Open AccessSTEREO RECONSTRUCTION OF ATMOSPHERIC CLOUD SURFACES FROM FISH-EYE CAMERA IMAGES
Author(s) -
G. Katai-Urban,
V. Otte,
N. Kees,
Z. Megyesi,
P. S. Bixel
Publication year - 2016
Publication title -
the international archives of the photogrammetry, remote sensing and spatial information sciences/international archives of the photogrammetry, remote sensing and spatial information sciences
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.264
H-Index - 71
eISSN - 1682-1777
pISSN - 1682-1750
DOI - 10.5194/isprsarchives-xli-b3-49-2016
Subject(s) - computer vision , artificial intelligence , point cloud , computer science , camera resectioning , stereo camera , cloud computing , workflow , focus (optics) , computer graphics (images) , camera auto calibration , calibration , optics , mathematics , physics , statistics , database , operating system
In this article a method for reconstructing atmospheric cloud surfaces using a stereo camera system is presented. The proposed camera system utilizes fish-eye lenses in a flexible wide baseline camera setup. The entire workflow from the camera calibration to the creation of the 3D point set is discussed, but the focus is mainly on cloud segmentation and on the image processing steps of stereo reconstruction. Speed requirements, geometric limitations, and possible extensions of the presented method are also covered. After evaluating the proposed method on artificial cloud images, this paper concludes with results and discussion of possible applications for such systems.