Preprints
https://doi.org/10.5194/essd-2023-73
https://doi.org/10.5194/essd-2023-73
15 Mar 2023
 | 15 Mar 2023
Status: this preprint has been withdrawn by the authors.

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, and Tianyu Tuo
Publisher's note: we have noticed some uncommon patterns in the community comments of this preprint’s public discussion. Please treat the community comments with care while we clarify these occurrences with the authors.

Abstract. With the advancement of computer vision, artificial intelligence, and remote sensing technologies, deep learning algorithms are increasingly used in terrestrial, airborne, and spaceborne-based fire detection systems. The performance and generalization of these data-driven fire detection algorithms, however, are restricted by the limited number and source of fire detection 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. It holds rich variations in image size, resolution, illumination (day and night), scenario (indoor and outdoor), image range (far and near), viewing angle (top view and side view), platform (surveillance cameras, drones, and satellites), and data source (Internet, social media, and open-access fire datasets). 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. Out-of-the-box annotations are published in four different formats for training deep learning models. Extensive performance evaluations based on classical methods show that most of the object detection 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. Deep learning models trained with FASDD can be simultaneously deployed on satellites, drones, and ground sensors, thus realizing collaborative fire observation and detection in a space-air-ground integrated network environment. The dataset is available from the Science Data Bank website at https://doi.org/10.57760/sciencedb.j00104.00103 (Wang et al., 2022a).

This preprint has been withdrawn.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Ming Wang, Liangcun Jiang, Peng Yue, Dayu Yu, and Tianyu Tuo
Publisher's note: we have noticed some uncommon patterns in the community comments of this preprint’s public discussion. Please treat the community comments with care while we clarify these occurrences with the authors.

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CC1: 'Comment on essd-2023-73', w jr, 29 Mar 2023
    • AC1: 'Reply on CC1', Ming Wang, 29 Mar 2023
  • RC1: 'Comment on essd-2023-73', Anonymous Referee #1, 17 Apr 2023
    • AC2: 'Reply on RC1', Ming Wang, 17 Apr 2023
    • AC3: 'Reply on RC1', Ming Wang, 17 Apr 2023
    • AC4: 'Reply on RC1', Ming Wang, 18 Apr 2023
    • AC5: 'Reply on RC1', Ming Wang, 29 May 2023
    • AC17: 'Reply on RC1', Ming Wang, 24 Sep 2023
  • CC2: 'Request for Dataset for my Thesis on Fire Detection', Ebrahim Akbari, 26 May 2023
    • CC3: 'Reply on CC2', Liangcun Jiang, 27 May 2023
  • CC4: 'Comment on essd-2023-73', Rakesh Kumar Mallik, 29 May 2023
    • AC6: 'Reply on CC4', Ming Wang, 30 May 2023
  • CC5: 'Comment on essd-2023-73', Stephan Sturges, 21 Jun 2023
    • AC7: 'Reply on CC5', Ming Wang, 23 Jun 2023
  • CC6: 'Comment on essd-2023-73', Rafik Ghali, 27 Jun 2023
    • AC8: 'Reply on CC6', Ming Wang, 03 Jul 2023
  • CC7: 'dataset access', dipesh digwal, 03 Jul 2023
    • AC9: 'Reply on CC7', Ming Wang, 03 Jul 2023
  • CC8: 'Comment on essd-2023-73', Rafik Ghali, 05 Jul 2023
    • AC10: 'Reply on CC8', Ming Wang, 06 Jul 2023
    • AC11: 'Reply on CC8', Ming Wang, 06 Jul 2023
  • CC9: 'Comment on essd-2023-73', lin jing, 08 Jul 2023
    • AC12: 'Reply on CC9', Ming Wang, 08 Jul 2023
  • CC10: 'Comment on essd-2023-73', sumanth reddy, 18 Jul 2023
    • AC13: 'Reply on CC10', Ming Wang, 18 Jul 2023
  • CC11: 'Comment on essd-2023-73', Shokhruz Kak, 30 Jul 2023
    • AC14: 'Reply on CC11', Ming Wang, 30 Jul 2023
  • CC12: 'Comment on essd-2023-73', hossein rajoli, 12 Aug 2023
    • AC15: 'Reply on CC12', Ming Wang, 12 Aug 2023
  • RC2: 'Comment on essd-2023-73', Anonymous Referee #2, 23 Aug 2023
    • AC16: 'Reply on RC2', Ming Wang, 24 Sep 2023

