An all-sky camera image classification method using cloud cover features
Open Access
- 16 June 2022
- journal article
- research article
- Published by Copernicus GmbH in Atmospheric Chemistry and Physics
- Vol. 15 (11), 3629-3639
- https://doi.org/10.5194/amt-15-3629-2022
Abstract
The all-sky camera (ASC) images can reflect the local cloud cover information, and the cloud cover is one of the first factors considered for astronomical observatory site selection. Therefore, the realization of automatic classification of the ASC images plays an important role in astronomical observatory site selection. In this paper, three cloud cover features are proposed for the TMT (Thirty Meter Telescope) classification criteria, namely cloud weight, cloud area ratio and cloud dispersion. After the features are quantified, four classifiers are used to recognize the classes of the images. Four classes of ASC images are identified: “clear”, “inner”, “outer” and “covered”. The proposed method is evaluated on a large dataset, which contains 5000 ASC images taken by an all-sky camera located in Xinjiang (38.19∘ N, 74.53∘ E). In the end, the method achieves an accuracy of 96.58 % and F1_score of 96.24 % by a random forest (RF) classifier, which greatly improves the efficiency of automatic processing of the ASC images.Keywords
Funding Information
- National Natural Science Foundation of China (U1931134)
This publication has 32 references indexed in Scilit:
- Evaluation of Global Horizontal Irradiance Derived from CLAVR-x Model and COMS Imagery Over the Korean PeninsulaJournal of The korean society for new and renewable energy, 2016
- From pixels to patches: a cloud classification method based on a bag of micro-structuresAtmospheric Chemistry and Physics, 2016
- Categorization of cloud image patches using an improved texton-based approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Automatic cloud classification of whole sky imagesAtmospheric Chemistry and Physics, 2010
- Using All Sky Cameras to determine cloud statistics for the Thirty Meter Telescope candidate sitesPublished by SPIE-Intl Soc Optical Eng ,2008
- Feature Extraction from Whole-Sky Ground-Based Images for Cloud-Type RecognitionJournal of Atmospheric and Oceanic Technology, 2008
- Arguments against a physical long‐term trend in global ISCCP cloud amountsGeophysical Research Letters, 2007
- Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene CategoriesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Random Forest: A Classification and Regression Tool for Compound Classification and QSAR ModelingJournal of Chemical Information and Computer Sciences, 2003
- Multiresolution gray-scale and rotation invariant texture classification with local binary patternsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002