Object detection under noisy condition

Abstract

Identifying moving objects from a video sequence is a fundamental and critical task in many computer-vision applications. Such automatic object detection soft wares have many applications in surveillance, auto navigation and robotics. A common approach is to perform background subtraction, which identifies the moving object from portion of video sequences. These soft wares work good under normal condition but tend to give false alarms when tested in real life conditions. Such a condition arises due to fog, smoke, glares ect. These situations are termed as noisy conditions and objects are detected under such conditions. In this paper we created noise by addition of standard Gaussian noise in clean video and compare the response of the detection system to various noise level. © 2010 American Institute of Physics.