High-dynamic-range imaging for cloud segmentation

Dev, Soumyabrata; Savoy, Florian M.; Lee, Yee Hui; Winkler, Stefan

doi:https://doi.org/10.5194/amt-11-2041-2018

Articles | Volume 11, issue 4

https://doi.org/10.5194/amt-11-2041-2018

© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 3.0 License.

https://doi.org/10.5194/amt-11-2041-2018

© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 3.0 License.

Articles | Volume 11, issue 4

Research article

|

11 Apr 2018

Research article |

| 11 Apr 2018

High-dynamic-range imaging for cloud segmentation

Soumyabrata Dev, Florian M. Savoy, Yee Hui Lee, and Stefan Winkler

Data sets

Reproducible research in signal processing P. Vandewalle https://doi.org/10.1109/MSP.2009.932122

Singapore High-dynamic-range Whole sky IMaging SEGmentation Database S. Dev, F. M. Savoy, Y. H. Lee, and S. Winkler http://vintage.winklerbros.net/shwimseg.html

MATLAB scripts for HDR cloud segmentation S. Dev, F. M. Savoy, Y. H. Lee, and S. Winkler https://github.com/Soumyabrata/HDR-cloud-segmentation

Short summary

Sky–cloud images obtained from ground-based sky cameras are usually captured using a fish-eye lens with a wide field of view. However, the sky exhibits a large variation in the scene luminance. In most cases, the circumsolar region is overexposed, and the regions near the horizon are underexposed. In this paper, we propose HDRCloudSeg – an effective method for cloud segmentation using high-dynamic-range (HDR) imaging. We describe the entire process and also release a new database.