High-Dynamic-Range Imaging for Cloud Segmentation

TL;DR

This paper introduces HDRCloudSeg, a novel cloud segmentation method utilizing HDR imaging from multi-exposure fusion, effectively handling the high luminance variation in sky images and providing a new benchmark database.

Contribution

The paper presents the first use of HDR radiance maps for cloud segmentation and offers a new database for benchmarking such methods.

Findings

Achieves very good segmentation results.

First approach using HDR radiance maps for cloud segmentation.

Provides a new database for community benchmarking.

Abstract

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 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.