Segmentation and 2D motion estimation by region fragments
- 30 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 192-199
- https://doi.org/10.1109/iccv.1993.378220
Abstract
A central problem in estimating multiple image motions is that 2-D motion estimation and region segmentation are mutually dependent. The authors present a new region description method for dealing with this mutual dependence problem. Segmentation and motion estimation are simultaneously performed by a clustering process based on color, motion, and pixel position. As a result of the clustering, an image is decomposed into region fragments. Each fragment is characterized by distribution parameters of color, pixel positions, and spatiotemporal intensity gradients. The image is described by the parameters of the region fragments; 2-D motion vectors for each fragment are obtained from the distribution parameters of the intensity gradients. By combining those features in the clustering process, regions are segmented more precisely, motion boundaries are not blurred, and the 2-D motions are obtained even in noisy areas. Experimental results are presented.Keywords
This publication has 12 references indexed in Scilit:
- Robust estimation of a multi-layered motion representationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Estimation of velocity, acceleration and disparity in time sequencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1991
- Generalized gradient schemes for the measurement of two-dimensional image motionBiological Cybernetics, 1990
- The self-organizing mapProceedings of the IEEE, 1990
- Computation of component image velocity from local phase informationInternational Journal of Computer Vision, 1990
- Analog hardware for detecting discontinuities in early visionInternational Journal of Computer Vision, 1990
- Image flow segmentation and estimation by constraint line clusteringPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Optical flow using spatiotemporal filtersInternational Journal of Computer Vision, 1988
- Directional selectivity and its use in early visual processingProceedings of the Royal Society of London. B. Biological Sciences, 1981
- Velocity determination in scenes containing several moving objectsComputer Graphics and Image Processing, 1979