ABSTRACT
In this paper, we propose a distributed sensing algorithm that integrates players' trajectories observed from multiple cameras during a football game. Football scenes present several situations where players occlude each other, thus generating ambiguities that may lead to tracking failures. The integration of tracks from different views may help disambiguate players tracks. The proposed approach first uses homography to synthesize the ground plane virtual top-view and then transforms players locations from the camera image plane to the ground plane. Finally, the tracking on the ground plane is performed applying the graph theory. We demonstrate the results of our algorithm on football scenario.
- K. Nummiaro, E. Koller-Meier, T. Svoboda, D. Roth, L.J. Van Gool, Color-Based Object Tracking in Multi-camera Environments, DAGM-Symposium, pp. 591--599, 2003.Google Scholar
- W. Du, J-B. Hayet, J. Piater and J. Verly, Collaborative Multi-Camera Tracking of Athletes in Team Sports, Workshop on Computer Vision Based Analysis in Sport Environments (CVBASE), pp. 2--13, 2006.Google Scholar
- T. Misu, S. Gohshi, Y. Izumi, Y. Fujita and M. Naemura, Robust Tracking of Athletes Using Multiple Features of Multiple Views, Proc. of Conf. WSCG DBLP:conf/wscg/MisuGIFN04, pp. 285--292, 2004.Google Scholar
- Y.L Meneses, P. Roduit, F. Luisier and J. Jacot, Trajectory Analisis fopr Sport and Video Surveillance, Electronic Letters on Comp. Vision and Image Analisis, vol. 5, n. 3, pp. 148--156, 2005.Google Scholar
- C. Piciarelli, G.L Foresti and L. Snidaro, Trajectory Clustering and its Applications for Video Surveillance, IEEE Conf. on Advanced Video and Signal Based Surveillance (AVSS 2005), pp. 40--45, Sept. 2005Google ScholarCross Ref
- Y.A Sheikh and M. Shah, Trajectory Association across Multiple Airborne Cameras, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 30, no. 2, pp. 361--367, Feb. 2008 Google ScholarDigital Library
- I.N. Junejo and H. Foroosh, Trajectory Rectification and Path Modeling for Video Surveillance, IEEE 11th Intern. Conf. on Computer Vision (ICCV 2007), pp.1--7, 14-21 Oct. 2007.Google ScholarCross Ref
- W. Du and J. Piater, Multi-view tracking using sequential belief propagation, Proc. of Asian Conference on Computer Vision (ACCV'06), 2006. Google ScholarDigital Library
- T. Hideki, M. Jun and S. Yoshiaki, Optical Flow-Based Person Tracking by Multiple Cameras, IEEE Proc. of Multisensor Fusion and Integration in Intelligent Systems, pp. 91--96, 2001.Google Scholar
- T. Zhao, M. Aggarwal, R. Kumar and Harpreet Sawhney, Real-Time Wide Area Multi-Camera Stereo Tracking, IEEE Proc. of the Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05), vol. 1, pp. 976--983, 2005. Google ScholarDigital Library
- S.L. Dockstader and A.M. Tekalp, Multiple Camera Tracking of interacting and occluded human motion, Proc. of IEEE, vol. 89, no. 10, pp. 1441--1455, 2001.Google ScholarCross Ref
- J.E. Hopcroft and R.M. Karp, An n 2.5 Algorithm for Maximum Matchings in Bipartite Graphs, SIAM J. Computing, vol. 2, n. 4, pp. 225--230, 1973.Google Scholar
- S. Intille and A. Bobick, Visual tracking using closed-worlds, Technical report, MIT Media Laboratory, 1995.Google Scholar
- T. Taki, J. Hasegawa and T. Fukumura, Development of motion analysis system for quantitative evaluation of team work in soccer game, Proc. of International Conference on Image Processing, pp. 815-818, 1996.Google ScholarCross Ref
- H. Kim and Y. Seo and S. Choi and K.S. Hong, Where are the ball and players? Soccer game analysis with color-based tracking and image mosaic, Lecture Notes in Computer Science, vol. 1311/1997, pp. 976--983, 1997. Google ScholarDigital Library
- C. Needham and R. Boyle, Tracking multiple sports players through occlusion, congestion and scale, British Machine Vision Conference, pp. 93--102, 2001.Google ScholarCross Ref
- J. Kang and I. Cohen and G. Medioni, Tracking people in crowded scenes across multiple cameras, Asian Conference on Computer Vision, 2004.Google Scholar
