Abstract: Fire Detectors play a very important role in Industries, shops, Malls etc. They help in detecting fire or smoke at an early stage and can help in saving lives. In this project we designed Computer vision - based fire detection. In this model we use a webcam which is used as an alternative for surveillance cameras. If a fire is detected, alarm rings to alert people in that particular area and also a short duration of the live video is sent to the security of the building or the remote fire station through wireless LAN. Thus, the fire station could act immediately. In the Existing system they use a MATLAB tool for processing. In this project we use Open CV for processing, and its processing time is less. Using this project we can able to detect fire at early stage and can help the peoples. To avoid using sensors in fire detectors, false alarms can be avoided. By using this method, we can identify the number of people caught inside the room can be checked and rescuers

Keywords: Open CV, Fire detection ,Image processing ,False alarm

| DOI: 10.17148/IJIREEICE.2021.9206