Motion Detection and Segmentation Using Image Mosaics

Abstract

We propose a motion segmentation algorithm for extracting foreground objects with a pan-tilt camera. Segmentation is achieved by spatio-temporal filtering of the scene to model the background. Temporal filtering is done by a set of modified AR (Auto-Regressive) filters which model the background statistics for a particular view of the scene. Backgrounds from different views of the pan-tilt camera are stitched together into a planar mosaic using a real-time image mosaicing strategy. Our algorithms work in real-time, require no user intervention, and facilitate high-quality video transmission at low bandwidths.