Occlusion Detection with Background Elimination and Moving Object Tracking
K. Padmapriya1, P.V. Gopirajan2, K.Suresh Kumar3
1Dr.K.Padmapriya, Assistant Professor(SG), Department of Computer Science and Engineering, Saveetha School of Engineering, Chennai, India.
2Mr.Gopirajan.P.V, Assistant Professor(SG), Department of Computer Science and Engineering, Saveetha Engineering College, Chennai, India.
3Dr.K.Suresh Kumar*, Associate Professor, Department of Information Technology, Saveetha Engineering College, Chennai, India.
Manuscript received on November 19, 2019. | Revised Manuscript received on November 29 2019. | Manuscript published on 30 November, 2019. | PP: 9248-9252 | Volume-8 Issue-4, November 2019. | Retrieval Number: D9287118419/2019©BEIESP | DOI: 10.35940/ijrte.D9287.118419
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© 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: An occlusion is said to be a situation when few parts of an object cannot be viewed by human vision. Detecting an object is quite difficult to identify and not so easy to track the moving objects during occlusion. It can be achieved in two steps. The first step is to identify the foreground or background image frame by frame, by naming each and every pixel in the frame. The next step is to compare the observations at each point in the sequence of the moving object with occlusion. It can be done by subtracting the background which yields pixel as combination of Gaussians. Then the distribution of Gaussian have to be calculated to conclude the result from the background process. This method is very much useful to identify the motions in surveillance camera, repeated suspicious movement and elongated changes in the scene. Keywords:
Keywords: Occlusion, Gaussian, Human Vision, Image Processing.
Scope of the Article: Signal and Image Processing.