Journal of Advanced Navigation Technology (한국항행학회논문지)

The Korean Navigation Institute (한국항행학회)
권호 표지
DOI QR코드

DOI QR Code

Merge and Split of Players under MeanShift Tracking in Baseball Videos

야구 비디오에 대한 민시프트 추적 하에서 선수 병합 분리

  • Choi, Hyeon-yeong (Department of Computer Engineering, Kumoh National Institute of Technology) ;
  • Hong, Sung-hwa (Department of Maritime Inform. & Comm. Eng., Mokpo National Maritime University) ;
  • Ko, Jae-pil (Department of Computer Engineering, Kumoh National Institute of Technology)
  • 최현영 (금오공과대학교 컴퓨터공학과) ;
  • 홍성화 (목포해양대학교 해양정보통신공학과) ;
  • 고재필 (금오공과대학교 컴퓨터공학과)
  • Received : 2017.01.23
  • Accepted : 2017.02.27
  • Published : 2017.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we propose a method that merges and splits players in the MeanShift tracking framework. The MeanShift tracking moves the center of tracking window to the maximum probability location given the target probability distribution. This tracking method has been widely used for real-time tracking problems because of its fast processing speed. However, it hardly handles occlusions in multiple object tracking systems. Occlusions can be usually solved by applying data association methods. In this paper, we propose a method that can be applied before data association methods. The proposed method automatically merges and splits the overlapped players by adjusting the each player's tracking map. We have compared the tracking performance of the MeanSfhit tracking algorithm and the proposed method.

본 논문에서는 야구 동영상에서 민시프트 추적 프레임워크 하에 선수들을 병합-분리하는 방법을 제안한다. 민시프트 추적 방법은 추적대상 객체의 확률분포에 대해 현재 추적영역에서 확률 값이 최대가 되는 위치로 중심점을 이동하여 객체를 추적한다. 민시프트 추적은 처리속도가 빨라 실시간 추적 문제에 널리 사용되고 있다. 그러나, 다수 객체 추적에서 겹침 문제를 처리하기 어렵다. 이와 같은 문제는 일반적으로 데이터 연관 방법을 적용하여 해결한다. 하지만, 야구선수의 겹침 문제는 선수영역의 해상도가 낮고, 여러 객체가 한 모델을 공유하기 때문에 데이터 연관 방법을 바로 적용하기 어렵다. 본 논문에서는 데이터 연관 방법 적용 이전에 선수 겹침 상황에서 병합-분리을 관리하는 방법을 제안한다. 제안하는 방법은 선수의 겹침 상황에서 추적영역 내의 추적 맵 값을 조정하여 선수의 병합-분리를 관리한다. 본 논문에서 제안하는 방법과 민시프트 알고리즘의 추적성능을 비교하여 제안방법의 성능이 우수함을 보였다.

Keywords

References

  1. D. Comaniciu, V. Ramesh, and P. Meer, "Real-time tracking of non-rigid objects using mean shift," in Proceedings of the 2000 IEEE Conference on Computer Vision and Pattern Recognition, Hilton Head: SC, pp. 142-149, 2000.
  2. Y. B. Shalom, and T. Fortmann, Tracking and Data Association, London: UK, Academic Press, 1988.
  3. J. Xing, H. Ai, L. Liu, and S. Lao. "Multiple players tracking in sports video: a dual-mode two-way bayesian inference approach with progressive observation modeling," IEEE Transaction on Image Processing, Vol. 20, No. 6, pp. 1652-1667, 2011. https://doi.org/10.1109/TIP.2010.2102045
  4. L. Zhang, Y. Li, and R. Nevatia, "Global data association for multi-object tracking using network flows," in Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, Anchorage: Alaska, 2008.
  5. J. Xing, H. Ai, and S. Lao "Multi-object tracking through occlusions by local tracklets filtering and global tracklets association with detection responses," in Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition, Miami: FL, pp. 1200-1207, 2009
  6. S. Araki, N. Yokoya, and H. Takemura, "Real-time tracking of multiple moving objects using split-and-merge contour models based on crossing detection," Systems and Computers in Japan, Vol. 30, No. 9, pp. 25-33, 1999. https://doi.org/10.1002/(SICI)1520-684X(199908)30:9<25::AID-SCJ4>3.0.CO;2-G
  7. J. C. Rubio, J. Serrat, and A. M. Lopez, "Multiple target tracking and identity linking under split, merge and occlusion of targets and observations," in Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods, Vilamoura: Portugal, pp. 15-24, 2012.
  8. Y. Ma, Q. Yu, and I. Cohen, "Multiple hypothesis target tracking using merge and split of graph's nodes," in International Symposium on Visual Computing, Lake Tahoe: NV, pp. 783-792, 2006.
  9. A. Makris, and C. Prieur, "Bayesian multiple hypothesis tracking of merging and splitting targets," IEEE Transactions on Geoscience and Remote Sensing, Vol. 52, No. 12, pp.7684-7694, 2014. https://doi.org/10.1109/TGRS.2014.2316600
  10. Z. Khan, B. Tucker, and F. Dellaert. "Multitarget tracking with split and merged measurements," in Proceedings of the 2005 IEEE Conference on Computer Vision and Pattern Recognition, San Diego: CA, pp. 605-610, 2005.
  11. C. Beyan, and A. Temizel, "Adaptive mean-shift for automated multi object tracking," IET Computer Vision, Vol. 6, No. 1, pp. 1-12, 2012. https://doi.org/10.1049/iet-cvi.2011.0054
  12. K. Kim, S. Hong, S. Kwak, J. Ahn, and H. Byun, "Multiple human tracking using mean shift and depth map with a moving stereo camera," Journal of Korean Institute of Science and Technology Information, Vol. 34, No. 10, pp. 937-944, 2007.
  13. Y. Wu, J. Lim, and M. H. Yang, "Online object tracking: A benchmark," in Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland: OR, pp. 2411-2418, 2013.
  14. J. Kim, J. Jeong, D. Han, J. Heo, and D. Lee, "Fixed-wing UAV's image-based target detection and tracking using embedded processor," Journal of Advanced Navigation Technology, Vol. 16, No. 6, pp. 910-919, 2012. https://doi.org/10.12673/jkoni.2012.16.6.910

Cited by

  1. 딥 러닝 기반의 영상처리 기법을 이용한 겹침 돼지 분리 vol.22, pp.2, 2017, https://doi.org/10.9717/kmms.2019.22.2.136