DOI QR코드

DOI QR Code

Dynamic Modeling of Eigenbackground for Object Tracking

객체 추적을 위한 고유 배경의 동적 모델링

  • Kim, Sung-Young (Dept. of Computer Engineering, Kumoh National Institute of Technology)
  • 김성영 (금오공과대학교 컴퓨터공학과)
  • Received : 2012.02.28
  • Accepted : 2012.03.23
  • Published : 2012.04.30

Abstract

In this paper, we propose an efficient dynamic background modelling method by using eigenbackground to extract moving objects from video stream. Even if a background model has been created, the model has to be updated to adapt to change due to several reasons such as weather or lighting. In this paper, we update a background model based on R-SVD method. At this time we define a change ratio of images and update the model dynamically according this value. Also eigenbackground need to be modelled by using sufficient training images for accurate models but we reorganize input images to reduce the number of images for training models. Through simulation, we show that the proposed method improves the performance against traditional eigenbackground method without background updating and a previous method.

본 논문에서는 비디오 스트림으로부터 움직이는 객체를 추출하기 위해 고유 배경(eigenbackground)을 사용하여 효율적으로 배경을 모델링하는 방법을 제안한다. 배경은 모델링하더라도 시간이 지남에 따라 날씨나 조명의 변화에 따라 변화가 발생하므로 변화 요소를 반영할 수 있도록 배경 모델을 갱신해야 한다. 이를 위해 본 논문에서는 R-SVD 방법에 기반을 두고 배경 모델을 갱신하도록 한다. 이 때 영상 변화도를 정의하여 이 값에 따라 동적으로 배경을 모델링하여 처리시간을단축할 수 있도록 한다. 또한 고유 배경을 사용하는경우 충분한 훈련 데이터를사용해야만 정확한 모델을 생성할 수 있지만 본 논문에서는 적은 수의 데이터만을 사용하여 정확한 모델을 생성할 수 있도록 입력 프레임을 재구성하여 사용한다. 제안한 방법은 초기 고유 배경 모델 및 기존의 주기적으로 배경을 갱신하는 방법과의 비교를 통해 그 우수성을 확인한다.

Keywords

References

  1. Nuria M. Oliver, Barbara Rosario, and Alex P. Pentland, "A Bayesian Computer Vision System for Modeling Human Interactions," Pattern analysis and machine intelligence, Vol. 22, No. 8, pp. 831-843, Aug. 2000. https://doi.org/10.1109/34.868684
  2. D. Ross, J. Lim and M.H. Yang, "Adaptive Probabilistic Visual Tracking with Incremental Subspace Update," Proc. of the 8th European Conf. on Computer Vision, Vol. 2, pp. 470-482, Nov. 2004.
  3. Lei Wang, Lu Wang, Qing Zhuo, Huan Xiao and Wenyuan Wang, "Adaptive Eigenbackground for Dynamic Background Modeling," Intelligent Computing in Signal Processing and Pattern Recognition, Vol. 345, pp. 670-675, Oct. 2006. https://doi.org/10.1007/978-3-540-37258-5_74
  4. A. Yilmaz, O. Javed, and M. Shah, "Object Tracking: A Survey," ACM Journal of Computing Surveys, Vol. 38, No. 4, pp. 1-45, Dec. 2006. https://doi.org/10.1145/1132952.1132953
  5. Massimo Piccardi, "Background subtraction techniques: a review," 2004 IEEE Int'l Conf. on Systems, Man and Cybermetics, pp. 3099-3104, Apr. 2004.
  6. Gilbert Strang, "Linear Algebra and Its Application," Brooks Cole Pub Co, 2005.
  7. Lirui Xu, "Tracking Pedestrian Trajectory Using Adaptive Background Model," Engineering Master's Thesis in Kumoh National Institute of Technology, Feb. 2009.
  8. A. Levy and M. Kindenbaum, "Sequential Karhunen-Loeve basis extraction and its application to images," IEEE Transaction on Image Processing, Vol. 9, pp. 1371-1374, Aug. 2000. https://doi.org/10.1109/83.855432
  9. Hag-hee Kim, "Realization of augmented reality and object tracking using multiple camera," Journal of The Korea Society of Computer and Information, Vol. 16, No. 6, pp.89-97, Jun. 2011. https://doi.org/10.9708/jksci.2011.16.6.089
  10. Young-Suk Ji, Young-Joon Han, Hern-Soo Hahn, "Robust Method of Updating Reference Background Image in Unstable Illumination Condition," Journal of The Korea Society of Computer and Information, Vol. 15, No. 1, pp.91-102, Jan. 2010. https://doi.org/10.9708/jksci.2010.15.1.091

Cited by

  1. 입체영상에서 특징의 군집화를 통한 대상객체 분할 vol.13, pp.10, 2012, https://doi.org/10.5762/kais.2012.13.10.4807