When Convolutional Neural Networks Meet Remote Sensing Data for Fire Detection

In this paper, we present a novel end-to-end Dual Fire Detection Network (DFD-Net) for the remote sensing data fire detection task. The proposed network architecture consists of two streams in a parallel fashion, a fire estimate stream is used to detect fire pixels, and a cloud-water stream is built to exclude cloud and water regions. Moreover, the pixel and band attention modules adapted to characteristics of the remote sensing data are proposed. Experimental results on our prepared Himawari-8 data fire detection dataset with ground truth labels demonstrate that the proposed algorithm outperforms existed fire detection methods in various metrics.