Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

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

Face Relation Feature for Separating Overlapped Objects in a 2D Image

2차원영상에서 가려진 물체를 분리하기 위한 면관계 특징

  • Piljae Song (Dept. of Electronic Engineering, Soongsil University) ;
  • Park, Hongjoo (Dept. of Electronic Engineering, Soongsil University) ;
  • Hyungtai Cha (Dept. of Electronic Engineering, Soongsil University) ;
  • Hernsoo Hahn (Dept. of Electronic Engineering, Soongsil University)
  • Published : 2001.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper proposes a new algorithm that detects and separates the occluding and occluded objects in a 2D image. An input image is represented by the attributed graph where a node corresponds to a surface and an arc connecting two nodes describes the adjacency of the nodes in the image. Each end of arc is weighted by relation value which tells the number of edges connected to the surface represented by the node in the opposite side of the arc. In attributed graph, homogeneous nodes pertained to a same object always construct one of three special patterns which can be simply classified by comparison of relation values of the arcs. The experimental results have shown that the proposed algorithm efficiently separates the objects overlapped arbitrarily, and that this approach of separating objects before matching operation reduces the matching time significantly by simplifying the matching problem of overlapped objects as the one of individual single object.

본 논문은 2D 영상에서 겹쳐진 물체를 분리하기 위한 새로운 기법을 제안한다. 제안된 알고리즘은 겹쳐진 물체를 분리하는 보편적인 기법으로서의 매칭 알고리즘이 가지는 계산상의 부담을 줄이고자 하였다. 영상에서의 물체의 표현은 attributed graph를 사용하며, 각 node와 arc는 물체의 면과 면간의 관계에 각각 대응시킨다 또한, 각 arc는 그 parameter로서 관계계수를 가지며 이는 arc를 중심으로 양 끝에 존재하는 임의의 node의 상대 node에 대한 가려짐 상태에 의해 정의된다. 각 node는 이웃 node와의 관계에 의해 다양한 패턴으로 분류되며, 제안된 패턴을 이용하여 node들의 homogeneity를 검사한다. 끝으로, Homogeneity를 만족하는 node들을 하나의 집합(node set)으로 grouping함으로써, 가려진 물체와 가리는 물체를 분리하게 된다. 본 논문에서 제안한 알고리즘은 임의의 형태로 놓여있는 겹쳐진 물체를 효율적으로 분리하고 있으며, 매칭단계 이전에 물체를 분리함으로써 매칭에 필요한 시간부담을 크게 줄일 수 있음을 실험을 통해 보여주고 있다.

Keywords

References

  1. S. J. Dickinson, A. Pentland, and A. Rosenfeld, 'From Volumes to Views: An Approach to 3-D Object Recognition', Computer Vision Graphics and Image Processing, Vol. 55, No. 2, March, pp. 130-154, 1992 https://doi.org/10.1016/1049-9660(92)90013-S
  2. S. J. Dickinson, A. Pentland, and A. Rosenfeld, '3-D Shape Recovery Using Distributed Aspect Matching,' IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 14, No 2, February 1992 https://doi.org/10.1109/34.121788
  3. A. Johnson and M. Hebert, 'Efficient Multiple Model Recognition in Clustered 3-D Scenes,' In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 671-677, 1998
  4. J. Edwards and H. Murase, 'Appearance Matching of Occluded Objects Using Coarseto-fine Adaptive Masks,' In Proceedings of IEEE Conference on Computer Vision and Pattern Recongnition, pp. 533-539, 1997
  5. A. Pikaz and I. Dinstein, 'Matching of Partially Occluded Planar Curves,' Pattern Recognition, Vol. 28, No. 2, pp. 199-209, 1995 https://doi.org/10.1016/0031-3203(94)00088-4
  6. T. Fan, G. Medioni and R. Nevatia, 'Recognizing 3-D Objects Using Surface Descriptions', EEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 11, No.11, November 1989 https://doi.org/10.1109/34.42853
  7. E. Salari and S. Balaji, 'Recognition of Partially Occluded Objects Using B-Spline Representation', Pattern Recognition, Vol. 24, pp. 653-660, 1991 https://doi.org/10.1016/0031-3203(91)90032-Z
  8. P. TSang, P. Yuen and F. Lam, 'Recognition of Occluded Objects', Pattern Recognition, Vol. 25, p. 1107-1117, 1992 https://doi.org/10.1016/j.patrec.2004.03.007
  9. P. TSang, P. Yuen and F. Lam, 'Classification of Partially Occluded Objects Using 3-Point Matching and Distance Transformation', Pattern Recognition, Vol. 27, pp. 27-40, 1994 https://doi.org/10.1016/0031-3203(94)90015-9
  10. Boohyung Lee and Hernsoo Hahn, 'Representation and Recognition of Polyhedral Objects using the Signatures of Surfaces in a Single 2ED image', ${\ulcorner}KITE Journal-S{\lrcorner}$, Vol. 34, No. 2, pp. 63-70, 1997
  11. A. Tremeau and N. Borel, 'A Region Growing and Merging Algorithm to Color Segmentation', Pattern Recognition, Vol. 30, No. 7, pp. 1191-1203, 1997 https://doi.org/10.1016/S0031-3203(96)00147-1
  12. Y. Kim, H. Hahn and C. Choo, 'Determination of the Initial Sensing Trajectory for Active Sensing and its Application to Stereo Vision', The Proceeding of 1993 Asian Conference on Computer Vision, 414-417, 1993