Anzeige
Erschienen in:
2013 | OriginalPaper | Buchkapitel
Shadow Detection Method Based on Shadow Model with Normalized Vector Distance and Edge
verfasst von : Shuya Ishida, Shinji Fukui, Yuji Iwahori, M. K. Bhuyan, Robert J. Woodham
Erschienen in: Computer and Information Science
Verlag: Springer International Publishing
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by (Link öffnet in neuem Fenster)
An object detection method needs a shadow detection because shadows often have a harmful effect on the result. Shadow detection methods based on shadow models are proposed. A new shadow model is proposed in this paper. The proposed model is constructed by the differences of UV components of YUV color space between the background image and the observed image, Normalized Vector Distance and edge information. The difference of Y component is less suitable for the model because it varies considerably with location. The proposed model includes Normalized Vector Distance instead of Y component. It is a robust feature to illumination changes and can remove a shadow effect in part. The proposed method can obtain shadow regions more accurately by including Normalized Vector Distance in the shadow model. Results are demonstrated by the experiments using the real videos.
