Abstract
Abstract. Sky–cloud images obtained from ground-based sky cameras are usually captured using a fisheye 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 overexposed, and the regions near the horizon are underexposed. This renders cloud segmentation for such images difficult. In this paper, we propose HDRCloudSeg – an effective method for cloud segmentation using high-dynamic-range (HDR) imaging based on multi-exposure fusion. We describe the HDR image generation process and release a new database to the community for benchmarking. Our proposed approach is the first using HDR radiance maps for cloud segmentation and achieves very good results.
Highlights
Clouds are important for understanding weather phenomena, the earth’s radiative balance and climate change (IPCC, 2013; Stephens et al, 2012)
HDR imaging is an effective technique for cloud observation, as it helps us better image the circumsolar region with reduced overexposure
In addition to containing fewer saturated pixels, HDR imaging helps in improved cloud segmentation performance, regardless of the techniques used, as we will demonstrate in the following
Summary
Clouds are important for understanding weather phenomena, the earth’s radiative balance and climate change (IPCC, 2013; Stephens et al, 2012). Manual observations are performed by cloud experts at WMO (World Meteorological Organization) stations around the world. Such manual methods are expensive and prone to human error. Ceilometers, are useful in understanding the vertical profile of the cloud formation. They are point-measurement devices and can provide cloud information along a particular slant path through the atmosphere. Satellite sensors are extensively used in monitoring the earth’s atmosphere. Satellite images typically suffer from either low temporal or low spatial resolution
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
