Motion Segmentation Algorithm using Spectral Framework

Authors

  • 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,

Downloads

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

License

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