Paper title

“Graph-Based Segmentation of Moving Objects”

Authors: Aliakbar Darabi , Amir Hossein Khalili and Shohreh Kasaei
Affiliation
: Image Processing Lab, Department of Computer Engineering, Sharif University of Technology, Tehran, Iran

Abstract — This paper addresses the problem of segmentation of moving objects in image sequences. A graph-based algorithm is introduced to separate the moving layers from the background. By using this method, the problem of contributing spatial and temporal global properties into segmentation of moving objects is handled. In addition, the complexity of segmentation procedure is reduced so that it can be used in real-time applications. The superiority of the proposed algorithm is shown by evaluating the results obtained from our approach and the latest similar methodologies. This assessment is done in both subjective measurement and complexity aspects.