Abstract:

An algorithm of early oil fire image detection and recognition is put forward. The flame color, brightness and movement characteristics are chosen as the criteria. The early oil fire images are further detected and recognized by the algorithm of the Discrete Fractal Brownian Incremental Random Field model based on an analysis of the flame model and the differential model. The results of the simulated tunnel experiments show that the algorithm can successfully detect and recognize oil fire.

Key words: oil fire image;flame model;differential model;discrete fractal brownian incremental random field model (DFBIR)