Simultaneous motion estimation and segmentation
Authors:
- A.M. TekalpATA.M. Tekalp
- M.I. SezanMSM.I. Sezan
- 1 September 1997
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 6 (9) , 1326-1333
Abstract
We present a Bayesian framework that combines motion (optical flow) estimation and segmentation based on a representation of the motion field as the sum of a parametric field and a residual field. The parameters describing the parametric component are found by a least squares procedure given the best estimates of the motion and segmentation fields. The motion field is updated by estimating the minimum-norm residual field given the best estimate of the parametric field, under the constraint that motion field be smooth within each segment. The segmentation field is updated to yield the minimum-norm residual field given the best estimate of the motion field, using Gibbsian priors. The solution to successive optimization problems are obtained using the highest confidence first (HCF) or iterated conditional mode, (ICM) optimization methods. Experimental results on real video are shown.Keywords
This publication has 10 references indexed in Scilit:
- Representing moving images with layersIEEE Transactions on Image Processing, 1994
- Robust estimation of motion vector fields with discontinuity and occlusion using local outliers rejection1993
- Multimodal estimation of discontinuous optical flow using Markov random fieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1993
- Bayesian estimation of motion vector fieldsIEEE Transactions on Pattern Analysis and Machine Intelligence, 1992
- Object-oriented motion estimation and segmentation in image sequencesSignal Processing: Image Communication, 1991
- The theory and practice of Bayesian image labelingInternational Journal of Computer Vision, 1990
- Image segmentation based on object oriented mapping parameter estimationSignal Processing, 1988
- Scene Segmentation from Visual Motion Using Global OptimizationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1987
- An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image SequencesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1986
- Determining optical flowArtificial Intelligence, 1981