Fire detection based on video processing method

Because of huge damage caused by fire, the early fire detection becomes more and more important. With the rapid development of image and video processing, the fire detection technology based on video processing is becoming the focal point of some research due to its advantages of high intuitive, speed and anti-jamming capability. In this paper, we propose a method for early fire detection based on region growing. This method uses colour and motion information extracted from video sequences to detect fire. It can work both indoors and outdoors. Moreover, it detects fire at the beginning of the burning process, enabling an early response than would be possible with a conventional fire detector. The method performs the region growing segmentation to identify colour pixels in the scene and then identify moving pixels based on the ratio of height and width of suspected fire region and correlation coefficient. This method can get low false alarm rate by eliminating the fire-like colours because it just needs a fire pixel as the seed pixel.