EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Deep learning-based debris flow hazard detection and recognition system: a case study

Fei Wu iD, Jianlin Zhang iD, Dunlong Liu iD, Andreas Maier iD, Vincent Christlein iD

Scientific Reports · 25.02.2025 · 15 (1)

DOI: 10.1038/s41598-025-86471-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Scientific Reports, online erschienen am 25.02.2025. Verfasst von Fei Wu und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical, Electronics and Communication Engineering, University of Chinese Academy of Sciences, Beijing, 100049, China. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Science and Technology Department of Sichuan Province, Software Engineering Technology Research Support Center of Informatization Application of Sichuan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Debris flows are characterized by their suddenness, rapidity, large scale and destructive power, causing serious threat to the population in mountainous areas. Surveillance cameras are widely used in geological hazard monitoring and early warning projects. So far, video cameras are used as a passive tool for post inspection and not as an active role for debris flow monitoring and early warning. Inspired by recent developments of anomaly detection in the field of computer vision, in this paper, we propose a novel automatic debris flow detection and recognition system based on deep learning. It consists of a video feature extraction network using a 3D convolutional neural network (CNN), a debris flow hazard detection network using a multi-layer perceptron (MLP), and a debris flow hazard recognition network for verification employing another CNN. The proposed system takes the video sequences captured by the cameras as inputs and enables the detection and recognition of debris flow hazards. All the networks are optimized and evaluated on a newly annotated image dataset called Debrisflow23. Extensive experimental evaluations with a detection accuracy of 86.3 % AUC, a recognition accuracy of 83.7 % AUC, and an overall identification accuracy of 88.1 % AUC on the test dataset demonstrate that the proposed method possesses accurate and reliable debris flow warning capability. Thus, further precautions can be taken in advance to reduce the damage to human settlements and infrastructure caused by debris flows.

Schlagwörter

Stichwörter der Autor:innen

Convolutional neural networkDebris flowHazard detection and recognitionTransfer learning

Autor:innen und Institutionen

  • School of Electrical, Electronics and Communication Engineering, University of Chinese Academy of Sciences, Beijing, 100049, China.
  • National Key Laboratory of Optical Field Manipulation Science and Technology, Key Laboratory of Optical Engineering, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, 610209, China.
  • Pattern Recognition Lab, Department of Computer Science, Friedrich-Alexander-Universität Erlangen-Nürnberg, 91058, Erlangen, Germany.
  • School of Electrical, Electronics and Communication Engineering, University of Chinese Academy of Sciences, Beijing, 100049, China. jlin@ioe.ac.cn.
  • National Key Laboratory of Optical Field Manipulation Science and Technology, Key Laboratory of Optical Engineering, Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu, 610209, China. jlin@ioe.ac.…
  • Software Automatic Generation and Intelligent Service Key Laboratory of Sichuan Province, Chengdu University of Information and Technology, Chengdu, 610225, China. ldl@cuit.edu.cn.

ORCID-Profile: Fei Wu, Jianlin Zhang, Dunlong Liu, Andreas Maier, Vincent Christlein

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Department of Sichuan Province
  • Software Engineering Technology Research Support Center of Informatization Application of Sichuan

Zitieren

APA

Wu, F., Zhang, J., Liu, D., Maier, A., & Christlein, V. (2025). Deep learning-based debris flow hazard detection and recognition system: a case study. Scientific Reports, 15(1). https://doi.org/10.1038/s41598-025-86471-4

Vancouver

Wu F, Zhang J, Liu D, Maier A, Christlein V. Deep learning-based debris flow hazard detection and recognition system: a case study. Scientific Reports. 2025;15(1). doi:10.1038/s41598-025-86471-4

BibTeX
@article{Wu2025,
  author = {Wu, Fei and Zhang, Jianlin and Liu, Dunlong and Maier, Andreas and Christlein, Vincent},
  title = {Deep learning-based debris flow hazard detection and recognition system: a case study},
  journal = {Scientific Reports},
  year = {2025},
  volume = {15},
  number = {1},
  doi = {10.1038/s41598-025-86471-4}
}
Kostenlos starten →