Attention based CNN model for fire detection and localization in real-world images

作者：

Highlights：

• A custom deep learning framework for detecting fire in real-world images.

• Attention mechanism and transfer learning is used with EfficientNetB0 trained.

• Framework uses Grad-CAM method for visualization and localization of fire.

• High recall of 97.61 supports the reliability of model for fire detection task.

摘要

•A custom deep learning framework for detecting fire in real-world images.•Attention mechanism and transfer learning is used with EfficientNetB0 trained.•Framework uses Grad-CAM method for visualization and localization of fire.•High recall of 97.61 supports the reliability of model for fire detection task.

论文关键词：Fire detection,CNN,Attention mechanism,Transfer learning,Grad-CAM

论文评审过程：Received 18 September 2021, Revised 14 October 2021, Accepted 16 October 2021, Available online 26 October 2021, Version of Record 28 October 2021.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116114