Motion segmentation based on motion/brightness integration and oscillatory correlation
Authors:
- DeLiang WangDWDeLiang Wang
- 1 July 2000
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 11 (4) , 935-947
Abstract
A segmentation method based on the integration of motion and brightness is proposed for image sequences. The method is composed of two parallel pathways that process motion and brightness, respectively. Inspired by the visual system, the motion pathway has two stages. The first stage estimates local motion at locations with reliable information. The second stage performs segmentation based on local motion estimates. In the brightness pathway, the input scene is segmented into regions based on brightness distribution. Subsequently, segmentation results from the two pathways are integrated to refine motion estimates. The final segmentation is performed in the motion network based on refined estimates. For segmentation, locally excitatory globally inhibitory oscillator network (LEGION) architecture is employed whereby the oscillators corresponding to a region of similar motion/brightness oscillate in synchrony and different regions attain different phases. Results on synthetic and real image sequences are provided, and comparisons with other methods are made.Keywords
This publication has 27 references indexed in Scilit:
- Nonlinear motion estimation using the supercoupling approachIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998
- The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow FieldsComputer Vision and Image Understanding, 1996
- Artificial neural networks for 3-D motion analysis. I. Rigid motionIEEE Transactions on Neural Networks, 1995
- Filter selection model for motion segmentation and velocity integrationJournal of the Optical Society of America A, 1994
- Representing moving images with layersIEEE Transactions on Image Processing, 1994
- Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus propertiesNature, 1989
- Computing Optical Flow in the Primate Visual SystemNeural Computation, 1989
- Phenomenal coherence of moving visual patternsNature, 1982
- Kinetic disruption of optical texture: The perception of depth at an edgePerception & Psychophysics, 1969
- Motion parallax as a determinant of perceived depth.Journal of Experimental Psychology, 1959