A UAV-Based Multi-Scenario RGB-Thermal Dataset and Fusion Model for Enhanced Forest Fire Detection
UAVs are essential for forest fire detection due to vast forest areas and inaccessibility of high-risk zones, enabling rapid long-range inspection and detailed close-range surveillance. However, aerial photography faces challenges like multi-scale target recognition and complex scenario adaptation (...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/15/2593 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849239686222970880 |
|---|---|
| author | Yalin Zhang Xue Rui Weiguo Song |
| author_facet | Yalin Zhang Xue Rui Weiguo Song |
| author_sort | Yalin Zhang |
| collection | DOAJ |
| description | UAVs are essential for forest fire detection due to vast forest areas and inaccessibility of high-risk zones, enabling rapid long-range inspection and detailed close-range surveillance. However, aerial photography faces challenges like multi-scale target recognition and complex scenario adaptation (e.g., deformation, occlusion, lighting variations). RGB-Thermal fusion methods integrate visible-light texture and thermal infrared temperature features effectively, but current approaches are constrained by limited datasets and insufficient exploitation of cross-modal complementary information, ignoring cross-level feature interaction. A time-synchronized multi-scene, multi-angle aerial RGB-Thermal dataset (RGBT-3M) with “Smoke–Fire–Person” annotations and modal alignment via the M-RIFT method was constructed as a way to address the problem of data scarcity in wildfire scenarios. Finally, we propose a CP-YOLOv11-MF fusion detection model based on the advanced YOLOv11 framework, which can learn heterogeneous features complementary to each modality in a progressive manner. Experimental validation proves the superiority of our method, with a precision of 92.5%, a recall of 93.5%, a mAP50 of 96.3%, and a mAP50-95 of 62.9%. The model’s RGB-Thermal fusion capability enhances early fire detection, offering a benchmark dataset and methodological advancement for intelligent forest conservation, with implications for AI-driven ecological protection. |
| format | Article |
| id | doaj-art-8dbce3e82a7f4a658c2fced47016283e |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-8dbce3e82a7f4a658c2fced47016283e2025-08-20T04:00:53ZengMDPI AGRemote Sensing2072-42922025-07-011715259310.3390/rs17152593A UAV-Based Multi-Scenario RGB-Thermal Dataset and Fusion Model for Enhanced Forest Fire DetectionYalin Zhang0Xue Rui1Weiguo Song2State Key Laboratory of Fire Science, University of Science and Technology of China, Hefei 230026, ChinaSchool of Emergency Management, Nanjing University of Information Science and Technology, Nanjing 210044, ChinaState Key Laboratory of Fire Science, University of Science and Technology of China, Hefei 230026, ChinaUAVs are essential for forest fire detection due to vast forest areas and inaccessibility of high-risk zones, enabling rapid long-range inspection and detailed close-range surveillance. However, aerial photography faces challenges like multi-scale target recognition and complex scenario adaptation (e.g., deformation, occlusion, lighting variations). RGB-Thermal fusion methods integrate visible-light texture and thermal infrared temperature features effectively, but current approaches are constrained by limited datasets and insufficient exploitation of cross-modal complementary information, ignoring cross-level feature interaction. A time-synchronized multi-scene, multi-angle aerial RGB-Thermal dataset (RGBT-3M) with “Smoke–Fire–Person” annotations and modal alignment via the M-RIFT method was constructed as a way to address the problem of data scarcity in wildfire scenarios. Finally, we propose a CP-YOLOv11-MF fusion detection model based on the advanced YOLOv11 framework, which can learn heterogeneous features complementary to each modality in a progressive manner. Experimental validation proves the superiority of our method, with a precision of 92.5%, a recall of 93.5%, a mAP50 of 96.3%, and a mAP50-95 of 62.9%. The model’s RGB-Thermal fusion capability enhances early fire detection, offering a benchmark dataset and methodological advancement for intelligent forest conservation, with implications for AI-driven ecological protection.https://www.mdpi.com/2072-4292/17/15/2593forest fireUAV multispectral imageryYOLOv11wildfire datasetsmall object detectionattention mechanism |
| spellingShingle | Yalin Zhang Xue Rui Weiguo Song A UAV-Based Multi-Scenario RGB-Thermal Dataset and Fusion Model for Enhanced Forest Fire Detection Remote Sensing forest fire UAV multispectral imagery YOLOv11 wildfire dataset small object detection attention mechanism |
| title | A UAV-Based Multi-Scenario RGB-Thermal Dataset and Fusion Model for Enhanced Forest Fire Detection |
| title_full | A UAV-Based Multi-Scenario RGB-Thermal Dataset and Fusion Model for Enhanced Forest Fire Detection |
| title_fullStr | A UAV-Based Multi-Scenario RGB-Thermal Dataset and Fusion Model for Enhanced Forest Fire Detection |
| title_full_unstemmed | A UAV-Based Multi-Scenario RGB-Thermal Dataset and Fusion Model for Enhanced Forest Fire Detection |
| title_short | A UAV-Based Multi-Scenario RGB-Thermal Dataset and Fusion Model for Enhanced Forest Fire Detection |
| title_sort | uav based multi scenario rgb thermal dataset and fusion model for enhanced forest fire detection |
| topic | forest fire UAV multispectral imagery YOLOv11 wildfire dataset small object detection attention mechanism |
| url | https://www.mdpi.com/2072-4292/17/15/2593 |
| work_keys_str_mv | AT yalinzhang auavbasedmultiscenariorgbthermaldatasetandfusionmodelforenhancedforestfiredetection AT xuerui auavbasedmultiscenariorgbthermaldatasetandfusionmodelforenhancedforestfiredetection AT weiguosong auavbasedmultiscenariorgbthermaldatasetandfusionmodelforenhancedforestfiredetection AT yalinzhang uavbasedmultiscenariorgbthermaldatasetandfusionmodelforenhancedforestfiredetection AT xuerui uavbasedmultiscenariorgbthermaldatasetandfusionmodelforenhancedforestfiredetection AT weiguosong uavbasedmultiscenariorgbthermaldatasetandfusionmodelforenhancedforestfiredetection |