摘要：To avoid the drawbacks caused by the long-distance and large-area features of the outdoor forest fires in the traditional fire detection methods. A new forest fire recognition method based on the neural network is proposed, which recognizes the fire based on the static and dynamic features of the fire. The method combines the multiple parameters of the flames and the shapes of the fire to distinguish fire image. Then the extracted features were tested by the Back Propagation Neural Network. The experiment results show that the method outperforms in terms of the recognition rate, recognition speed, and the Anti-jamming capability compared with the traditional fire recognition method. Thus, the results illustrate the validity and the generalizability of the method.
