ATT Squeeze U-Net: A Lightweight Network for Forest Fire Detection and Recognition

• Published in: IEEE access Vol. 9; pp. 10858 - 10870
• Main Authors: Zhang, Jianmei, Zhu, Hongqing, Wang, Pengyu, Ling, Xiaofeng
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: attention U-Net; Coders; Convolution; Ecological effects; Encoders-Decoders; Feature extraction; fire module; Forest fire detection; Forest fire detection and recognition; Forestry; Image color analysis; Image segmentation; light-weight network; Modules; Natural disasters; Shape; SqueezeNet; Task analysis
• DOI: 10.1109/ACCESS.2021.3050628
• ISSN: 2169-3536

Forest fire is becoming one of the most significant natural disasters at the expense of ecology and economy. In this article, we develop an effective SqueezeNet based asymmetric encoder-decoder U-shape architecture, Attention U-Net and SqueezeNet (ATT Squeeze U-Net), mainly functions as an extractor and a discriminator of forest fire. This model takes attention mechanism to highlight useful features and suppress irrelevant contents by embedding Attention Gate (AG) units in the skip connection of U-shape structure. In this way, salient features are emphasized so that the proposed method could be competent at forest fire segmentation tasks with a small number of parameters. Specifically, we first replace classical convolution layer by a depthwise one and engage a Channel Shuffle operation as a feature communicator in the Fire module of classical SqueezeNet. Then, this modified SqueezeNet is employed as a substitution of the encoder of Attention U-Net and a corresponding DeFire module designed is combined into the decoder as well. Finally, to classify true fire, we take use of a fragment of the encoder in ATT Squeeze U-Net. The experimental results of modified SqueezeNet integrated Attention U-Net show that a competitive accuracy at 0.93 and an average prediction time at 0.89 second per image are achieved for reliable real-time forest fire detection.