The fire detection system gives a solution to detect fire in crowd event video and sets alarm for public safety in mass gatherings. The machine learning techniques are used to detect fire at initial stage from the input video and set alarm to avoid damages. The proposed system gets frames from input crowd video to detect fire. The RGB colour is converted into HSV (Hue, Saturation and Value) in each frame of video. Using Bitwise AND operation, the system detects the fire colour from the fire location. If any fire is occurred in a video, the fire is detected from specified frames of video. The specified frames are extracted from a video to find the location of fire. The fire detection system makes alarm sound for specified location of fire. Using GSM module, the system sends messages to controller of fired area. In the existing system, they used sensors and board for finding fire. But the proposed system detects the fire on video using computer vision based machine learning technique. Thus the fire detection system provides alarm for public safety with less cost compare with others.
Volume 11 | 02-Special Issue
Pages: 280-286