Explicit Basis Function Kernel Methods for Cloud Segmentation in Infrared Sky Images

TL;DR

This paper compares kernel discriminative models for infrared sky image cloud segmentation, emphasizing real-time feasibility and improved performance through preprocessing and neighboring features.

Contribution

It introduces a primal formulation approach for kernel models that enhances real-time cloud segmentation in infrared images.

Findings

Primal kernel models significantly reduce computation time.

Preprocessing and neighboring features improve segmentation accuracy.

Models achieve high performance in cloud detection tasks.

Abstract

Photovoltaic systems are sensitive to cloud shadow projection, which needs to be forecasted to reduce the noise impacting the intra-hour forecast of global solar irradiance. We present a comparison between different kernel discriminative models for cloud detection. The models are solved in the primal formulation to make them feasible in real-time applications. The performances are compared using the j-statistic. The infrared cloud images have been preprocessed to remove debris, which increases the performance of the analyzed methods. The use of neighboring features of the pixels also leads to a performance improvement. Discriminative models solved in the primal yield a dramatically lower computing time along with high performance in the segmentation.