Channel Attention for Fire and Smoke Detection: Impact of Augmentation, Color Spaces, and Adversarial Attacks
Open Access
Abstract
The prevalence of wildfires presents significant challenges for fire detection systems, particularly in differentiating fire from complex backgrounds and maintaining detection reliability under diverse environmental conditions. It is crucial to address these challenges for developing sustainable and effective fire detection systems. In this paper: (i) we introduce a channel-wise attention-based architecture, achieving 95% accuracy and demonstrating an improved focus on flame-specific features critical for distinguishing fire in complex backgrounds. Through ablation studies, we demonstrate that our channel-wise attention mechanism provides a significant 3–5% improvement in accuracy over the baseline and state-of-the-art fire detection models; (ii) evaluate the impact of augmentation on fire detection, demonstrating improved performance across varied environmental conditions; (iii) comprehensive evaluation across color spaces including RGB, Grayscale, HSV, and YCbCr to analyze detection reliability; and (iv) assessment of model vulnerabilities where Fast Gradient Sign Method (FGSM) perturbations significantly impact performance, reducing accuracy to 41%. Using Local Interpretable Model-Agnostic Explanations (LIME) visualization techniques, we provide insights into model decision-making processes across both standard and adversarial conditions, highlighting important considerations for fire detection applications.Keywords
Funding Information
- Sangmyung University
This publication has 38 references indexed in Scilit:
- Optimized cross-module attention network and medium-scale dataset for effective fire detectionPattern Recognition, 2024
- Enhancing real-time fire detection: an effective multi-attention network and a fire benchmarkNeural Computing and Applications, 2023
- An Effective Attention-based CNN Model for Fire Detection in Adverse Weather ConditionsISPRS Journal of Photogrammetry and Remote Sensing, 2023
- FSDF: A high-performance fire detection frameworkExpert Systems with Applications, 2023
- Quantifying the effectiveness of shaded fuel breaks from ground-based, aerial, and spaceborne observationsForest Ecology and Management, 2023
- Preferred vector machine for forest fire detectionPattern Recognition, 2023
- Advances in the study of global forest wildfiresJournal of Soils and Sediments, 2023
- A modified YOLOv5 architecture for efficient fire detection in smart citiesExpert Systems with Applications, 2023
- Uncertainty assessment of remote sensing- and ground-based methods to estimate wildfire emissions: a case study in Calabria region (Italy)Air Quality, Atmosphere & Health, 2023
- Attention based CNN model for fire detection and localization in real-world imagesExpert Systems with Applications, 2022