Vision based ?re detection is potentially a useful technique. With the increase in the number of surveillance cameras being installed, a vision based ?re detection capability can be incorporated in existing surveillance systems at relatively low additional cost. Vision based ?re detection offers advantages over the traditional methods. It will thus complement the existing devices. Conventional fire detection systems use physical sensors to detect fire. Chemical properties of particles in the air are acquired by sensors and are used by conventional fire detection systems to raise an alarm. However, this can also cause false alarms; for example, a person smoking in a room may trigger a typical fire alarm system. In order to manage false alarms of conventional fire detection systems, a computer vision-based fire detection algorithm is proposed in this paper. The proposed system consists of two main parts: fire color modeling and robot navigation. The algorithm can be used in parallel with conventional fire detection systems to reduce false alarms in order to rescue indoor appliances. It can also be deployed as a stand-alone system to detect fire by using video frames acquired through a video acquisition device. A fire color model is developed in RGB color space to identify fire pixels. The proposed fire color model is tested with video sequences captured in different illumination condition in indoor ambience. The experimental results are quite encouraging in terms of correctly classifying fire pixels according to color information only. In addition; the navigation of the robot is tested through a simulated environment.

False alarm RGB fire color model robot navigation