Abstract
Athlete detection and action recognition in sports video is a very challenging task due to the dynamic and cluttered background. Several attempts for automatic analysis focus on athletes in many sports videos have been made. However, taekwondo video analysis remains an unstudied field. In light of this, a novel framework for automatic techniques analysis in broadcast taekwondo video is proposed in this paper. For an input video, in the first stage, athlete tracking and body segmentation are done through a modified Structure Preserving Object Tracker. In the second stage, the de-noised frames which completely contain the body of analyzed athlete from video sequence, are trained by a deep learning network PCANet to predict the athlete action of each single frame. As one technique is composed of many consecutive actions and each action corresponds a video frame, focusing on video sequences to achieve techniques analysis makes sense. In the last stage, linear SVM is used with the predicted action frames to get a techniques classifier. To evaluate the performance of the proposed framework, extensive experiments on real broadcast taekwondo video dataset are provided. The results show that the proposed method achieves state-of-the-art results for complex techniques analysis in taekwondo video.
Similar content being viewed by others
References
Afrouzian R, Seyedarabi H, Kasaei S (2016) Pose estimation of soccer players using multiple uncalibrated cameras. Multimedia Tools and Applications 75:6809–6827
Archana M, Kalaiselvi Geetha M (2016) An efficient ball and player detection in broadcast tennis video. Intell Syst Technol Appl 384:427–436
Chan TH, Jia K, Gao S et al (2015) PCANet: a simple deep learning baseline for image classification? IEEE Trans Image Process 24:5017–5032
Chen CM, Chen LH (2014) A novel method for slow motion replay detection in broadcast basketball video. Multimedia Tools and Applications 74:9573–9593
Chu WT, Wu JL (2008) Explicit semantic events detection and development of realistic applications for broadcasting baseball videos. Multimedia Tools and Applications 38:27–50
Crammer K, Dekel O, Keshet J et al (2006) Online passive-aggressive algorithms. J Mach Learn Res 7:551–585
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. Proceedings – 2005. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 I:886–893
Dao MS, Babaguchi N (2010) A new spatio-temporal method for event detection and personalized retrieval of sports video. Multimedia Tools and Applications 50:227–248
Duh D-J, Chang S-Y, Chen S-Y, Kan C-C (2013) Automatic broadcast soccer video analysis, player detection, and tracking based on color histogram. Intelligent Technologies and Engineering Systems. Springer New York, New York, pp 123–130
Everts I, van Gemert JC, Gevers T (2013) Evaluation of color STIPs for human action recognition. IEEE Conf Comput Vis Pattern Recognit 23:2850–2857
Fan R-E, Chang K-W, Hsieh C-J et al (2008) LIBLINEAR: a library for large linear classification. J Mach Learn Res 9:1871–1874
Farajidavar N, Campos T D, Kittler J, et al (2012) Transductive transfer learning for action recognition in tennis games. IEEE International Conference on Computer Vision Workshops: 1548–1553
Fathi A, Mori G (2008) Action recognition by mid-level motion features. IEEE International Conference on Computer Vision and Pattern Recognition: 1–8
Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition. IEEE Conf Comput Vis Pattern Recognit 2016:1933–1941
Felzenszwalb PF, Girshick RB, McAllester D et al (2010) Object detection with discriminatively trained part-based models. IEEE Trans Pattern Anal Mach Intell 32:1627–1645
Gastin PB, McLean O, Spittle M, Breed RVP (2013) Quantification of tackling demands in professional Australian football using integrated wearable athlete tracking technology. J Sci Med Sport 16:589–593
Ghasemzadeh H, Jafari R (2011) Coordination analysis of human movements with body sensor networks: a signal processing model to evaluate baseball swings. IEEE Sensors J 11:603–610
