UNATTENDED OBJECT DETECTION

Abstract

Metropolitan cities are finding more problems to keeping the life secured from attacks even cities having security systems like number plate recognition and automatic traffic management, CCTV cameras installed etc. on roads. Many such bad incidences can be avoided by detecting some unattended objects placed on roads. Video surveillance system should be a sufficiently fast enabling a real-time performance. Thus, a prime goal of automated visual surveillance is to obtain a live description of what is happening in a monitored area and trigger appropriate action. Compounding the problem is that usually public areas under surveillance often have fluctuating and variable lighting conditions, people are frequently occluded by other people or structures, and people may temporarily leave a monitored area, etc. Variation in the light in scene area, size of the object, shadow in scene, distance of camera of system all these can add tremendous difficulty and delay. Here the proposed system described with basic description, Algorithm ideas for system operation. And it is verified with output results.
Key words: Background subtraction, brightness adjustment, classification of objects and humans, MATLAB, real-time video processing.