Browse > Article

A Study on Video Object Segmentation using Nonlinear Multiscale Filtering  

이웅희 (인하대학교 전자공학과)
김태희 (한국전자통신연구원 전파방송연구소)
이규동 (인하대학교 전자공학과)
정동석 (인하대학교 전자공학과)
Abstract
Object-based coding, such as MPEG-4, enables various content-based functionalities for multimedia applications. In order to support such functionalities, as well as to improve coding efficiency, each frame of video sequences should be segmented into video objects. In this paper. we propose an effective video object segmentation method using nonlinear multiscale filtering and spatio-temporal information. Proposed method performs a spatial segmentation using a nonlinear multiscale filtering based on the stabilized inverse diffusion equation(SIDE). And, the segmented regions are merged using region adjacency graph(RAG). In this paper, we use a statistical significance test and a time-variant memory as temporal segmentation methods. By combining of extracted spatial and temporal segmentations, we can segment the video objects effectively. Proposed method is more robust to noise than the existing watershed algorithm. Experimental result shows that the proposed method improves a boundary accuracy ratio by 43% on "Akiyo" and by 29% on "Claire" than A. Neri's Method does.
Keywords
video object segmentation; nonlinear multiscale filtering; SIDE;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Y. Tsaig and A. Averbuch, 'Automatic segm entation of moving objects in video sequences: A region labeling approach,' IEEE Trans. on C ircuits and Syst. Video Technol, vol. 12, no. 7, pp. 597-612, July 2002   DOI   ScienceOn
2 T. Aach, A. KauP, and R. Mester, 'Statistica 1 model-based change detection in moving vide o,' Signal Processing, vol. 31, PP. 165-180, Mar. 1993   DOI   ScienceOn
3 R. Mech and M. Wollborn, 'A noise robust method for 2D shape estimation of moving objects in video sequences considering a moving c amera,' SignaI Processing, vol. 66, PP. 203-21 7, Apr. 1998   DOI   ScienceOn
4 P. Perona and J. Malik, 'Scale-space and edg e detection using anisotropic diffusion,' IEEE T rans. on Pattern Anal. Machine Intell., vol. 12, no. 7, PP. 629-639, July 1990   DOI   ScienceOn
5 I. Pollak, 'Segmentation and restoration via nonlinear multiscale filtering,' IEEE Signal Pro cessing Mag., vol. 19, PP. 26-36, Sept. 2002   DOI   ScienceOn
6 F. Long, D. Feng, H. Peng, and W. Siu, 'Extractmg semantic video objects,' IEEE Computer Graphics and Apptications, vol. 21, no. 1, PP. 48-55, January/February 2003
7 A. Neri, S. Colonnese, G. Russo, and P. Tal one, 'Automatic moving object and background separation,' Signal Processing, vol. 66, PP. 219 -232, Apr. 1998   DOI   ScienceOn
8 S. Y. Chien, S. Y. Ma, and L. G. Chen, 'Efficient moving object segmentation algorithm using background registration technique,' IEEE Trans. on Circuit and Syst. Video Technol., vol. 12, no. 7, PP. 577-586, July 2002   DOI   ScienceOn
9 I. Pollak, 'Nonlinear scale space analysis in image processing,' Ph.D. dissertation, Massachus etts Institute of technology, Aug. 1999
10 M. Kim, J. G. Choi, D. Kim, H. Lee, M. H. Lee, C. Ahn, and Y. Ho, 'A VOP generati on tool : Automatic segmentation of moving ob jects in image sequences based on spatio-tempo ral information,' IEEE Trans. on Circuit and S yst. Video Technol., vol. 9, no. 8, PP. 1216-122 6, Dec. 1999   DOI   ScienceOn
11 I. Pollak, 'Image segmentation and edge en hancement with stabilized inverse diffusion equa tions,' IEEE Trans. on Image Processing, vol. 9, no. 2, PP. 256-266, Feb. 2000   DOI   ScienceOn
12 L. Vincent and P. Soille, 'Watershed in digital spaces: an efficient algorithm based on immersion simulations,' IEEE Trans. on Pattern Ana/. Machine Intell., vol. 13, no. 6, PP. 583-598, June 1991   DOI   ScienceOn
13 D. Wang, 'Unsupervised video segmentation based on watersheds and temporal tracking,' IE EE Trans. on Circuit and Syst. Video Technol., vol. 8, no. 5, PP. 539-546, Sept. 1998   DOI   ScienceOn