Motion analysis of Omni-Directional video streams for a mobile sentry

Abstract

A mobile platform mounted with Omni-Directional Vision Sensor (ODVS) can be used to monitor large areas and detect interesting events such as independently moving persons and vehicles. To avoid false alarms due to extraneous features, the image motion induced by the moving platform should be compensated. This paper describes a formulation of parametric ego-motion compensation for an ODVS. Omni images give 360 degrees view of surroundings but undergo considerable image distortion. To account for these distortions, the parametric planar motion model is integrated with the transformations into omni image space. Prior knowledge of approximate camera calibration and vehicle speed are integrated with the estimation process using Bayesian approach. Iterative, coarse to fine, gradient based estimation is used to correct the motion parameters for vibrations and other inaccuracies in prior knowledge. Experiments with camera mounted on a mobile platform demonstrate successful detection of moving persons and vehicles.