Tracking the Human Motion in Real Time using Star Skeleton Model
B. Muthukumar1, S.Ravi2
1B. Muthukumar, Associate Professor, Department of Information Technology, Kathir College of Engineering, Coimbatore, Tamilnadu, India.
2Dr. S. Ravi, Professor, Department of ECE, Dr. MGR University, Chennai Tamilnadu, India.
Manuscript received on January 17, 2012. | Revised Manuscript received on February 05, 2012. | Manuscript published on February 29, 2012. | PP: 1-3 | Volume-1 Issue-3, February 2012. | Retrieval Number: C0200021312/2011©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. 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: Human motion analysis is receiving increasing attention from researchers. This interest is motivated by wide spectrum of applications. In this paper, a process is described for detecting moving targets and extracting boundaries. From these, “star” skeleton is produced. The star skeletonization is suitable for detecting and analyzing human motion in real time. Also the method does not require great deal of image-based information to work efficiently. Extremal points are extracted in star skeleton like head, hands and legs, their tracking described based on an n block of DCTs coefficient. Then we correct the false tracked extremal points such as occluded extremal points.
Keywords: Human Detection, Image Processing, Occlusion Removal.