Statistical context priming for object detection

A simple probabilistic framework for modeling the relationship between context and object properties is introduced, representing global context information in terms of the spatial layout of spectral components and serving as an effective procedure for context driven focus of attention and scale-selection on real-world scenes.

Abstract

There is general consensus that context can be a rich source of information about an object's identity, location and scale. However the issue of how to formalize centextual influences is still largely open. Here we introduce a simple probabilistic framework for modeling the relationship between context and object properties. We represent global context information in terms of the spatial layout of spectral components. The resulting scheme serves as an effective procedure for context driven focus of attention and scale-selection on real-world scenes. Based on a simple holistic analysis of an image, the scheme is able to accurately predict object locations and sizes.