of basketball videos. In: International conference on multimedia and expo, pp 1885–1888
Ivankovic Z, Rackovic M, Markoski B, Radosav D, Ivkovic M (2010) Appliance of neural networks in basketball scouting. Acta Polytech Hungarica 7(4):167–180
Ke Y, Sukthankar R (2004) PCA-SIFT: a more disinctive representation for local image descriptors. In: IEEE conference on computer vision and pattern recognition
Leibe B, Leonardis A, Schiele B (2008) Robust object detection with interleaved categorization and segmentation. Int J Comput Vis 77(1):259–289
Lifang W, Xiuli H, Hao C, Wei S (2007) Shot segmentation and classification in basketball videos. In: Intelligent information hiding and multimedia signal processing, pp 539–542
Lu WL, Ting JA, Murphy KP, Little JJ (2011) Identifying players in broadcast sports videos using conditional random fields. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 3249–3256
Markoski B, Pecev P, Ratgeber L, Ivkovic M, Ivankovic Z (2011) A new approach to decision making in basketball – BBFBR program. Acta Polytech Hungarica 8(6):111–130
Okuma K, Taleghani A, Freitas N, Little JJ, Lowe DG (2004) A boosted particle filter: multitarget detectionand tracking. In: European conference of computer vision (ECCV)
Panagiotakis C, Ramasso E, Tziritas G, Rombaut M, Pellerin D (2008) Shape-based individual/group detection for sport videos categorization. Int J Pattern Recogn Artif Intell (IJPRAI) 22(6):1187–1213
Pele O, Werman M (2010) The quadratic-chi histogram distance family. In: European conference on computer vision (ECCV), pp 749–762
Perše M, Kristan M, Kovačič S, Vučkovič G, Perš J (2009) A trajectory-based analysis of coordinated team activity in a basketball game. Comput Vis Image Under 113(5):612–621
Quattoni A, Wang S, Morency L, Collins M, Darrell T (2007) Hidden conditional random fields. IEEE Trans Pattern Anal Mach Intell 29(10):1848–1852
Rabaud V, Belongie S (2006) Counting crowded moving objects. In: 18th IEEE international conference on computer and pattern recognition, pp 705–711
Schumaker R, Soliman O, Chen H (2010) Sports data mining. Springer, New York
Szeliski R (2010) Computer vision: algorithms and applications. Springer, New York
Theron R, Casares L (2010) Visual analysis of time-motion in basketball games. In: X International symposium on smart graphics, pp 196–207
Viola P, Jones M (2004) Robust real-time face detection. Int J Comput Vis 57(2):137–154
Viola P, Platt J, Zhang C (2005) Multiple instance boosting for object detection. Adv Neural Inf Process Syst 18:1417
Wu L, Gong Y, Yuan X, Zhang X, Cao L (2012) Semantic aware sport image resizing jointly using seam carving and warping. Multimed Tools Appl. doi:10.1007/s11042-012-1002-7
Xinghao J, Tanfeng S, Fu G (2011) Multi-scale image semantic recognition with hierarchical visual vocabulary. Comput Sci Inf Syst 8(3):931–951
Yang Y, Ramanan D (2011) Articulated pose estimation using flexible mixture of parts. Comput Vis Pattern Recogn (CVPR) 1385–1392
Zhu X, Wu X, Elmagarmid AK, Feng Z, Wu L (2005) Video data mining: semantic indexing and event detection from the association perspective. IEEE Trans Knowl Data Eng 17(5):665–677
Acknowledgements
Research was partially supported by the Ministry of Science and Technological Development of Republic of Serbia by Grant 171039 and through project no. III47003 “Infrastructure for technology enhanced learning in Serbia”.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ivankovic, Z., Rackovic, M. & Ivkovic, M. Automatic player position detection in basketball games. Multimed Tools Appl 72, 2741–2767 (2014). https://doi.org/10.1007/s11042-013-1580-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-013-1580-z