Detection of Cast Shadows in Surveillance Applications

Søren G. Erbou, Helge Bjarne Dissing Sørensen, Bjarne Stage

    Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearch

    340 Downloads (Pure)


    Cast shadows from moving objects reduce the general ability of robust classification 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 significantly, based on a test set of real-world examples.
    Original languageEnglish
    Title of host publicationDen 14. Danske Konference i Mønstergenkendelse og Billedanalyse
    PublisherInformatics and Mathematical Modelling, Technical University of Denmark, DTU
    Publication date2005
    Publication statusPublished - 2005

    Cite this