Statistical context priming for object detection

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 contex- tual influences is still largely open. Here we introduce a simple probabilistic framework for modeling the relation- ship 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 ef- fective 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 accu- rately predict object locations and sizes.