Fire detection method of mine belt conveyor based on Artificial Bee Colony algorithm

Abstract

The detection of fire on mine belt conveyor is very difficult in traditional image processing method, a novel image processing method is proposed in this paper, which integrates Artificial Bee Colony algorithm, gray scale morphology and information entropy. In Artificial Bee Colony algorithm the best threshold is approached in parallel via the division of labor, cooperation and information sharing of employed bees, onlookers and scouts. The fitness function of Artificial Bee Colony algorithm is designed by 2D maximum entropy method and fire image thresholds are regarded as nectar source. In order to reduce image noise the close operation is applied based on gray scale morphology. Theory analysis and simulation experimental results indicate that the proposed method is useful to detect fire of mine belt conveyor in complex coal under ground environment.