DOI QR코드

DOI QR Code

Object Tracking Algorithm Using Weighted Color Centroids Shifting

가중 컬러 중심 이동을 이용한 물체 추적 알고리즘

  • Choi, Eun-Cheol (Institude of TMS information technology, Yonsei university) ;
  • Lee, Suk-Ho (Division of computer and information engineering, Dongseo university) ;
  • Kang, Moon-Gi (Institude of TMS information technology, Yonsei university)
  • 최은철 (연세대학교 TMS 정보기술 사업단) ;
  • 이석호 (동서대학교 컴퓨터정보공학부) ;
  • 강문기 (연세대학교 TMS 정보기술 사업단)
  • Received : 2009.09.16
  • Accepted : 2010.03.15
  • Published : 2010.03.30

Abstract

Recently, mean shift tracking algorithms have been proposed which use the information of color histogram together with some spatial information provided by the kernel. In spite of their fast speed, the algorithms are suffer from an inherent instability problem which is due to the use of an isotropic kernel for spatiality and the use of the Bhattacharyya coefficient as a similarity function. In this paper, we analyze how the kernel and the Bhattacharyya coefficient can arouse the instability problem. Based on the analysis, we propose a novel tracking scheme that uses a new representation of the location of the target which is constrained by the color, the area, and the spatiality information of the target in a more stable way than the mean shift algorithm. With this representation, the target localization in the next frame can be achieved by one step computation, which makes the tracking stable, even in difficult situations such as low-rate-frame environment, and partial occlusion.

최근 평균이동(mean shift) 알고리즘과 같은 커널 기반의 추적 알고리즘이 활발하게 연구되고 있다. 이러한 방식의 알고리즘은 커널이 제공하는 컬러 히스토그램 정보와 약간의 공간적 정보를 이용하는 방식으로 적은 연산량으로 추적을 수행할 수 있는 장점을 지니고 있다. 그러나 공간성을 확보하기 위한 등방성 커널과 유사성을 비교하기 위한 바타차야 계수를 사용하기 때문에 발생하는 불안정성이 존재한다. 본 논문은 커널과 바타차야 계수의 사용이 왜 알고리즘의 불안정성을 야기 시킬 수 있는지에 대해 분석한다. 또한 이 분석을 바탕으로 새로운 추적 알고리즘을 제안한다. 제안한 알고리즘은 표적을 구성하는 컬러별 중심을 이용하는 방법으로 표적의 컬러, 컬러별 화소의 빈도, 공간적 정보 등이 반영된다. 제안한 방법은 평균 이동 방법보다 결과의 오류 비율이 적으며, 다음 프레임에서의 표적 위치가 반복 없이 한차례의 연산으로 얻어진다. 또한, 낮은 프레임 율 및 일부 폐색이 발생하여 평균 이동 방법으로는 실패하는 상황에서도 성공적으로 동작한다.

Keywords

References

  1. D. Comaniciu, v. Ramesh, and P. Meer, "Kernel-based object tracking," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 25, pp. 564-75, 2003. https://doi.org/10.1109/TPAMI.2003.1195991
  2. G. R. Bradski, "Computer vision face tracking for use in a perceptual user interface," Intel Technology Journal, 2nd Quarter,1998.
  3. S. McKenna, Y. Raja, and S. Gong, "Tracking colour objects using adaptive mixture models," Image and Vision Computing Journal, vol. 17, pp. 223-29, 1999
  4. A. Yilmaz. "Object tracking by asymmetric kernel mean shift with automatic scale and orientation selection," In IEEE Conf. on Computer Vision and Pattern Recognition, 2007.
  5. R. Collins. "Mean-shift blob tracking through scale space," In IEEE Conf. on Computer Vision and Pattern Recognition, 2003.
  6. A. Babaeian, S. Rastegar, M. Bandarabadi, and M. Rezaei, "Mean shift-based object tracking with multiple features," Southeastern Symposium on System Theory, pp. 68-72, 2009
  7. N. Oshima, T. Saitoh, and R. Konishi, "Real Time Mean Shift Tracking using Optical Flow Distribution," International Joint Conference SICE-ICASE, pp. 4316-4320, 2006.
  8. Hongxia Chu and K. Wang, "Target tracking based on mean shift and improved kalman filtering algorithm," IEEE International Conference on Automation and Logistics, pp. 808-812, 2009
  9. Fang Xu, Jun Cheng, and Chao Wang, "Real time face tracking using particle filtering and mean shift," IEEE International Conference on Automation and Logistics, pp. 2252-2255, 2008
  10. Zhou Bin, Wang Jun-zheng, Li Jing, and Shen Wei, "Object Tracking with Mean Shift and Model Prediction," International Congress on Image and Signal Processing, pp. 1-5, 2009
  11. P. Li, "An Adaptive Binning Color Model for Mean Shift Tracking," IEEE Transactions on Circuits and Systems for Video Technology, pp. 1293-1299, Vol. 18, 2008 https://doi.org/10.1109/TCSVT.2008.928528
  12. D. Comaniciu and P. Meer, "Mean shift: A robust approach toward feature space analysis," IEEE Trans. Pattern Anal. Machine Intell., vol. 24, no. 5, pp. 603-619, 2002. https://doi.org/10.1109/34.1000236
  13. http://groups.inf.ed.ac.uk/vision/CAVIAR/CAVIARDATA1/
  14. C. Yang, R. Duraiswami, and L. Davis, "Efficient Mean-Shift Tracking via a New Similarity Measure," CVPR'05, pp. 176-183, 2005.

Cited by

  1. Histogram Equalization Based Color Space Quantization for the Enhancement of Mean-Shift Tracking Algorithm vol.19, pp.3, 2014, https://doi.org/10.5909/JBE.2014.19.3.329