A Novel Approach for Foreground Extraction Technique in Video Surveillance Systems
Anjanadevi B1, S Nagakishore Bhavanam2, E. Sreenivasa Reddy3
1Anjanadevi B, Research Scholar, Acharya Nagarjuna University, Guntur (A.P), India.
2Dr. S Nagakishore Bhavanam, Assistant Professor, Department of ECE, Acharya Nagarjuna University, Guntur (A.P), India.
3Dr. E Sreenivasa Reddy, Professor, Department of CSE, Acharya Nagarjuna University, Guntur (A.P), India.
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 174-177 | Volume-8 Issue-5, March 2019 | Retrieval Number: E2933238519/19©BEIESP
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: Everything in real word is monitored through surveillance cameras. Video surveillance is a critical tool for a variety of tasks such as law enforcement, personal safety, traffic control, resource planning, and security of assets. The widespread use of surveillance cameras in offices and other business establishments produces huge amount of data every second. The advent of large data is introducing important innovations like availability of additional external data sources, dimensions previously unknown and questionable consistency, poses new challenges to the worldwide spread of data sources (web, e-commerce, sensors). These collections of data sets having video frames which become difficult to process using traditional image processing applications. So, in this paper we propose a new foreground extraction technology using segmentation based on Skew Gaussian Mixture Model. The proposed model is more accurate than traditional approaches.
Keyword: Video Surveillance, Foreground Extraction, Background Subtraction, Illumination Changes, Segmentation, Skew Gaussian Mixture Model.
Scope of the Article: Expert Systems