Articles | Volume 10, issue 1
https://doi.org/10.5194/amt-10-199-2017
https://doi.org/10.5194/amt-10-199-2017
Research article
 | 
17 Jan 2017
Research article |  | 17 Jan 2017

Cloud detection in all-sky images via multi-scale neighborhood features and multiple supervised learning techniques

Hsu-Yung Cheng and Chih-Lung Lin

Abstract. Cloud detection is important for providing necessary information such as cloud cover in many applications. Existing cloud detection methods include red-to-blue ratio thresholding and other classification-based techniques. In this paper, we propose to perform cloud detection using supervised learning techniques with multi-resolution features. One of the major contributions of this work is that the features are extracted from local image patches with different sizes to include local structure and multi-resolution information. The cloud models are learned through the training process. We consider classifiers including random forest, support vector machine, and Bayesian classifier. To take advantage of the clues provided by multiple classifiers and various levels of patch sizes, we employ a voting scheme to combine the results to further increase the detection accuracy. In the experiments, we have shown that the proposed method can distinguish cloud and non-cloud pixels more accurately compared with existing works.

Download
Short summary
A cloud detection method for all-sky images is proposed. Obtaining improved cloud detection results is helpful for cloud classification, tracking and solar irradiance prediction. The features are extracted from local image patches with different sizes to include local structure and multi-resolution information. The cloud models are learned through the training process. We have shown that taking advantages of multiple classifiers and various patch sizes is able to increase the detection accuracy.