ABSTRACT
The goal of motion segmentation is to segregate a visual scene into independently moving objects. It is an indispensable pre-processing step for various tasks in computer vision and has evolved as an active and flourishing research area in the last few decades. In the sequences captured using a monocular camera, motion segmentation is typically performed by analyzing apparent motion of pixels in the image plane, i.e. the optical flow. Optical flow is generally contemplated as an appropriate representation of image motion. Numerous techniques for reliable flow estimation and subsequent advancements in their framework have been proposed in the last couple of decades and are outlined briefly in this work. The paper attempts to give a summary of diverse optical flow-based approaches used for robust segmentation of static or dynamic scenes containing rigidly moving objects and discusses in brief the shortcomings associated with them.
Acknowledgement
The authors are deeply indebted to the anonymous reviewers whose comments led to appropriate and meaningful changes in the originally submitted manuscript and in the process enabled authors to have a better understanding of the concepts discussed in this paper.
Disclosure statement
No potential conflict of interest was reported by the authors.
Notes on contributors
Shivangi Anthwal is currently a Ph.D. candidate at the department of Applied Science and Humanities, Indira Gandhi Delhi Technical University for Women, Delhi. Her research interests include computer vision, visual motion analysis, artificial intelligence and machine learning.
Dinesh Ganotra has done his Ph.D. from Indian Institute of Technology, Delhi and post doc from University of Arizona, USA. He is currently working as an Assistant Professor at Indira Gandhi Delhi Technical University for Women, Delhi. His research interests include digital image processing, computer vision, neural networks, pattern recognition and speech processing.