TY - GEN

T1 - Detection and Removal of Chromatic Moving Shadows in Surveillance Scenarios<em/>

A1 - Casado,Ivan Huerta

A1 - Holte,Michael Boelstoft

A1 - Moeslund,Thomas B.

A1 - Gonzàlez,Jordi

AU - Casado,Ivan Huerta

AU - Holte,Michael Boelstoft

AU - Moeslund,Thomas B.

AU - Gonzàlez,Jordi

PB - IEEE

PY - 2009

Y1 - 2009

N2 -   <p>Segmentation in the surveillance domain has to deal with shadows to avoid distortions when detecting moving objects. Most segmentation approaches dealing with shadow detection are typically restricted to penumbra shadows. Therefore, such techniques cannot cope well with umbra shadows. Consequently, umbra shadows are usually detected as part of moving objects. In this paper we present a novel technique based on gradient and colour models for separating chromatic moving cast shadows from detected moving objects. Firstly, both a chromatic invariant colour cone model and an invariant gradient model are built to perform automatic segmentation while detecting potential shadows.</p><p>In a second step, regions corresponding to potential shadows are grouped by considering "a bluish effect" and an edge partitioning.</p><p>Lastly, (i) temporal similarities between textures and (ii) spatial similarities between chrominance angle and brightness distortions are analysed for all potential shadow regions in order to finally identify umbra shadows. Unlike other approaches, our method does not make any a-priori assumptions about camera location, surface geometries, surface textures, shapes and types of shadows, objects, and background. Experimental results show the performance and accuracy of our approach in different shadowed materials and illumination conditions.</p>

AB -   <p>Segmentation in the surveillance domain has to deal with shadows to avoid distortions when detecting moving objects. Most segmentation approaches dealing with shadow detection are typically restricted to penumbra shadows. Therefore, such techniques cannot cope well with umbra shadows. Consequently, umbra shadows are usually detected as part of moving objects. In this paper we present a novel technique based on gradient and colour models for separating chromatic moving cast shadows from detected moving objects. Firstly, both a chromatic invariant colour cone model and an invariant gradient model are built to perform automatic segmentation while detecting potential shadows.</p><p>In a second step, regions corresponding to potential shadows are grouped by considering "a bluish effect" and an edge partitioning.</p><p>Lastly, (i) temporal similarities between textures and (ii) spatial similarities between chrominance angle and brightness distortions are analysed for all potential shadow regions in order to finally identify umbra shadows. Unlike other approaches, our method does not make any a-priori assumptions about camera location, surface geometries, surface textures, shapes and types of shadows, objects, and background. Experimental results show the performance and accuracy of our approach in different shadowed materials and illumination conditions.</p>

KW - Background Subtraction

KW - colour segmentation

KW - computer vision

KW - edge segmentation

KW - ICCV 2009

KW - image processing

KW - motion segmentation

KW - shadows

KW - temporal difference

KW - video surveillance

SN - 9781424444199

BT - International Conference on Computer Vision

T2 - International Conference on Computer Vision

ER -