- S. Iwase and Hideo Saito, Parallel Tracking of All Soccer Players by Integrating Detected Positions in Multiple View Images, Proc. of the Pattern Recognition, 17th International Conference on (ICPR'04), vol.4, pp. 751--754, 2004. Google ScholarDigital Library
- M. Xu and J. Orwell and L. Lowey and D. Thirde, Architecture and algorithms for tracking football players with multiple cameras, IEEE Proc. Vision, Image and Signal Processing, vol. 152, no.2, pp. 232--241, 2005.Google ScholarCross Ref
- P. J. Figueroa, N. J. Leite and R. M. Barros, Tracking soccer players aiming their kinematical motion analysis, Journal of Computer Vision and Image Understanding, vol. 101, no. 2, pp. 122--135, Feb. 2006. Google ScholarDigital Library
- G. Zhu, Q. Huang, C. Xu, Y. Rui, S. Jiang, W. Gao and H. Yao, Trajectory based event tactics analysis in broadcast sports video, Proc. of the 15th international conference on Multimedia, pp. 58--67, New York, NY, USA, 2007. Google ScholarDigital Library
- M. Beetz, S. Gedikli, J. Bandouch, B. Kirchlechner, N. von Hoyningen-Huene and A. Perzylo, Visually Tracking Football Games Based on TV Broadcasts, International Joint Conference on Artificial Intelligence, pp. 2066--2071, 2007. Google ScholarDigital Library
- P. Spagnolo, T. D'Orazio, M. Leo and A. Distante, Moving object segmentation by background subtraction and temporal analysis, Image Vision Comput., vol. 24, no. 5, pp. 411--423, 2006. Google ScholarDigital Library
- Q. Cai and K. Aggarwal, Tracking human motion in structured environments using a distributed-camera system, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 21, pp. 1241--1247, 1999. Google ScholarDigital Library
- A.Utsumi and J. Ohya, Multiple-camera-based human tracking using non-synchronous observations, Proc. of 4th Asian Conference on Computer Vision (ACCV'00), pp. 1034--1039, Taipei, Taiwan, 2000.Google Scholar
- K. Kanatani, N. Ohta and Y. Kanazawa, Optimal homography computation with a reliability Measure, IEICE Trans. on Information and Systems. Special Issue on Machine Applications, vol. 7, pp. 1369--1374, July, 2000.Google Scholar
- G. Kayumbi and A. Cavallaro, Robust homography-based trajectory transformation for multi-camera scene analysis, Proc. IEEE Int. Conf. on Distributed Smart Cameras (ICDSC), sept. 2007.Google ScholarCross Ref
- K. Shafique and M. Shah, A noniterative Greedy Algorithm for Multiframe Point Correspondence, IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 27, no. 1, pp. 51--65, Jan. 2005. Google ScholarDigital Library
- R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Second ed. Cambridge University Press (U.K), 2004. Google ScholarDigital Library
Index Terms
- Distributed visual sensing for virtual top-view trajectory generation in football videos
Recommendations
A novel approach for tracking high speed skaters in sports using a panning camera
This paper presents a computer vision system for tracking high-speed non-rigid skaters over a larger rink in short track speed skating competitions. The outputs of the tracking system are spatio-temporal trajectories of the skaters which can be further ...
Synthesizing Free-Viewpoint Images from Multiple View Videos in Soccer Stadium
CGIV '06: Proceedings of the International Conference on Computer Graphics, Imaging and VisualisationWe propose a new method for synthesizing freeviewpoint images from multiple view videos in soccer stadium. The previous method[1] can synthesize virtual viewpoint images at only intermediate viewpoint between real cameras. The previous method estimates ...
Monocular omnidirectional visual odometry for outdoor ground vehicles
ICVS'08: Proceedings of the 6th international conference on Computer vision systemsThis paper describes an algorithm for visually computing the ego-motion of a vehicle relative to the road under the assumption of planar motion. The algorithm uses only images taken by a single omnidirectional camera mounted on the roof of the vehicle. ...
Comments