Abstract
Affine motion model is widely used in motion segmentation. This paper gives an approach for moving object segmentation by using Fuzzy C-Means clustering on Affine parameters. Here this algorithm has been simulated in Matlab. Fuzzy C-Means clustering has been applied on the affine parameters of the pixels. Affine parameters have been calculated from Optical Flow data. Here Lucas Kanade method has been used for Optical flow Velocity calculation. Comparison of proposed method with respect to K-Means clustering segmentation method has been presented. By proposed method reduction in segmentation computation time has been achieved to almost half of the time compared to K-Means clustering segmentation. Segmentation output of the proposed method on the test video flower.yuv has produced good results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barron, J.L., Fleet, D.J., Beauchemin, S.S.: Performance of Optical Flow Techniques. International Journal of Computer Vision, 43–77 (1994)
Barron, J.L., Thacker, N.A.: 2D and 3D Optical Flow, Imaging Science and Biomedical Engineering, University of Manchester (2005)
Wang, J.Y.A., Adelson, E.H.: Representing Moving Images with Layers. IEEE Trans. on Image Processing 3(5), 625–638 (1994)
Borshukov, G.D., Bozdagi, G., Altunbasak, Y., Tekalp, A.M.: Motion Segmentation by Multistage Classication. IEEE Transactions on Image Processing 6(11), 1591–1594 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Bhandari, V., B.R., K., M.M., K. (2011). Moving Object Segmentation Using Fuzzy C-Means Clustering Affine Parameters. In: Venugopal, K.R., Patnaik, L.M. (eds) Computer Networks and Intelligent Computing. ICIP 2011. Communications in Computer and Information Science, vol 157. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-22786-8_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-22786-8_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-22785-1
Online ISBN: 978-3-642-22786-8
eBook Packages: Computer ScienceComputer Science (R0)