Abstract
Abstract. The use of solar power as a renewable energy has grown rapidly over the last few decades. However, the amount of solar radiation reaching the ground vary significantly in the short term. Clouds are the main factor. In this paper, a novel cloud detection method for ground-based sky images is proposed. First, the multiple features from the sky images, including spectral, texture and colour features are combined into a feature set. Then, Random Forest with this feature set is used to classify different types of cloud and clear sky. The experimental results show that cumulus and cirrus clouds can be identified from sky images. Combined with random forest, three types of features and various feature combinations are used for cloud classification, respectively. The classification accuracy with multiple features is higher than that of single-type features and dual-type features.
Highlights
Some researchers have predicted that human would run out of fossil fuels within 100 years (Lackner, 2002)
When C is greater than 0.3, it can be considered that the sun is not blocked by clouds, and the clear sky pixels can be re-determined by threshold method
According to the existing research (Rodriguez-Galiano et al, 2012), when random forest is applied to classification, the value of mty is suitable to be the square root of the feature number we used
Summary
Some researchers have predicted that human would run out of fossil fuels within 100 years (Lackner, 2002). There have been many cloud detection studies of ground-based sky images They are mainly divided into two categories: threshold method and classifier method. In order to overcome the shortage of threshold methods, classifier methods integrate multi-feature into cloud detection of ground-based sky image. They can get better classification results than that of threshold methods. An automatic cloud classification algorithm are proposed for seven cloud-type based on a set of statistical features describing the color as well as the texture of an image and the KNN (kNearest-Neighbor) classifier to achieve the high accuracy about 75% (Heinle et al, 2010).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
