DOI QR코드

DOI QR Code

Soccer Ball Tracking Robust Against Occlusion

가려짐에 강인한 축구공 추적

  • Lee, Kwon (School of Electrical & Electronic Engineering at Yonsei University) ;
  • Lee, Chulhee (School of Electrical & Electronic Engineering at Yonsei University)
  • 이권 (연세대학교 전기전자공학과) ;
  • 이철희 (연세대학교 전기전자공학과)
  • Received : 2012.07.30
  • Accepted : 2012.11.20
  • Published : 2012.11.30

Abstract

In this paper, we propose a ball tracking algorithm robust against occlusion in broadcasting soccer video sequences. Soccer ball tracking is a challenging task due to occlusion, fast motion and fast direction changes. Many works have been proposed based on ball trajectory. However, this approach requires heavy computational complexity. We propose a ball tracking algorithm with occlusion handling capability. Initial ball location is calculated using the circular hough transform. Then, the ball is tracked using template matching. Occlusion is handled by matching score. In occlusion cases, we generate a set of ball candidates. The ball candidates which exist in the previous frame were removed. On the other hand, the new appearing candidate is determined as the ball. Experiments with several broadcasting soccer video sequences show that the proposed method efficiently handles the occlusion cases.

본 논문에서는 축구 방송 영상에서 가려짐에 강인한 축구공 추적 알고리즘을 제안한다. 축구공은 가려짐, 축구공의 빠른 움직임 그리고 빠른 방향 전환 등으로 인해 추적이 어렵다. 기존의 방법들은 대부분 각각의 영상에서 축구공 후보들을 찾고 가능한 모든 경로를 예측하여 최적의 축구공 경로를 찾는 방식으로 축구공을 추적하였으나 이러한 방식은 연산량이 많아 실시간 축구공 추적에 적합하지 않다. 본 논문에서는 Circular Hough Transform을 이용하여 초기 축구공의 위치를 찾아내고, 이전 프레임의 축구공 템플릿을 이용하여 축구공을 추적하고 가려짐 상황에서는 가려짐 처리 알고리즘을 적용한다. 축구공 추적을 위하여, 매칭 스코어를 이용하여 축구공의 가려짐 상황을 판단한다. 가려짐 상태에서 축구공 후보들을 찾고 이전 프레임과의 매칭을 통해 이전 프레임에 존재하는 축구공 후보들은 축구공이 아니며, 새롭게 나타나는 축구공 후보가 축구공일 것이라는 가정을 적용하여 축구공 가려짐 처리 알고리즘을 제안한다. 실제 방송용 축구 경기 영상에 적용하여 제안된 알고리즘이 가려짐 상황을 효과적으로 처리함을 보여준다.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. H. Kim and D. Shin, "Soccer Video Highlight Summarization for Intelligent PVR," Conference on The Korean Society of Broadcast Engineers 2009, pp. 209-212, Nov. 2009.
  2. J. Y, Y. Lee and K. Kim, "Object Tracking using Color Information in soccer game video and Ball Occupation rate analysis," Conference on Korean Institute of Information Scientists and Engineers 2008, Vol. 35, No. 2, pp. 452-456, Oct. 2008.
  3. T. D'Orazio, M. Leo, P. Spagnolo, M. Nitti, N. Mosca and A. Distante, "A visual system for real time detection of goal events during soccer matches," Computer Vision and Image Understanding, Vol. 113, No. 5, pp. 622-632, May 2009. https://doi.org/10.1016/j.cviu.2008.01.010
  4. J. Ren, J. Orwell, G. Jones and M. Xu, "Real-time modeling of 3-d soccer ball trajectories from multiple fixed cameras," IEEE Transaction on Circuits and Systems for Video Technology, Vol. 18, No. 3, pp. 350-362, March 2008. https://doi.org/10.1109/TCSVT.2008.918276
  5. X. Yu, H.W. Leong, C. Xu and Q. Tian, "Trajectory-based ball detection and tracking in broadcast soccer video," IEEE Transactions on Multimedia, Vol. 8, No. 6, pp. 1164-1178, Dec. 2006. https://doi.org/10.1109/TMM.2006.884621
  6. Y. Liu, D. Liang, Q. Huang and W. Gao, "Extracting 3D information from broadcast soccer video," Image and Vision Computing, Vol. 24, No. 10, pp. 1146-1162, Oct. 2006. https://doi.org/10.1016/j.imavis.2006.04.001
  7. T. Shimawaki, T. Sakiyama, J. Miura and Y. Shirai, "Estimation of ball route under overlapping with players and lines in soccer video image sequence," International Conference on Pattern Recognition ICPR, pp. 359-362, Hong Kong, Aug. 2006.
  8. K. Choi and Y. Seo, "Tracking soccer ball in TV broadcast video," Image Analysis and Processing (ICIAP), pp. 661-668, Cagliari, Italy, Sep. 2005.
  9. V. Pallavi, J. Mukherjee, A.K. Majumdar and S. Sural, "Ball detection from broadcast soccer videos using static and dynamic features," Journal Visual Communication and Image Representation, Vol. 19, No. 7, pp. 426-436, Oct. 2008. https://doi.org/10.1016/j.jvcir.2008.06.007
  10. T. Misu, A. Matsui, M. Naemura, M. Fujii and N. Yagi, "Distributed particle filtering for multiocular soccer ball tracking," IEEE International Conference on Acoustic, Speech and Signal Processing, pp. 937-940, Hawaii, USA, April 2007.
  11. T. D'Orazio, M. Leo, A. Distante and C. Guaragnella, "New algorithm for ball recognition using circle hough transform and neural classifier," Pattern Recognition, Vol. 37, No. 3, pp. 393-408, March 2004. https://doi.org/10.1016/S0031-3203(03)00228-0