Open AccessA New Contrast-Enhancing Feature for Cloud Detection in Ground-Based Sky Images
Author(s) -
Vijai Jayadevan,
Jeffrey J. Rodríguez,
Alexander D. Cronin
Publication year - 2015
Publication title -
journal of atmospheric and oceanic technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.774
H-Index - 124
eISSN - 1520-0426
pISSN - 0739-0572
DOI - 10.1175/jtech-d-14-00053.1
Subject(s) - hue , sky , pixel , hsl and hsv , artificial intelligence , contrast (vision) , thresholding , computer science , cloud computing , computer vision , remote sensing , feature (linguistics) , contrast ratio , color space , image (mathematics) , geology , physics , meteorology , linguistics , virus , philosophy , virology , biology , operating system
For this study a ground-based sky imaging system was developed that, unlike most other such systems, consists of a low-cost sun-tracking camera fitted with a fish-eye lens. The application of interest is short-term solar power forecasting, so cloud detection is an important step. The hybrid thresholding algorithm proposed by Li et al. for cloud detection is employed. Most cloud detection algorithms make use of the red and blue components in a color image. Though these features perform well for many images, they do not produce good results for the images in this study due to the insufficient contrast between cloud and sky pixels when using ratios between red and blue. To overcome this issue, a new feature, the normalized saturation/value (NSV) ratio, is proposed that is computed in the hue–saturation–value (HSV) color space. This study shows that the NSV ratio produces good contrast between cloud and sky pixels not only for the images in this study but also for general sky images acquired using different camera systems. The reasoning behind the choice of the new ratio is described, and quantitative and qualitative results are presented.