Algorithm for Person Detection in Adaptive Background using Matlab Platform
Suryakant Kaiwart
Suryakant Kaiwart, Electronics & Telecommunication, CSVTU/BIT Durg, India.
Manuscript received on June 03, 2013. | Revised Manuscript received on June 29, 2013. | Manuscript published on July 05, 2013. | PP: 93-95 | Volume-3 Issue-3, July 2013. | Retrieval Number: C1629073313/2013©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: Detection of motion is the first essential process in the extraction of information in moving objects and makes use of stabilization in functional areas, such as tracking, classification, recognition, and so on. In this paper, we propose an approach to motion detection for the automatic visual surveillance system. Our method achieves complete detection of moving objects by involving three significant proposed modules: a background modeling module, a trigger module and an object extraction module. For our proposed first module, a unique two-phase background matching procedure is performed using rapid matching followed by accurate matching in order to produce optimum background pixels for the background model. Next, our proposed trigger module eliminates the unnecessary examination of the entire background region, allowing the subsequent third module to only process blocks containing moving objects. Finally, we get a moving object with subtracted background.
Keywords: Detection, extraction, surveillance, trigger.