16 April 2014 Recognition methods on cloud amount, movement of clouds, and rain clouds for rainfall prediction using whole sky images
Author Affiliations +
Proceedings Volume 9159, Sixth International Conference on Digital Image Processing (ICDIP 2014); 915902 (2014) https://doi.org/10.1117/12.2063930
Event: Sixth International Conference on Digital Image Processing, 2014, Athens, Greece
Abstract
The final target of our research is to develop a system for forecasting local concentrated heavy rain, such as guerrilla rainstorms, by using whole sky images taken on the ground. To construct this system, this paper proposes the following recognition methods: cloud amount, movement of clouds, and rain clouds. The experimental results show that red/blue (R/B) values are efficient for measuring the cloud amount. However, using the gravity of images and the difference among time-sequenced images is insufficient to recognize the movement of clouds and does not correlate well with the R/B values and rain.
© (2014) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Kazuma Fujinuma, Masayuki Arai, "Recognition methods on cloud amount, movement of clouds, and rain clouds for rainfall prediction using whole sky images", Proc. SPIE 9159, Sixth International Conference on Digital Image Processing (ICDIP 2014), 915902 (16 April 2014); doi: 10.1117/12.2063930; https://doi.org/10.1117/12.2063930
PROCEEDINGS
7 PAGES


SHARE
Back to Top