Motion Segmentation Algorithm using Spectral Framework

  • Vrinthavani R Center for Airborne Systems, Hyderabad
  • M.R. Kaimal Amrita Vishwa Vidyapeetham University, Kollam
DOI: https://doi.org/10.14429/dsj.60.102

Abstract

This paper presents a new motion segmentation method using iterative maximum likelihood framework. The method consists of two steps. In the first step, motion regions are detected and motion vectors are computed for these detected regions. In the second step, a similarity matrix is computed from the motion vectors and motion segmentation is done using maximum likelihood method. The method has been tested using real world motion sequences and is found to give very low error rate and it also detects the slow moving objects.

Defence Science Journal, 2010, 60(1), pp.39-47, DOI:http://dx.doi.org/10.14429/dsj.60.102

Author Biographies

Vrinthavani R, Center for Airborne Systems, Hyderabad
Center for Airborne Systems, DRDO, Hyderabad
M.R. Kaimal, Amrita Vishwa Vidyapeetham University, Kollam
Dept. of Computer Science & Engg, Amrita Vishwa Vidyapeetham University, Kollam, Kerala,
Published
2010-03-25
How to Cite
R, V., & Kaimal, M. (2010). Motion Segmentation Algorithm using Spectral Framework. Defence Science Journal, 60(1), 39-47. https://doi.org/10.14429/dsj.60.102
Issue
Vol 60 No 1: Mobile Intelligent Autonomous Systems
Section
Review Papers
Copyright (c) 2016 Defence Science Journal

 Where otherwise noted, the Articles on this site are licensed under Creative Commons License: CC Attribution-Noncommercial-No Derivative Works 2.5 India