Surveillance Rendering

With: Adrian Illie and Ramesh Raskar

Abstract

We propose a class of image enhancement techniques suitable for scenes captured by fixed cameras. The basic idea is to increase the information density in a set of low quality images by exploiting the context from a higher quality image captured under different illumination from the same view. For example, a nighttime surveillance video is enriched with information available in daytime images.

The paper will be published at International Journal on Pattern Recognition and Artificial Intelligence. A short version of the paper was published at ACCV 2004. See also a video demo of our work.