DOI QR코드

DOI QR Code

Positive Random Forest 기반의 강건한 객체 추적

Positive Random Forest based Robust Object Tracking

  • 조윤섭 (중앙대학교 첨단영상대학원 영상학과) ;
  • 정수웅 (중앙대학교 첨단영상대학원 영상학과) ;
  • 이상근 (중앙대학교 첨단영상대학원 영상학과)
  • Cho, Yunsub (Department of Image Engineering, Graduate School of Advanced Imaging Science, Multimedia, and Film, Chung-Ang University) ;
  • Jeong, Soowoong (Department of Image Engineering, Graduate School of Advanced Imaging Science, Multimedia, and Film, Chung-Ang University) ;
  • Lee, Sangkeun (Department of Image Engineering, Graduate School of Advanced Imaging Science, Multimedia, and Film, Chung-Ang University)
  • 투고 : 2015.01.02
  • 심사 : 2015.05.26
  • 발행 : 2015.06.25

초록

고성능 컴퓨터와 디지털 카메라의 보급으로 컴퓨터를 이용한 객체 탐지 및 추적은 컴퓨터 비전의 다양한 응용분야에서 중요한 문제로 대두 되고 있다. 또한, 지능형 자동화 감시 장치, 영상 분석 장치, 자동화된 로봇 분야 등에서 그 필요성이 점점 부각 되고 있다. 객체 추적은 카메라를 이용하여 움직이는 객체의 위치를 찾는 처리 과정을 의미 하며, 강건한 객체 추적을 위해서는 객체의 스케일, 형태 변화, 회전에 강건하고 정확한 객체의 위치를 파악할 수 있어야한다. 본 논문에서는 랜덤 포레스트를 이용한 강건한 객체 추적에 대한 알고리즘을 제안하였다. 정확한 객체의 위치를 찾기 위해 지역 공분산과 ZNCC (Zeros Mean Normalized Cross Correlation)를 사용하여 객체를 검출하고 검출된 객체를 5개의 부분으로 나누어 랜덤 포레스트로 객체가 잘 검출 되었는지 검증 한다. 검증된 객체 중 모델을 선택하여 객체 검출이 잘못 되었다고 판단된 경우 입력 모델을 변경하여 정확한 객체를 찾도록 하였다. 제안된 알고리즘과 기존의 알고리즘들을 비교 하였을 때 비교적 정확한 객체의 위치를 잘 찾아 가는 것을 확인하였다.

In compliance with digital device growth, the proliferation of high-tech computers, the availability of high quality and inexpensive video cameras, the demands for automated video analysis is increasing, especially in field of intelligent monitor system, video compression and robot vision. That is why object tracking of computer vision comes into the spotlight. Tracking is the process of locating a moving object over time using a camera. The consideration of object's scale, rotation and shape deformation is the most important thing in robust object tracking. In this paper, we propose a robust object tracking scheme using Random Forest. Specifically, an object detection scheme based on region covariance and ZNCC(zeros mean normalized cross correlation) is adopted for estimating accurate object location. Next, the detected region will be divided into five regions for random forest-based learning. The five regions are verified by random forest. The verified regions are put into the model pool. Finally, the input model is updated for the object location correction when the region does not contain the object. The experiments shows that the proposed method produces better accurate performance with respect to object location than the existing methods.

키워드

참고문헌

  1. A. Yilmaz, O. Javed, and M. Shah, "Object tracking: a survey," Association for Computing Machinery, vol. 38, no. 4, pp. 1-45, 2006.
  2. H. Yang, L. Shao, F. Zheng, L. Wang, and Z. Song, "Recent advances and trends in visual tracking: A review," Neurocomputing, vol. 74, no. 18, pp. 3823-3831, Nov. 2011. https://doi.org/10.1016/j.neucom.2011.07.024
  3. D.Jeong, D. Kang, Y. Yang, and J. Ra, "A real-time head tracking algorithm using mean-shift color convergence and shape based Refinement," Journal of The Institute of Electronics Engineers of Korea, vol. 42SP, no.6, pp. 1-8, Nov. 2015.
  4. D. Kim, S. Lee, and S. Ko, "Target modeling with color arrangement for region-based object tracking," Journal of The Institute of Electronics Engineers of Korea, vol. 49SP, no.1, pp. 1-10, Jan. 2012.
  5. K. Nummiaro, E. Koller-Meier, and L. Van Gool, "An adaptive color-based particle filter," Image and Vision Computing, vol. 21, no. 1, pp. 99-110, 2003. https://doi.org/10.1016/S0262-8856(02)00129-4
  6. G. Welch, and G. Bishop. An introduction to the kalman filter. Technical report, UNC-CH Computer Science Technical Report 95041, 1995.
  7. Z. Kalal, J. Matas, and K. Mikolajczyk, "P-N learning: Bootstrapping binary classifiers by structural constraints," IEEE Conference on Computer Vision and Pattern Recognition, pp. 49-56, Jun. 2010.
  8. B. Babenko, M. Yang, and S. Belongie, "Visual tracking with online multiple instance learning," in Proceeding IEEE Conference on Computer Vision and Pattern Recognition, pp. 983-990, Jun. 2009.
  9. O. Tuzel, F. Porikli, and P. Meer, "Region covariance: A fast descriptor for detection and Classification," European Conference on Computer Vision, vol. 2, pp. 589-600, 2006.
  10. J.P. Lewis, "Fast normalized cross-correlation," Vision Interface, 1995.
  11. A. Liaw, and M. Wiener, "Classification and regression by randomforest," R News, vol. 2, no. 3, pp. 18-22, 2002.
  12. Y. Wu, J. Lim, and M.-H. Yang, "Online object tracking: A benchmark," IEEE Conference on Computer Vision and Pattern Recognition, pp. 2411-2418, 2013.
  13. P. Feguth and D. Teropulos, "Color-Based Tracking of Heads and Other Mobile Object at Video Frame Rates," IEEE Conference on Computer Vision and Pattern Recognition, pp.21-27, 1997.
  14. R. Collins, "Mean shift blob tracking through scale space," IEEE Conference on Computer Vision and Pattern Recognition, pp. II: 234-240, Jun. 2003.
  15. H. Grabner, M. Grabner, and H. Bischof, "Real-Time Tracking via Online Boosting," Proceeding Conference on British Machine Vision, pp. 47-56, 2006.
  16. H. Grabner, C. Leistner, and H. Bischof, "Semi-Supervised Online Boosting for Robust Tracking," in Proceeding European Conference on Computer Vision, 2008.
  17. S. Stalder, H. Grabner, and L. van Gool, "Beyond Semi-Supervised Tracking: Tracking Should Be as Simple as Detection, But Not Simpler than Recognition," in Proceeding Workshop on Online Learning for Computer Vision, 2009.
  18. T. B. Dinh, N. Vo, and G. Medioni, "Context tracker: Exploring supporters and distracters in unconstrained environments," IEEE Conference on Computer Vision and Pattern Recognition, pp.1177-1184, Jun. 2011.