Real Time Object Tracking using Different Mean Shift Techniques–a Review
Snekha1, Chetna Sachdeva2, Rajesh Birok3
1Snekha, Electronics and Communication Department, Delhi Technological University, New Delhi, India.
2Chetna Sachdeva ,Electronics and Communication Department ,Delhi Technological University, New Delhi, India.
3Rajesh Birok , Associate professor ,Electronics and Communication Department, Delhi Technological University, New Delhi, India.
Manuscript received on June 03, 2013. | Revised Manuscript received on June 29, 2013. | Manuscript published on July 05, 2013. | PP: 98-102 | Volume-3 Issue-3, July 2013. | Retrieval Number: C1657073313/2013©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The many different mean shift techniques for object tracking in real time are discussed in this paper. The mean shift is a non-parametric feature space analysis technique. It is a method for finding local maxima of a density function from given discrete data samples.There are several approaches that use the mean shift techniques for locating target objects. These techniques are taken from the literature dating back to the earliest methods. It is shown that at least 07 distinct methods have been introduced in the literature, with many variations on implementation. This paper should serve as a convenient reference for future work in real time object tracking.
Keywords: Mean shift, CAM shift, ABC shift, Path assigned mean shift , SOAMST and Fuzzy clustering mean shift.