Motion based segmentation
Bezalel Peleg, H. Rom · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · 2002
An iterative method is described for segmenting image sequences into independently moving regions while computing the motion parameters of each region. In each iteration, image points are classified into regions based on their consistency with the different motion estimates, and motion estimates are then updated using the obtained regions. The motion estimates and the segmentation improve with every iteration, and the iteration stops when a stable segmentation is obtained. Accurate motion parameters are recovered for each segment. The process is performed directly on gray-level images and does not require detection of special feature points and the computation of point correspondence. It is also faster and more robust than optical-flow-based segmentation methods.>
Cited by 51 works. doi:10.1109/icpr.1990.118074
Authors
References
- Image Analysis Using Mathematical Morphology
- The interpretation of a moving retinal image
- Determining Three-Dimensional Motion and Structure from Optical Flow Generated by Several Moving Objects
- Registration of Translated and Rotated Images Using Finite Fourier Transforms
- Computational Stereo
- Direct methods for recovering motion
- Contour Evolution, Neighborhood Deformation, and Global Image Flow: Planar Surfaces in Motion
- Scene Segmentation from Visual Motion Using Global Optimization
- Direct Passive Navigation
- Image Sequence Analysis: Motion Estimation