In this work, we address the detection of vehicles in a video stream obtained from a moving airborne platform. We propose a Bayesian framework for estimating dense optical flow over time that explicitly estimates a persistent model of background appearance. The approach assumes that the scene can be described by background and occlusion layers, estimated within an expectation-maximization framework. The mathematical formulation of the paper is an extension of the work in (H. Yalcin et al., 2005) where motion and appearance models for foreground and background layers are estimated simultaneously in a Bayesian framework.
A flow-based approach to vehicle detection and background mosaicking in airborne video
2005-01-01
126064 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Hyperspectral Mosaicking, Coregistration and Change Detection
British Library Conference Proceedings | 1998
|Digital mosaicking of underwater imagery
Tema Archiv | 1999
|Image Mosaicking for Estimating the Motion of an Underwater Vehicle
British Library Conference Proceedings | 2001
|