Background Modeling and Subtraction Based People Counting for Real Time Video Surveillance
Rakesh Kumar1, Tapesh Parashar2, Gopal Verma3
1Rakesh Kumar, Director, KS Jain Engineering College, Modinagar, U.P., India.
2Tapesh Parashar, Associate Professor, Vishveshwarya Institute of Technology, G.B.Nagar, U.P., India
3Gopal Verma, Associate Professor, Sunderdeep Engineering College, Ghaziabad, U.P., India
Manuscript received on November 01, 2012. | Revised Manuscript received on November 02, 2012. | Manuscript published on November 05, 2012. | PP: 100-102 | Volume-2 Issue-5, November 2012. | Retrieval Number: E1006102512/2012©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: This paper presents a multiple people counting using only single camera, entering or exiting in a region of interest. Sigma-Delta background modeling and subtraction is used to segment the people from region. Background subtraction provides blobs as a result with connected component. CG of blobs was used to track and count the entry and exit of people. This paper also proposed method for counting two or more people based on blob size and distance between floor and camera. People will be counted if and only if they passed through the three regions consecutively. Experiments shows that proposed method is robust and provides approximate accurate counts
Keywords: Edge based Local Thresholding, Background Subtraction, Mathematical Morphological Processes, Connected Component.