Detection of Cast Shadows in Surveillance Applications

Abstract

Cast shadows from moving objects reduce the general ability of robust classi cation and tracking of these objects, in outdoor surveillance applications. A method for segmentation of cast shadows is proposed, combining statistical features with a new similarity feature, derived from a physics-based model. The new method is compared to a reference method, and found to improve performance signi cantly, based on a test set of real-world examples.

Extracted Key Phrases

7 Figures and Tables

Cite this paper

@inproceedings{Erbou2005DetectionOC, title={Detection of Cast Shadows in Surveillance Applications}, author={S\oren G. H. Erbou and Helge B. D. S\orensen and Bjarne Stage}, year={2005} }