Affiliations: [a] Department of Electronics and CommunicationEngineering, Sridevi Women’s Engineering College, JNTU Hyderabad, Telangana, India
| [b] Department of Electronics and CommunicationEngineering, R.M.K. Engineering College, India
| [c] Department of Electronics andCommunication Engineering, Sri Venkateswara College of Engineering, Sriperumpudur, India
| [d] Department of Electronics and CommunicationEngineering, Vinayaka Mission’s Kirupananda Variyar Engineering College, India
Correspondence:
[*]
Corresponding author. A. Prasanth, Department of Electronics and Communication Engineering, Sri Venkateswara College of Engineering, Sriperumpudur, India. E-mail: aprasanthdgl@gmail.com.
Abstract: Automatic moving object detection has gained increased research interest due to its widespread applications like security provision, traffic monitoring, and various types of anomalies detection, etc. In the video surveillance system, the video is processed for the detection of motion objects in a step-by-step process. However, the detection has become complex and less effective due to various complex constraints. To obtain an effective performance in the detection of motion objects, this research work focuses to develop an automatic motion object detection system based on the statistical properties of video and supervised learning. In this paper, a novel Background Modeling mechanism is proposed with the help of a Biased Illumination Field Fuzzy C-means algorithm to detect the moving objects more accurately. Here, the non-stationary pixels are separated from stationary pixels through the Background Subtraction. Afterward, the Biased Illumination Field Fuzzy C-means approach has accomplished to improve the segmentation accuracy through clustering under noise and varying illumination conditions. The performance of the proposed algorithm compared with conventional methods in terms of accuracy, precision, recall, and F- measure.
Keywords: Background modeling, fuzzy c-means, motion object detection, video surveillance system
