Motion Based Background Subtraction and Extraction Using Decolor and K-Means Clustering for Providing Security
V. Eswari, T. Amruthavalli · 2014
Video surveillance systems have long been in use to monitor security sensitive areas. The making of video surveillance systems “smart” requires fast, reliable and robust algorithm for moving object detection, classification, tracking and activity analysis. Moving object detection is the basic step for further analysis of video. It handles segmentation of moving objects from stationary background objects. Object classification step categorizes detected objects into predefined classes such as human, vehicle, clutter etc. It is necessary to distinguish objects from each other in order to track and analyse their actions reliably. In previous system we have performed background subtraction by using Canny Edge Detection. In Canny Edge Detection process we are taking background image and foreground image for comparison. In previous strategies we are conducting background subtraction only for images. In proposed system the background subtraction is done for moving objects, we propose a pixel wise background modeling and subtraction technique using multiple features. Hence, in this colour, gradient and digital image features are integrated to handle the variation pixel. Then the detected image is send to the mobile through GSM modem as a message and the detected image can be viewed through mobile using the IP address.