Abstract
Disparity information enables a multi-layered representation of a video frame. But how to extract object attracting the users’ interest is still to be considered. Based on the definition and estimation of image disparity, we propose an approach to segment video objects for video conference. Chrominance, luminance, position and other information are introduced to compute the saliency map, and the edge information is used to obtain the disparity map. Combining with the disparity estimation results, the layer representing the most interested object that contains most of conspicuity values can be easily segmented. The experimental results demonstrate this algorithm is capable of segmenting video object from sequences quite effectively.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Garrido, L., Marques, F., Pardas, M., Salembier, P., Vilaplana, V.: A hierarchical technique for image sequence analysis. In: Proc. Workshop Image Analysis for Multimedia Interactive Services (WIAMIS), Louvain-la-Neuve, Belgium, June 1997, pp. 13–20 (1997)
Wei, W., Ngan, K.N.: Disparity estimation with edge-based matching and interpolation. In: IEEE International Symposium on Intelligent Signal Processing and Communications Systems, Hong Kong SAR, China, December 2005, pp. 153–156 (2005)
Chai, D., Ngan, K.N.: Face segmentation using skin-color map in videophone applications. IEEE Trans. On Circuits and System for Video Technology 9, 551–564 (1999)
Habili, N., Lin, C.C., Moini, A.: Segmentation of the Face and Hands in Sign Language Video Sequences Using Color and Motion Cues. IEEE Trans. On Circuits and System for Video Technology 8, 1086–1097 (2004)
Li, H., Ngan, K.N.: Face Segmentation in Head-and-Shoulder Video Sequences Based on Facial Saliency Map. In: IEEE International Symposium on Circuit and Systems (2006)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Xingming, O., Wei, W. (2009). Video Object Segmentation Based on Disparity. In: Chen, L., et al. Advances in Web and Network Technologies, and Information Management. APWeb WAIM 2009 2009. Lecture Notes in Computer Science, vol 5731. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-03996-6_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-03996-6_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-03995-9
Online ISBN: 978-3-642-03996-6
eBook Packages: Computer ScienceComputer Science (R0)