Fire Flame Detection in Tunnel Based on Halcon and ResNet50

Fires in tunnels have the problem of difficult detection and rescue. Thus, fire monitoring is crucial for prompt discovery of fires. Aiming at the problems of high false detection rate of traditional tunnel fire detection methods, a flame detection method based on Halcon and ResNet50 is designed. Gamma decoding is used for image preprocessing. The gamma decoding reduces the details of the dark part in the image and highlights the flame part. With the help of ResNet50 network, the flame after pretreatment is detected. The experimental result shows that the method has high recall and precision. This method provides an important reference value for the design of tunnel fire monitoring system.