English

Short-term prediction of localized cloud motion using ground-based sky imagers

Computer Vision and Pattern Recognition 2016-10-24 v1

Abstract

Fine-scale short-term cloud motion prediction is needed for several applications, including solar energy generation and satellite communications. In tropical regions such as Singapore, clouds are mostly formed by convection; they are very localized, and evolve quickly. We capture hemispherical images of the sky at regular intervals of time using ground-based cameras. They provide a high resolution and localized cloud images. We use two successive frames to compute optical flow and predict the future location of clouds. We achieve good prediction accuracy for a lead time of up to 5 minutes.

Keywords

Cite

@article{arxiv.1610.06666,
  title  = {Short-term prediction of localized cloud motion using ground-based sky imagers},
  author = {Soumyabrata Dev and Florian M. Savoy and Yee Hui Lee and Stefan Winkler},
  journal= {arXiv preprint arXiv:1610.06666},
  year   = {2016}
}

Comments

Accepted in Proc. TENCON 2016 - 2016 IEEE Region 10 Conference

R2 v1 2026-06-22T16:27:25.077Z