Gouwanda D, Senanayake SMNA (2008) Emerging trends of body-mounted sensors in sports and human gait analysis. 4th Kuala Lumpur International Conference on Biomedical Engineering :715–718
Kumar K, Prasad S (2010) Sports video summarization using priority curve algorithm. Int J Comput Sci Eng 2:2996–3002
Li H, Lin S, Zhang Y, Tao K (2007) Automatic video-based analysis of athlete action. Proceedings of 14th International conference on Image Analysis and Processing, ICIAP 2007 205–210
Li H, Tang J, Wu S et al (2010) Automatic detection and analysis of player action in moving background sports video sequences. IEEE Trans Circuits Syst Video Technol 20:351–364
Liu J, Carr P, Collins RT, Liu Y (2013) Tracking sports players with context-conditioned motion models. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 1830–1837
Ma S, Zhang J, Ikizler-Cinbis N, Sclaroff S (2013) Action Recognition and Localization by Hierarchical Space-Time Segments. Proceedings of the IEEE International Conference on Computer Vision, ICCV 2013:2744–2751
Mei T, Hua XS (2008) Structure and event mining in sports video with efficient mosaic. Multimedia Tools and Applications 40:89–110
Mendi E, Clemente HB, Bayrak C (2013) Sports video summarization based on motion analysis. Comput Electr Eng 39:790–796
Nitta N, Babaguchi N, Kitahashi T (2005) Generating semantic descriptions of broadcasted sports videos based on structures of sports games and TV programs. Multimedia Tools and Applications 25:59–83
Qian X, Wang H, Liu G, Hou X (2012) HMM based soccer video event detection using enhanced mid-level semantic. Multimedia Tools and Applications 60:233–255
Roh MC, Christmas B, Kittler J, Lee SW (2008) Gesture spotting for low-resolution sports video annotation. Pattern Recogn 41:1124–1137
Simonyan K, Zisserman A (2015) Very Deep Convolutional Networks for Large-Scale Image Recognition. Proceedings of International Conference on Learning Representations ICRL 2015 1–14
Tao W, Liu T, Zheng R, Feng H (2012) Gait analysis using wearable sensors. Sensors 12:2255–2283
Tsochantaridis I, Joachims T, Hofmann T et al (2005) Large margin methods for structured and interdependent output variables. J Mach Learn Res 6:1453–1484
Vainstein J, Delrieux C, Maguitman A (2013) Action recognition in tennis videos using optical flow and conditional random fields. Argentine Symposium on Technology, AST 2013:152–162
Wang Z, Yu J, He Y, Guan T (2014) Affection arousal based highlight extraction for soccer video. Multimedia Tools and Applications 73:519–546
Xie X, Zaitsev Y, Velásquez-García LF et al (2014) Scalable, MEMS-enabled, vibrational tactile actuators for high resolution tactile displays. J Micromech Microeng 24:125014
Xie X, Zaitsev Y, Velásquez-García LF, et al (2014) Compact, scalable, high-resolution, MEMS-enabled tactile displays. Proceedings of Solid-State Sensors, Actuators, and Microsystems Workshop 127–130
Xing J, Ai H, Liu L, Lao S (2011) Multiple player tracking in sports video: a dual-mode two-way Bayesian inference approach with progressive observation modeling. IEEE Trans Image Process 20:1652–1667
Xu C, Wang J, Lu H, Zhang Y (2008) A novel framework for semantic annotation and personalized retrieval of sports video. IEEE Trans Multimedia 10:421–436
Zawbaa HM, El-Bendary N, Hassanien AE, Kim TH (2011) Machine learning-based soccer video summarization system. Communications in Computer and Information Science CCIS 263:19–28
Zhang L, Van Der Maaten L (2013) Structure preserving object tracking. Proc IEEE Conf Comput Vis Pattern Recognit 2013:1838–1845
Zhang L, Van Der Maaten L (2014) Preserving structure in model-free tracking. IEEE Trans Pattern Anal Mach Intell 36:756–769
Zhen X, Shao L, Tao D, Li X (2013) Embedding motion and structure features for action recognition. IEEE Trans Circuits Syst Video Technol 23:1182–1190
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kong, Y., Wei, Z. & Huang, S. Automatic analysis of complex athlete techniques in broadcast taekwondo video. Multimed Tools Appl 77, 13643–13660 (2018). https://doi.org/10.1007/s11042-017-4979-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-4979-0