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CC1: 'Comment on essd-2023-73', w jr, 29 Mar 2023
    • AC1: 'Reply on CC1', Ming Wang, 29 Mar 2023
  • RC1: 'Comment on essd-2023-73', Anonymous Referee #1, 17 Apr 2023
    • AC2: 'Reply on RC1', Ming Wang, 17 Apr 2023
    • AC3: 'Reply on RC1', Ming Wang, 17 Apr 2023
    • AC4: 'Reply on RC1', Ming Wang, 18 Apr 2023
    • AC5: 'Reply on RC1', Ming Wang, 29 May 2023
    • AC17: 'Reply on RC1', Ming Wang, 24 Sep 2023
  • CC2: 'Request for Dataset for my Thesis on Fire Detection', Ebrahim Akbari, 26 May 2023
    • CC3: 'Reply on CC2', Liangcun Jiang, 27 May 2023
  • CC4: 'Comment on essd-2023-73', Rakesh Kumar Mallik, 29 May 2023
    • AC6: 'Reply on CC4', Ming Wang, 30 May 2023
  • CC5: 'Comment on essd-2023-73', Stephan Sturges, 21 Jun 2023
    • AC7: 'Reply on CC5', Ming Wang, 23 Jun 2023
  • CC6: 'Comment on essd-2023-73', Rafik Ghali, 27 Jun 2023
    • AC8: 'Reply on CC6', Ming Wang, 03 Jul 2023
  • CC7: 'dataset access', dipesh digwal, 03 Jul 2023
    • AC9: 'Reply on CC7', Ming Wang, 03 Jul 2023
  • CC8: 'Comment on essd-2023-73', Rafik Ghali, 05 Jul 2023
    • AC10: 'Reply on CC8', Ming Wang, 06 Jul 2023
    • AC11: 'Reply on CC8', Ming Wang, 06 Jul 2023
  • CC9: 'Comment on essd-2023-73', lin jing, 08 Jul 2023
    • AC12: 'Reply on CC9', Ming Wang, 08 Jul 2023
  • CC10: 'Comment on essd-2023-73', sumanth reddy, 18 Jul 2023
    • AC13: 'Reply on CC10', Ming Wang, 18 Jul 2023
  • CC11: 'Comment on essd-2023-73', Shokhruz Kak, 30 Jul 2023
    • AC14: 'Reply on CC11', Ming Wang, 30 Jul 2023
  • CC12: 'Comment on essd-2023-73', hossein rajoli, 12 Aug 2023
    • AC15: 'Reply on CC12', Ming Wang, 12 Aug 2023
  • RC2: 'Comment on essd-2023-73', Anonymous Referee #2, 23 Aug 2023
    • AC16: 'Reply on RC2', Ming Wang, 24 Sep 2023
Ming Wang, Liangcun Jiang, Peng Yue, Dayu Yu, and Tianyu Tuo
Publisher's note: we have noticed some uncommon patterns in the community comments of this preprint’s public discussion. Please treat the community comments with care while we clarify these occurrences with the authors.
Ming Wang, Liangcun Jiang, Peng Yue, Dayu Yu, and Tianyu Tuo
Publisher's note: we have noticed some uncommon patterns in the community comments of this preprint’s public discussion. Please treat the community comments with care while we clarify these occurrences with the authors.

Viewed

Total article views: 2,606 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
1,837 638 131 2,606 48 43
  • HTML: 1,837
  • PDF: 638
  • XML: 131
  • Total: 2,606
  • BibTeX: 48
  • EndNote: 43
Views and downloads (calculated since 15 Mar 2023)
Cumulative views and downloads (calculated since 15 Mar 2023)

Viewed (geographical distribution)

Total article views: 2,524 (including HTML, PDF, and XML) Thereof 2,524 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 22 May 2024
Download

This preprint has been withdrawn.

Please read the editorial note first before accessing the preprint.

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 platforms (surveillance cameras, drones, and satellites). To the best of our knowledge, FASDD is currently the most versatile and comprehensive dataset for fire detection.
Altmetrics