#13: Coupled, multi-resolution stereo and motion analysis


Abstract

We propose a novel approach for fusing multi- resolution stereo and motion (both rigid and non-rigid) analysis in order to complement each other’s perfor- mance. A hierarchical frame-work is presented to couple motion correspondences and stereo correspon- dences in order to generate accurate disparity map and motion parameters. One scenariofor such system is the analysis of time-varying multa-spectral obser- vations of clouds from meteorological satellites. Our experiments involve such time-varying remote sens- ing stereo data sets, and the motion is typically non- rigid as the clouds undergo shape changes. Rigid mo- tion matching may still be performed for initial fu- sion, and gradually raised to non-rigid motion match- ing as in a coarse-to-fine strategy. Both stereo dis- parities and motion correspondences are estimated us- ing such multi-resolution coarse-to-fine strategy to a sub-pixel accuracy. Experimental results using time- varying data of visible channel from two satellites in geosynchronous orbit is presented for the Hurricane Fred eri e.