Atmospheric Measurement Techniques
Atmospheric Measurement Techniques
AMT
Articles | Volume 18, issue 20
Articles | Volume 18, issue 20
https://doi.org/10.5194/amt-18-5457-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/amt-18-5457-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 18, issue 20
Research article
 | 
17 Oct 2025
Research article |  | 17 Oct 2025

Surveillance Camera-Based Deep Learning Framework for High-Resolution Near Surface Precipitation Type Observation

Xing Wang, Kun Zhao, Hao Huang, Ang Zhou, and Haiqin Chen

Viewed

Total article views: 3,824 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
2,174 1,499 151 3,824 130 139
  • HTML: 2,174
  • PDF: 1,499
  • XML: 151
  • Total: 3,824
  • BibTeX: 130
  • EndNote: 139
Views and downloads (calculated since 19 Feb 2025)
Cumulative views and downloads (calculated since 19 Feb 2025)

Viewed (geographical distribution)

Total article views: 3,824 (including HTML, PDF, and XML) Thereof 3,692 with geography defined and 132 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Saved (final revised paper)

Latest update: 03 Nov 2026
Download
Short summary
Surveillance cameras have emerged as a new low-cost, high-resolution Near Surface Precipitation Type observer. A novel deep learning approach is developed to classify rain, snow, and graupel, achieving 93 % accuracy in real-world observations. The model remains robust to camera parameter variations and maintains reliable performance at wind speeds below 5 m s−1, demonstrating strong potential for large-scale practical applications.
Read more
Share
Altmetrics
Final-revised paper
Preprint