ESTIMATION OF 2D ILLUMINANT DIRECTION AND SHADOW SEGMENTATION IN NATURAL VIDEO SEQUENCES

This paper presents a new method to estimate in natural video sequences the position of the projection of the light source in the image plane and a shadow segmentation of previously segmented video objects. The proposed method is based on simple geometric constraints between the object, its shadow and the light source location. It requires the segmentation of video objects during the sequence, but without any assumptions on its surface. Furthermore, this method is applied to video post-production applications such as the insertion and the suppression of video objects in original sequences. The method has been tested and validated on natural and synthetic scenes.

[1]  Jörn Ostermann,et al.  Detection of Moving Cast Shadows for Object Segmentation , 1999, IEEE Trans. Multim..

[2]  S. M. Steve.  SUSAN - a new approach to low level image processing , 1997 .

[3]  Claire-Lise Mottaz Jiang,et al.  Shadow segmentation and classification in a constrained environment , 1994 .

[4]  Naoki Mukawa.  Estimation of shape, reflection coefficients and illuminant direction from image sequences , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[5]  Michael J. Brooks,et al.  Shape and Source from Shading , 1985, IJCAI.

[6]  Alan L. Yuille,et al.  Sources from shading , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  A. Pentland.  Finding the illuminant direction , 1982 .

[8]  Rama Chellappa,et al.  Estimation of Illuminant Direction, Albedo, and Shape from Shading , 1991, IEEE Trans. Pattern Anal. Mach. Intell..