Advanced real time fire detection in video surveillance system

Development of automatic and intelligent video surveillance systems has been the core trend in the security and guard service industry. This paper presents a simple and effective algorithm for detecting the fire calamity event automatically in the monitoring area via real time video contents analysis. By observing and utilizing features of fire event, a fast and exact detection process is developed for early fire warning purpose thus to reduce the loss caused by fire accidents. The experimental results show that the proposed algorithm not only achieves real-time requirement and has better performance (more robust and correct) than the compared surveillance systems, but also attains the goal of alleviating the existing system cost efficiently.