Preprints
https://doi.org/10.5194/essd-2022-394
https://doi.org/10.5194/essd-2022-394
 
21 Nov 2022
21 Nov 2022
Status: this preprint is currently under review for the journal ESSD.

FASDD: An Open-access 100,000-level Flame and Smoke Detection Dataset for Deep Learning in Fire Detection

Ming Wang1, Liangcun Jiang1,2,3, Peng Yue1,3,4,5, Dayu Yu1, and Tianyu Tuo1 Ming Wang et al.
  • 1School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, Hubei, 430079, China
  • 2School of Resources and Environmental Engineering, Wuhan University of Technology, Wuhan, Hubei, 430070, China
  • 3Hubei LuoJia Laboratory, Wuhan, Hubei, 430079, China
  • 4Collaborative Innovation Center of Geospatial Technology, Wuhan, Hubei, 430079, China
  • 5Hubei Province Engineering Center for Intelligent Geoprocessing (HPECIG), Wuhan University, Wuhan, Hubei, 430079, China

Abstract. Deep learning methods driven by in situ video and remote sensing images have been used in fire detection. The performance and generalization of fire detection models, however, are restricted by the limited number and modality of fire detection training datasets. A large-scale fire detection benchmark dataset covering complex and varied fire scenarios is urgently needed. This work constructs a 100,000-level Flame and Smoke Detection Dataset (FASDD) based on multi-source heterogeneous flame and smoke images. To the best of our knowledge, FASDD is currently the most versatile and comprehensive dataset for fire detection. It provides a challenging benchmark to drive the continuous evolution of fire detection models. Additionally, we formulate a unified workflow for preprocessing, annotation and quality control of fire samples. Meanwhile, out-of-the-box annotations are published in four different formats for training deep learning models. Deep learning models trained on FASDD demonstrate the potential value and challenges of our dataset in fire detection and localization. Extensive performance evaluations based on classical methods show that most of the models trained on FASDD can achieve satisfactory fire detection results, and especially YOLOv5x achieves nearly 80 % mAP@0.5 accuracy on heterogeneous images spanning two domains of computer vision and remote sensing. And the application in wildfire location demonstrates that deep learning models trained on our dataset can be used in recognizing and monitoring forest fires. It can be deployed simultaneously on watchtowers, drones and optical satellites to build a satellite-ground cooperative observation network, which can provide an important reference for large-scale fire suppression, victim escape, firefighter rescue and government decision-making. The dataset is available from the Science Data Bank website at https://doi.org/10.57760/sciencedb.j00104.00103 (Wang et al., 2022).

Ming Wang et al.

Status: open (until 16 Jan 2023)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse

Ming Wang et al.

Data sets

FASDD: An Open-access 100,000-level Flame and Smoke Detection Dataset for Deep Learning in Fire Detection Ming Wang, Liangcun Jiang, Peng Yue, Dayu Yu, Tianyu Tuo https://www.scidb.cn/en/s/nqYfi2

Ming Wang et al.

Viewed

Total article views: 116 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
86 25 5 116 10 3 3
  • HTML: 86
  • PDF: 25
  • XML: 5
  • Total: 116
  • Supplement: 10
  • BibTeX: 3
  • EndNote: 3
Views and downloads (calculated since 21 Nov 2022)
Cumulative views and downloads (calculated since 21 Nov 2022)

Viewed (geographical distribution)

Total article views: 109 (including HTML, PDF, and XML) Thereof 109 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 27 Nov 2022
Download
Short summary
We present a large-scale Flame and Smoke Detection Dataset (FASDD) covering complex and varied fire scenarios. FASDD contains fire, smoke, and confusing non-fire/non-smoke images acquired at different distances (near and far), different scenes (indoor and outdoor), different light intensities (day and night), and from various sensors (surveillance cameras, UAV, and satellites). To the best of our knowledge, it is the largest multimodal dataset for deep learning based fire detection.