Smart City Gnosys

Smart city article details

Title	Optimizing Fire Detection In Remote Sensing Imagery For Edge Devices: A Quantization-Enhanced Hybrid Deep Learning Model
ID_Doc	40809
Authors	Bukhari S.M.S.; Dahmani N.; Gyawali S.; Zafar M.H.; Sanfilippo F.; Raja K.
Year	2025
Published	Displays, 89
DOI	http://dx.doi.org/10.1016/j.displa.2025.103070
Abstract	Wildfires are increasing in frequency and severity, presenting critical challenges for timely detection and response, particularly in remote or resource-limited environments. This study introduces the Inception-ResNet Transformer with Quantization (IRTQ), a novel hybrid deep learning (DL) framework that integrates multi-scale feature extraction with global attention and advanced quantization. The proposed model is specifically optimized for edge deployment on platforms such as unmanned aerial vehicles (UAVs), offering a unique combination of high accuracy, low latency, and compact memory footprint. The IRTQ model achieves 98.9% accuracy across diverse datasets and shows strong generalization through cross-dataset validation. Quantization significantly reduces the parameter count to 0.09M and memory usage to 0.13 MB, enabling real-time inference in 3 ms. Interpretability is further enhanced through Grad-CAM visualizations, supporting transparent decision-making. While achieving state-of-the-art performance, the model encounters challenges in visually ambiguous fire-like regions. To address these, future work will explore multi-modal inputs and extend the model towards multi-class classification. IRTQ represents a technically grounded, interpretable, and deployable solution for AI-driven wildfire detection and disaster response. © 2025 The Authors
Author Keywords	Bushfire detection; Inception-resNet; Quantization; Smart city applications; Transformer models; Unmanned aerial vehicles (UAV)

Similar Articles

Id	Similarity	Authors	Title	Published
17955	0.902	Qadir Z.; Le K.; Bao V.N.Q.; Tam V.W.Y.	Deep Learning-Based Intelligent Post-Bushfire Detection Using Uavs	IEEE Geoscience and Remote Sensing Letters, 21 (2024)
59290	0.887	Hussain T.; Dai H.; Gueaieb W.; Sicklinger M.; De Masi G.	Uav-Based Multi-Scale Features Fusion Attention For Fire Detection In Smart City Ecosystems	ISC2 2022 - 8th IEEE International Smart Cities Conference (2022)
26883	0.88	Karthi M.; Priscilla R.; Subhashini G.; Infantia C.N.; Abijith G.R.; Vinisha J.	Forest Fire Detection: A Comparative Analysis Of Deep Learning Algorithms	Proceedings of the International Conference on Artificial Intelligence and Knowledge Discovery in Concurrent Engineering, ICECONF 2023 (2023)
26592	0.879	He Y.; Sahma A.; He X.; Wu R.; Zhang R.	Firenet: A Lightweight And Efficient Multi-Scenario Fire Object Detector	Remote Sensing, 16, 21 (2024)
10444	0.871	Alboody A.; Qaisar S.M.; Roussel G.	Artificial Intelligence Assistive Fire Detection And Seeing The Invisible Through Smoke Using Hyperspectral And Multi-Spectral Images	2023 IEEE 13th International Conference on Electronics and Information Technologies, ELIT 2023 - Proceedings (2023)
26572	0.871	Ud D.S.; Muhammad S.; Han F.; Shoaib H.; Ather Iqbal H.M.	Fire Classification Using Attention-Based Deep-Cnn In Digital Images	Proceedings - 2023 10th International Conference on Electrical and Electronics Engineering, ICEEE 2023 (2023)
21573	0.857	Wang X.; Li M.; Gao M.; Liu Q.; Li Z.; Kou L.	Early Smoke And Flame Detection Based On Transformer	Journal of Safety Science and Resilience, 4, 3 (2023)
26427	0.857	Khan S.; Khan A.	Ffirenet: Deep Learning Based Forest Fire Classification And Detection In Smart Cities	Symmetry, 14, 10 (2022)
58208	0.855	Bittencourt J.C.N.; Costa D.G.; Portugal P.; Vasques F.	Towards Lightweight Fire Detection At The Extreme Edge Based On Decision Trees	2024 IEEE 22nd Mediterranean Electrotechnical Conference, MELECON 2024 (2024)
380	0.853	Mukherjee A.; Rakshit S.; Panja A.K.; De D.; Dey N.	A 6G-Enabled Edge-Assisted Internet Of Drone Things Ecosystem For Fire Detection	Lecture Notes in Networks and Systems, 975 (2024)