Segmentation of Planar Objects and Their Shadows in Motion Sequences Article Received: 21 January 2005 Revised: 25 July 2005 Accepted: 27 July 2005 DOI:
Cite this article as: Yacoob, Y. & Davis, L. Int J Comput Vision (2006) 67: 53. doi:10.1007/s11263-006-3859-2 Abstract
We investigate segmentation of planar objects and their cast shadows in image sequences. Given two moving image regions in an image sequence we present an algorithm for determining if the two moving regions can be interpreted as a planar object and its cast shadow. Projective geometry and motion properties are employed to directly recover a homology that constrains point correspondences of the outlines of the image regions and determine if they obey an object/shadow relationship. This homology is derived directly from the motions of the regions and therefore is easier to accomplish than determining point-to-point correspondences between candidate object-shadow pairs. Several experiments under approximate point light source illumination are presented.
Keywords motion analysis shadow planar objects projective geometry homology
First online version published in February, 2006
Adiv. G. 1985. Determining three-dimensional motion and structure from optical flow generated by several moving objects.
Black, M. and Yacoob, Y. 1997. Tracking and recognizing rigid and non-rigid facial motions using local parametric models of image motions.
CrossRef Google Scholar
Cucchiara, R., Grana, C., Piccardi, M., and Prati, A. 2001. Detecting objects, shadows and costs in video streams by exploiting color and motion information. In
Proceedings of 11th International Conference on Image Analysis and Processing (ICIAP 2001).
Elgammal, A., Duraiswami, R., Harwood, D. and Davis. L.S. 2002. Background and Foreground Modeling using Non-parametric Kernel Density Estimation for Visual Surveillance,
Proceedings of the IEEE, 1151–1163.
Horprasert, T., Harwood, D., and Davis, L.S. 1999. A statistical approach for real-time robust background subtraction and shadow detection,
Proc. ICCV FRAME-RATE Workshop, Greece.
Longuet-Higgins, H.C. and Prazdny, K. 1980. The interpretation of a moving retinal image.
Proc. Royal Society of London, B
Mikic, I., Cosman, P.C. Kogut, G.T., and Trivedi. M.M. 2000. Moving shadow and object detection in traffic scenes.
Noronah, S. and Nevatia. R. 2001. Detection and modeling of buildings from multiple arial images.
Sonoda, Y. and Ogata. T. 1998. Separation of moving objects and their shadows, and applications to tracking of loci and monitoring images.
Proceedings of ICIP, 1261–1264.
Springer, C.E. 1964. Geometry and anlaysis of protective spaces, W.H. Freeman and Company.
Stauder, J., Mech, R., and Ostermann, J. 1999. Detection of moving cast shadows for object segmentation.
IEEE Trans.i on Multimedia
Subbarao, M. and Waxman, A.M. 1986. Closed form solutions to image flow equations for planar surfaces in motion.
Van Gool, L., Proesmans M., and Zisserman, A. 1998. Planar homologies as a basis for grouping and recognition,
Image and Vision Computing
Wolberg, G. 1990. Digital Image Warping.
IEEE Computer Society Press. Copyright information
© Springer Science + Business Media, Inc. 2006