Litcius/Paper detail

An Efficient Fire Detection Method Based on Multiscale Feature Extraction, Implicit Deep Supervision and Channel Attention Mechanism

Songbin Li, Qiandong Yan, Peng Liu

2020IEEE Transactions on Image Processing138 citationsDOI

Abstract

Recent progress in vision-based fire detection is driven by convolutional neural networks. However, the existing methods fail to achieve a good tradeoff among accuracy, model size, and speed. In this paper, we propose an accurate fire detection method that achieves a better balance in the abovementioned aspects. Specifically, a multiscale feature extraction mechanism is employed to capture richer spatial details, which can enhance the discriminative ability of fire-like objects. Then, the implicit deep supervision mechanism is utilized to enhance the interaction among information flows through dense skip connections. Finally, a channel attention mechanism is employed to selectively emphasize the contribution between different feature maps. Experimental results demonstrate that our method achieves 95.3% accuracy, which outperforms the suboptimal method by 2.5%. Moreover, the speed and model size of our method are 3.76% faster on the GPU and 63.64% smaller than the suboptimal method, respectively.

Topics & Concepts

Computer scienceDiscriminative modelFeature extractionArtificial intelligenceConvolutional neural networkFeature (linguistics)Mechanism (biology)Channel (broadcasting)Pattern recognition (psychology)EpistemologyPhilosophyComputer networkLinguisticsFire Detection and Safety SystemsVideo Surveillance and Tracking MethodsIoT-based Smart Home Systems
An Efficient Fire Detection Method Based on Multiscale Feature Extraction, Implicit Deep Supervision and Channel Attention Mechanism | Litcius