템플릿 변형과 Level-Set이론을 이용한 비강성 객체 추적 알고리즘

A Robust Algorithm for Tracking Non-rigid Objects Using Deformed Template and Level-Set Theory

  • 발행 : 2003.05.01

초록

본 논문에서는 템플릿 변형과 Level-Set 이론을 사용하여 모델과 에지 기반의 객체 추적 방법을 제안한다. 제안된 방법은 배경의 변화, 객체 자체의 모양변화, 객체간의 겹침 등이 있는 경우에도 객체를 추적할 수 있다. 먼저, 객체 추적을 위해 템플릿과 목적 프레임간의 상호 영역 차이(Inter-region distance)와 에지 값으로 구성된 에너지 함수 PDEF(Potential Difference Energy Function)를 새롭게 정의한다. 이 함수는 객체 위치 및 경계 예측과 객체 모양 재결정 단계에서 사용된다. 객체 위치 및 경계 예측 단계에서는 객체의 변화가 어파인(affine) 변형을 따른다는 가정 하에 객체의 대략적인 모양 및 위치를 예측한다. 객체 모양 재결정 단계에서는 퍼텐셜 에너지 지도(Potential energy map)와 수정된 Level-Set 운동 함수를 사용하여 객체의 정확한 형태를 재결정한다. 실험결과에서 제안된 방법은 기존의 방법보다 배경의 변화가 큰경우, 객체 자체의 모양변화가 심한 경우, 객체간의 겹침이 있는 경우 등 다양한 상황이 포함된 동영상에서 정확하게 객체를 추적할 수 있음을 확인할 수 있다.

In this paper, we propose a robust object tracking algorithm based on model and edge, using deformed template and Level-Set theory. The proposed algorithm can track objects in case of background variation, object flexibility and occlusions. First we design a new potential difference energy function(PDEF) composed of two terms including inter-region distance and edge values. This function is utilized to estimate and refine the object shape. The first step is to approximately estimate the shape and location of template object based on the assumption that the object changes its shape according to the affine transform. The second step is a refinement of the object shape to fit into the real object accurately, by using the potential energy map and the modified Level-Set speed function. The experimental results show that the proposed algorithm can track non-rigid objects under various environments, such as largely flexible objects, objects with large variation in the backgrounds, and occluded objects.

키워드

참고문헌

  1. L. Vincent and P. Soille, 'Watersheds in Digital Spaces : An Efficient Algorithm based on Immersion Simulations,' PAMI. 13, no. 6, pp 583-589, 1991 https://doi.org/10.1109/34.87344
  2. D. K. Park, H. S. Yoon, C. S. Won, 'Fast Object Tracking in Digital Video,' IEEE Trans. Consumer Electronics, vol. 46, no. 3, pp. 785-790, 2000 https://doi.org/10.1109/30.883448
  3. M. Kass, A. Witkin and D. Terzopoulos 'Snakes, active contour models,' International Journal of Computer Vision, Vol.1, 1987, pp.321-331 https://doi.org/10.1007/BF00133570
  4. D. Cohen, 'On Active Contour Models and Balloons,' CVGIP: Image Understanding, vol. 53, pp. 211-218, 1991 https://doi.org/10.1016/1049-9660(91)90028-N
  5. A. Kumar, A. Yezzi, S. Kichenassamy, P. Olver, A. Tannenbaum, 'Active Contours for visual tracking: a geometric gradient based approach, ' IEEE Conf. Decision and Control. vol. 4, pp. 4041-4046, 1995 https://doi.org/10.1109/CDC.1995.479238
  6. M. Bertalmio, G. Sapiro, G. Randall, 'Morphing Active Contours,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 7, Jul. 2000 https://doi.org/10.1109/34.865191
  7. V. Caselles, R. Kimmel, and G. Sapiro, 'Geodesic Active Contours,' IEEE Proc. International Conference on Computer Vision, 1995 https://doi.org/10.1109/ICCV.1995.466871
  8. S. Kichenassamy, A. Kumar, P. Olver, A. Tannenbaum, and A. Yezzi, 'Gradient Flows and Geometric Active Contour Models,' IEEE Proc. International Conference on Computer Vision, pp. 810-815, 1995 https://doi.org/10.1109/ICCV.1995.466855
  9. V. Caselles, R. Kimmel, and G. Sapiro, 'Geodesic Active Contours,' IEEE Proc. International Conference on Computer Vision, 1995. https://doi.org/10.1109/ICCV.1995.466871
  10. N. Paragios, R. Deriche, 'Unifying Boundary and Region-based information for Geodesic Active Tracking,' IEEE Proc. International Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 300-305, 1999 https://doi.org/10.1109/CVPR.1999.784648
  11. Y. Zhong, A. K. Jain, M.-P. Dubuisson-Jolly, 'Object Tracking Using Deformable Templates,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 5, pp. 554-549, May. 2000 https://doi.org/10.1109/34.857008
  12. M.-P. Dubuisson-Jolly, A. Gupta, 'Tracking deformable templates using a shortest path algorithm,' Computer Vision and Image Understanding, vol. 81, no. 1, pp. 26-45, Jan. 2001 https://doi.org/10.1006/cviu.2000.0883
  13. N. Paragios, R. Deriche, 'Geodesic Active Contour and Level Sets for the Detection and Tracking of Moving Objects,' IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 22, no. 3, pp. 296-280, Mar. 2000 https://doi.org/10.1109/34.841758
  14. J. M. Odobez and P. Bouthemy, 'Robust Multi-resolution Estimation of Parametric Motion Models,' Journal. Visual Communication and Image Representation, vol. 6, no. 4, December. pp. 348-365, 1995 https://doi.org/10.1006/jvci.1995.1029