Early Fire Detection for Coal Mine Based on Double Band Image Processing

摘要

Fire is one of the great threaten for human security in coal mine. The previous temperature-sensed and smokesensed method can't respond quickly to early fire, and fire may not immediately be detected if it is far away from the sensors. Therefore, double band infrared vision-based fire detection is adopted to overcome the drawbacks of traditional detection equipment for coal mine. Firstly, region partition algorithm is proposed, which improves the recognition efficiency. The flame features are extracted and normalized, then a BP neural network model is established for recognition combined with image processing. The experimental results demonstrate that the proposed method can distinguish dangerous fire flame effectively and improve the accuracy. In addition, it drastically reduces the false alarms issued to traditional approach. It has strong robust and short response time.