Early Fire Detection Using HEP and Space-time Analysis

—In this article, a video base early fire alarm system is developed by monitoring the smoke in the scene. There are two major contributions in this work. First, to find the best texture feature for smoke detection, a general framework, named Histograms of Equivalent Patterns (HEP), is adopted to achieve an extensive evaluation of various kinds of texture features. Second, the Block based Inter-Frame Difference (BIFD) and a improved version of LBP-TOP are proposed and ensembled to describe the space-time characteristics of the smoke. In order to reduce the false alarms, the Smoke History Image (SHI) is utilized to register the recent classification results of candidate smoke blocks. Experimental results using SVM show that the proposed method can achieve better accuracy and less false alarm compared with the state-of-the-art technologies. I. INTRODUCTION As one of the leading hazards, fire causes grave losses of life and property around the world each year. In order to detect and eliminate fire at very early stage, during the past decades, different kinds of technologies are developed by researchers. However, traditional methods usually depend on heat sensors, optical sensors (ultraviolet , infrared), ion sensors, or thermocouples. These sensors suffer from the transport delay of the fire (heat or smoke particles) to the sensor, and cannot work effectively if the fire is far away. Moreover, these sensors can not provide the situation and development of the fire for validation and rescue. With the increasingly wide usage of video surveillance systems, in recent years, video based fire detection technologies received much attentions from researchers. Smoke is usually generated before flames and can be observed from a great distance, it is an important sign for early fire detection. Since the video camera can accomplish real-time monitoring in a large range, the smoke of uncontrolled fire can be easily observed by