Development of an Intelligent Eye for Automatic Surveillance Based on Sound Recognition

In surveillance or homeland security most of the systems aiming to automatically detect abnormal situations are only based on visual clues while, in some situations, it may be easier to detect a given event using the audio information. A new platform for sustainable development of automatic surveillance is introduced based on intelligent eye system which gathers information of human behavior, activities and environmental changes. The present research deals with audio events detection in noisy environments for surveillance application. The increasing availability of forensic audio surveillance recordings covering days or weeks of time makes human audition impractical and error prone. The ability of a normal human listener to recognize objects in the environment from only the sounds they produce is extraordinarily robust even in adverse acoustic conditions. In this research, we have developed a surveillance system which can recognize sound sources and detect events. This system can cover large area which is cost efficient. Sound sources can be recognized by comparing the frequency of sounds. This proposed intelligent eye system can recognize different sound sources accurately in real time and pretty much quick.