Journal of the Institute of Electronics Engineers of Korea CI (전자공학회논문지CI)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Robust Object Tracking for Scale Changes

스케일에 강건한 물체 추적 기법

  • Published : 2008.11.25
Download PDF
⟨ Previous Next ⟩

Abstract

Though conventional video surveillance systems such as CCTV depended on operators, recently developed intelligent surveillance systems no longer needed operators. However, these new intelligent surveillance systems have their own problems such as Occlusion, changing scale of target object, and affine. This paper handled information damage caused by changing the scale of the target object among other objects. Due to the change of the scale, the inaccurate information of target can be obtained when we update the background information. To handle this problem, we introduce a solution for information damage caused by problem of changing scale of target object located among other objects. Specifically, we suggest multi-stage sampling particle filter based advanced MSER for object tracking system. Through this method, the problem caused by changing scale of target can be avoided.

CCTV와 같은 기존의 영상 감시 시스템들은 상황을 통제하는 오퍼레이터에 많이 의존했었다. 하지만, 최근 제품화 되고 있는 시스템들은 오퍼레이터에 의존하지 않고 시스템 안에서 자동으로 문제를 해결할 수 있도록 지능화 되고 있다. 하지만, 시스템에서 자동으로 상황을 처리하기에 많은 문제가 존재한다. Occlusion, 타겟의 Scale, Affine 변화가 대표적인 문제인데, 본 논문에서는 타겟의 크기변 화로 인해 발생하는 정보 손상 문제를 다룬다. 이 문제는 타겟의 크기가 다양하게 변화함으로써 정확한 정보를 얻지 못하고, 배경 정보를 흡수함으로써 추적 알고리즘의 성능을 크게 저하시키는 원인이 된다. 따라서 본 논문에서는 물체의 크기가 변화함으로써 타겟 정보를 손상시키는 문제를 최소화하기 위한 방법을 제안한다. 이 문제를 해결하기 위해 Multi-Stage Sampling을 이용한 Particle Filter를 기반으로 물체 추적 알고리즘에 적합하도록 개량된 MSER을 이용하였다. 이를 통해 타겟 물체의 크기가 다양하게 변화해도 정확한 크기를 추정함으로써 이 문제를 해결할 수 있다.

Keywords

References

  1. Merwe, R., Doucet, A., Freitas, N., and Wan, E., "The unscented particle filter", Technical Report CUED/F-INFENG/TR 380, Cambridge University Engineering Department, August 2000
  2. D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-Based Object Tracking", IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 5, pp. 564-575, May 2003 https://doi.org/10.1109/TPAMI.2003.1195991
  3. Katja Nummiaro, Esther Koller-Meier and Luc Van Gool. "A Color-based Particle Filter", in First International Workshop on Generative- Model-Based Vision(GMBV), 2002
  4. M. Isard and A. Blake, "CONDENSATION: conditional density propagation for visual tracking," International Journal on Computer Vision, vol. 29, no. 1, pp. 5-28, 1998 https://doi.org/10.1023/A:1008078328650
  5. Lowe, D. G., "Distinctive Image Features from Scale-Invariant Keypoints", International Journal of Computer Vision, 60, 2, pp. 91-110, 2004. Lindeberg https://doi.org/10.1023/B:VISI.0000029664.99615.94
  6. J. Matas, O. Chum, M. Urban, and T.Pajdla. "Robust wide baseline stereo from maximally stable extremal regions", In Proc. of British Machine Vision conference, pp. 384-396, 2002
  7. Andrea Vedaldi. "An Implementation of Multi-Dimensional Maximally Stable Extremal regions", 2007
  8. M. Donoser and H. Bischof. "Efficient maximally stable extremal region. (MSER) tracking", In Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp.553-560, 2006
  9. S. Kang, J. Paik, A. Koschan, B. Abidi, and M. Abidi, "Real-time video tracking using PTZ cameras," QCAV, pp.103-111,. 19-22 May 2003
  10. Yong Rui and Yunqiang Chen. "Better Proposal Distributions: Object Tracking Using Unscented Particle Filter", In Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 786-793, 2001
  11. Bohyung Han, Ying Zhu, Dorin Comaniciu, Larry S. Davis, "Kernel-Based Bayesian Filtering for Object Tracking", In Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). pp.227-234, 2005
  12. Tao Wang, Qian Diao, Yimin Zhang, Gang Song, Chunrong Lai, Gary Bradski. "A Dynamic Bayesian Network Approach to Multi-cue based Visual Tracking", In Proc. Of International Conference on Pattern Recognition (ICPR), pp. 167-170, 2004
  13. Hang-Bong Kang and Kihong Chun. "Multiple Object Tracking Via Multi-layer Multi-modal Framework", SCIA 2007, LNCS 4522, pp.789-797, 2007
  14. Ying Wu, Ting Yu, Gang Hua. "Tracking Appearances with Occlusions", In Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), pp. 789, 2003
  15. 천기홍, 강행봉. "다중 물체 추적에서의 모션 히스토그램을 이용한 샘플 생성 기법", HCI, 2006
  16. W. Qu, D. Schonfeld, and M. Mohamed, "Real-time interactively distributed multi-object tracking using a magnetic-inertia potential model,", In Proc. of 10th IEEE International Conference on Computer Vision (ICCV), vol. 1, pp. 535-540, Beijing, China, October 2005
  17. Yang, C., Duraiswami, R., Davis, R. "Fast Multiple Object Tracking via a Hierarchical Particle Filter", In Proc. of 10th IEEE International Conference on Computer Vision (ICCV), 2005
  18. 천기홍, 강행봉. "동일한 다중 물체 추적 기법", 대한전자공학회. vol29, pp. 679-680, 2006