International Journal of Advanced Information and Communication Technology


Real Time Object Tracking using Mean Shift Algorithm - A Review

Sadaf Khan, Sanjay L. Haridas, Sanjay. B. Tembhurne G. H. Raisoni Academy of Engineering and Technology, Nagpur, Maharashtra, India.

DOI : 01.0401/ijaict.2014.07.08

International Journal of Advanced Information and Communication Technology

Received On : July 20, 2016

Revised On : August 13, 2016

Accepted On : September 12, 2016

Published On : October 05, 2016

Volume 03, Issue 10

Pages : 572-574

Abstract


In the field of computer vision object tracking is one of the crucial research area. In order to evaluate the final tracking position of a target, target representation and locations are important. Mean shift algorithm is one of the accurate and fast objects tracking algorithm the modified mean shift algorithm which has been proposed here aims at continuous tracking in complex situations, such as the shape and the change in illumination of an object. The mean shift algorithm emphasizes on determining the object target region, and then a judgment on the tracking effect is made. In case of tracking failure, the object area is matched with the target model and a new track position is determined. Another option is to update target model periodically according to the state change of the moving object. Our emphasis will be there on experimentally showing that the proposed method can effectively track an object under the condition of varying illumination and shape deformation.

Keywords


Object Tracking, Mean Shift, Joint Color Histogram, LBP.

Cite this article


Sadaf Khan, Sanjay L. Haridas, Sanjay. B. Tembhurne, “Real Time Object Tracking using Mean Shift Algorithm - A Review” INTERNATIONAL JOURNAL OF ADVANCED INFORMATION AND COMMUNICATION TECHNOLOGY, pp.572-574, October 05, 2016.

Copyright


© 2016 Sadaf Khan, Sanjay L. Haridas, Sanjay. B. Tembhurne. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.