Optimized Faster R-CNN with Swintransformer for Robust Multi-Class Wildfire Detection
Open Access
Abstract
Wildfires are a critical global threat, emphasizing the need for efficient detection systems capable of identifying fires and distinguishing fire-related from non-fire events in their early stages. This study integrates the swintransformer into the Faster R-CNN backbone to overcome challenges in detecting small flames and smoke and distinguishing complex scenarios like fog/haze and chimney smoke. The proposed model was evaluated using a dataset comprising five classes: flames, smoke, clouds, fog/haze, and chimney smoke. Experimental results demonstrate that swintransformer-based models outperform ResNet-based Faster R-CNN models, achieving a maximum mAP50 of 0.841 with the swintransformer-based model. The model exhibited superior performance in detecting small and dynamic objects while reducing misclassification rates between similar classes, such as smoke and chimney smoke. Precision–recall analysis further validated the model’s robustness across diverse scenarios. However, slightly lower recall for specific classes and a lower FPS compared to ResNet models suggest a need for further optimization for real-time applications. This study highlights the swintransformer’s potential to enhance wildfire detection systems by addressing fire and non-fire events effectively. Future research will focus on optimizing its real-time performance and improving its recall for challenging scenarios, thereby contributing to the development of robust and reliable wildfire detection systems.Keywords
Funding Information
- Korea Agency for Infrastructure Technology Advancement (202102220002, 2021R1G1A1014385)
- National Research Foundation of Korea (202102220002, 2021R1G1A1014385)
This publication has 36 references indexed in Scilit:
- Automatic Identifier of Socket for Electrical Vehicles Using SWIN-Transformer and SimAM Attention Mechanism-Based EVS YOLOIEEE Access, 2023
- Dual Swin-transformer based mutual interactive network for RGB-D salient object detectionNeurocomputing, 2023
- Assessing the Effectiveness of YOLO Architectures for Smoke and Wildfire DetectionIEEE Access, 2023
- Wildfire detection via transfer learning: a surveySignal, Image and Video Processing, 2023
- Review Study on Recent Developments in Fire Sensing MethodsIEEE Access, 2023
- An improved fire detection approach based on YOLO-v8 for smart citiesNeural Computing and Applications, 2023
- Detection of forest fire using deep convolutional neural networks with transfer learning approachApplied Soft Computing, 2023
- Research on multi-detector real-time fire alarm technology based on signal similarityFire Safety Journal, 2022
- Elevation in wildfire frequencies with respect to the climate changeJournal of Environmental Management, 2022
- Image fire detection algorithms based on convolutional neural networksCase Studies in Thermal Engineering, 2020