Affiliation:
1. School of Sciences, Hangzhou Dianzi University, Hangzhou 310018, China
2. Southeast-Monash Joint Graduate School, Southeast University, Suzhou 210096, China
Abstract
Fire remains a pressing issue that requires urgent attention. Due to its uncontrollable and unpredictable nature, it can easily trigger chain reactions and increase the difficulty of extinguishing, posing a significant threat to people’s lives and property. The effectiveness of traditional photoelectric- or ionization-based detectors is inhibited when detecting fire smoke due to the variable shape, characteristics, and scale of the detected objects and the small size of the fire source in the early stages. Additionally, the uneven distribution of fire and smoke and the complexity and variety of the surroundings in which they occur contribute to inconspicuous pixel-level-based feature information, making identification difficult. We propose a real-time fire smoke detection algorithm based on multi-scale feature information and an attention mechanism. Firstly, the feature information layers extracted from the network are fused into a radial connection to enhance the semantic and location information of the features. Secondly, to address the challenge of recognizing harsh fire sources, we designed a permutation self-attention mechanism to concentrate on features in channel and spatial directions to gather contextual information as accurately as possible. Thirdly, we constructed a new feature extraction module to increase the detection efficiency of the network while retaining feature information. Finally, we propose a cross-grid sample matching approach and a weighted decay loss function to handle the issue of imbalanced samples. Our model achieves the best detection results compared to standard detection methods using a handcrafted fire smoke detection dataset, with APval reaching 62.5%, APSval reaching 58.5%, and FPS reaching 113.6.
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference64 articles.
1. Real-time multi-feature based fire flame detection in video;Chi;IET Image Process.,2017
2. Video fire detection–review;Cetin;Digit. Signal Process.,2013
3. Forest fire smoke recognition based on convolutional neural network;Sun;J. For. Res.,2021
4. Surf: Speeded up robust features;Bay;Lect. Notes Comput. Sci.,2006
5. Chiew, K., and Wang, Y. (2006, January 7–11). Shape feature representation in partial object matching. Proceedings of the 2006 International Conference on Computing & Informatics, Vilnius, Lithuania.
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献