This Article 
 Bibliographic References 
 Add to: 
Hierarchical Contour-Based Segmentation of Dynamic Scenes
September 1992 (vol. 14 no. 9)
pp. 946-952

A motion segmentation algorithm is introduced. The algorithm is based on the assumption of one coherent moving area (without holes) on a static background. It does coarse-to-fine pyramid-based boundary refinement that attempts to classify the blocks into three classes: inside, border, and outside.

[1] M. Kass, A. Witkin, and D. Terzopoulos, "Snakes: Active contour models," inProc. ICCV'87(London), June 8-11, 1987, pp. 259-268.
[2] V. Cantoni and S. Levialdi, Eds.,Pyramidal Systems for Computer Vision. Berlin: Springer-Verlag, 1986.
[3] S. Tanomito and T. Pavlidis, "A hierarchical data structure for picture processing," inProc. CGIP, vol. 4, pp. 101-119, 1975.
[4] A. Rosenfeld, "Some pyramid techniques for image segmentation," inPyramidal Systems for Computer Vision(V. Cantoni and S. Levialdi, Eds.). Berlin, Heidelberg: Springer-Verlag, 1986, pp. 261-271, NATO ASI Series, vol. F25.
[5] R. Jain, "Difference and accumulative difference pictures in dynamic scene analysis," inProc. IVC, vol. 2, no. 2, 1984.
[6] R. Jain, "Extraction of motion information from peripheral processes,"IEEE Trans Patt. Anal. Machine Intell., vol. PAMI-3, no. 5, Sept. 1981.
[7] R. Jain and H. Nagel, "On the analysis of accumulative difference pictures from image sequence of real world scenes," vol. PAMI-1, no. 2, pp. 206-214, 1979.
[8] N. Nahi and M. Jahanshahi, "Image boundary estimation,"IEEE Trans. Comput., vol. C-26, no. 8, pp. 772-781, 1977.
[9] D. Koller and H. Nagel, "Ein robustes Verfahren zur Detektion und Verfolgungbewegter Objekte in Bildfolgen," inProc. 12 DAGM-Symp. Aaler 1990 Informatik-Fachbesichte, pp 625-633.
[10] R. Jain, W. Martin, and J. Aggarwal, "Segmentation through the detection of changes due to motion," inProc. CGIP, 1979, pp. 13-34.
[11] W. Thompson, "Combining motion and contrast for segmentation,"IEEE Trans Patt. Anal. Machine Intell., vol. PAMI-2, no. 6, pp. 543-549, 1980.
[12] M. Leung and Y. Yang, "Human body motion segmentation in a complex scene,"Patt. Recogn., vol. 20, no. 1, pp. 55-64, 1987.
[13] A. Rosenfeld, Ed.,Multiresolution Image Processing and Analysis. Berlin: Springer-Verlag, 1984.
[14] P. Chen and T. Pavlidis, "Image segmentation as an estimation problem," inImage Modeling(A. Rosenfeld, Ed.). New York: Academic, 1981, pp. 9-29.
[15] M. Schneier, "Using pyramids to define local threshold for blob detection,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-5, no. 3, pp. 345-349, 1983.
[16] S. Yalamanchili, W. Martin, and J. Aggarwal, "Extraction of moving object descriptions via differencing," inCGIP, vol. 18, pp. 188-201, 1982.
[17] S. Baugher and A. Rosenfeld, "Boundary localization in an image pyramid,"Patt. Recogn., vol. 19, pp. 373-395, 1986.
[18] H. L. Van Trees,Detection, Estimation, and Modulation Theory, Vol. I. New York: Wiley, 1968.
[19] F. Bergholm, "Edge focusing,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-9, pp. 726-741, 1987.
[20] A. D. Gross and A. Rosenfeld, "Multiresolution object detection and delineation,"Comput. Vision Graphics Image Processing, vol. 39, pp. 102-115, 1987.
[21] A. Sher and A. Rosenfeld, "Detecting and extracting compact textured regions using pyramids,"IVC, vol. 7, 1987.
[22] R. Hartley, "Segmentation of optical flow fields by pyramid linking,"Patt. Recogn. Lett., vol. 3, pp. 253-262, 1985.
[23] L. Westberg, "Hierarchical object--Background segmentation," Licenciate thesis, Dept. TTT, Royal Inst. of Tech., Stockholm, Sweden, 1989.

Index Terms:
hierarchical contour based segmentation; picture processing; pattern recognition; image sequence; dynamic scenes; motion segmentation; coarse-to-fine pyramid-based boundary refinement; pattern recognition; picture processing
L. Westberg, "Hierarchical Contour-Based Segmentation of Dynamic Scenes," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 9, pp. 946-952, Sept. 1992, doi:10.1109/34.161353
Usage of this product signifies your acceptance of the Terms of Use.