Wildfire detection using hybrid vision transformer and MobileNetV2 with XAI

Wildfires cause severe ecological and economic damage, and limiting it requires rapid and accurate detection. This study presents an image classification framework for wildfire detection in RGB images from the FLAME 3 dataset, captured by an unmanned aerial vehicle. The preprocessing pipeline applies gamma correction, sharpening, contrast-limited adaptive histogram equalisation (CLAHE) and class-balanced data augmentation. The proposed model combines a vision transformer (ViT) and MobileNetV2 in parallel branches, fusing global contextual features with local spatial features. Explainable artificial intelligence techniques (Grad-CAM, Grad-CAM++ and LIME) are used to visualise the image regions that influence the predictions. The model is compared with nine convolutional and five transformer-based baselines and evaluated with accuracy, Cohen’s κ, the Matthews correlation coefficient (MCC), the critical success index (CSI) and related metrics. Trained with the AdamW optimiser, the ViT–MobileNetV2 model achieves a test accuracy of 98.44%, a macro-average F1-score of 0.984 and a recall of 1.000 for the fire class on the FLAME 3 RGB classification subset. Inference takes 10–15 ms per image on an NVIDIA T4 GPU in half precision and 50–70 ms on an x86 CPU with INT8 quantisation. The results apply to the evaluated dataset and experimental protocol.

Authors

Institutions

Publication Details

Journal
Journal of Edge Computing
Published
2026-11-20
DOI
https://doi.org/10.55056/jec.1157
Citations
1
Primary Topic
Fire Detection and Safety Systems
Type
article
Field-Weighted Citation Impact
2.30
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Wildfire detection using hybrid vision transformer and MobileNetV2 with XAI

Akinul Islam Jony, Dipta Justin Gomes, Kazi Tanvir, M. Mostafizur Rahman et al.
1 citations
Journal of Edge Computing
Fire Detection and Safety Systems
2.30
article

Wildfire detection using hybrid vision transformer and MobileNetV2 with XAI

Akinul Islam Jony, Dipta Justin Gomes, Kazi Tanvir, M. Mostafizur Rahman, Tasnim Sultana Sintheia, Md. Sayem Kabir, Saif Mostasir Rohan
article en
1 citations

Abstract

Wildfires cause severe ecological and economic damage, and limiting it requires rapid and accurate detection. This study presents an image classification framework for wildfire detection in RGB images from the FLAME 3 dataset, captured by an unmanned aerial vehicle. The preprocessing pipeline applies gamma correction, sharpening, contrast-limited adaptive histogram equalisation (CLAHE) and class-balanced data augmentation. The proposed model combines a vision transformer (ViT) and MobileNetV2 in parallel branches, fusing global contextual features with local spatial features. Explainable artificial intelligence techniques (Grad-CAM, Grad-CAM++ and LIME) are used to visualise the image regions that influence the predictions. The model is compared with nine convolutional and five transformer-based baselines and evaluated with accuracy, Cohen’s κ, the Matthews correlation coefficient (MCC), the critical success index (CSI) and related metrics. Trained with the AdamW optimiser, the ViT–MobileNetV2 model achieves a test accuracy of 98.44%, a macro-average F1-score of 0.984 and a recall of 1.000 for the fire class on the FLAME 3 RGB classification subset. Inference takes 10–15 ms per image on an NVIDIA T4 GPU in half precision and 50–70 ms on an x86 CPU with INT8 quantisation. The results apply to the evaluated dataset and experimental protocol.

Journal of Edge ComputingVol. 5(2)
American International University-Bangladesh (BD), Universitat Oberta de Catalunya (ES)
Openalex Percentile: Top 18%
Fire Detection and Safety Systems
2.30
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Wildfire detection using hybrid vision transformer and MobileNetV2 with XAI — Akinul Islam Jony, Dipta Justin Gomes, et al. · Journal of Edge Computing (2026) | TGRS Research Map | TGRS