Real-Time Fire Smoke Detection Method Combining a Self-Attention Mechanism and Radial Multi-Scale Feature Connection

• Published in: Sensors (Basel, Switzerland) Vol. 23; no. 6; p. 3358
• Main Authors: Jin, Chuan, Zheng, Anqi, Wu, Zhaoying, Tong, Changqing
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 22.03.2023; MDPI
• Subjects: Accuracy; Algorithms; Artificial intelligence; attention mechanism; cross-grid matching strategy; Deep learning; Design; Design and construction; Fire detectors; fire smoke detection; Machine learning; Machine vision; multi-scale feature; Neural networks; Permutations; Photoelectricity; radial connection; Real time; Semantics; Sensors; Smoke; weighted decay; China; multi-scale feature; attention mechanism; weighted decay; radial connection; fire smoke detection; cross-grid matching strategy
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s23063358

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.