Search

Ground-based whole sky cameras are now-a-days extensively used for localized monitoring of the clouds. They capture hemispherical images of the sky at regular intervals using a fisheye lens. In this paper, we derive a model for estimating the solar irradiance using pictures taken by those imagers. Unlike pyranometers, these sky images contain information about the cloud coverage and can be used to derive cloud movement. An accurate estimation of the solar irradiance using solely those images is thus a first step towards short-term solar energy generation forecasting, as cloud movement can also be derived from them. We derive and validate our model using pyranometers co-located with our whole sky imagers. We achieve a root mean square error of 178 Watt/m² between estimated and measured solar irradiance, outperforming state-of-the-art methods using other weather instruments. Our method shows a significant improvement in estimating strong short-term variations. [ABSTRACT FROM AUTHOR]

Sky/cloud images obtained from ground-based sky-cameras are usually captured using a fish-eye lens with a wide field of view. However, the sky exhibits a large dynamic range in terms of luminance, more than a conventional camera can capture. It is thus difficult to capture the details of an entire scene with a regular camera in a single shot. In most cases, the circumsolar region is over-exposed, and the regions near the horizon are under-exposed. This renders cloud segmentation for such images difficult. In this paper, we propose HDRSeg - an effective method for cloud segmentation using High-Dynamic-Range (HDR) imaging based on multi-exposure fusion. We describe the HDR generation process and release a new database to the community for benchmarking. Our proposed approach is the first using HDR images for cloud segmentation and achieves very good results. [ABSTRACT FROM AUTHOR]