Cloud Detection in Hyperspectral Images with Atmospheric Column Water Vapor: Application to PRISMA and AVIRIS-NG Images

The Cloud detection in Hyperspectral Images With Atmospheric column WAter vapor (CHIWAWA) cloud detection method is presented. It aims to detect thick and thin clouds in a single hyperspectral image covering the reflective spectral range (400-2500 nm) in an unsupervised way. Its main originality is...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on geoscience and remote sensing 2024, Vol.62, p.1-24
Main Author: Alakian, Alexandre
Format: Article
Language:English
Subjects:
Atmospheric column water vapor
AVIRIS
cloud
Cloud computing
Cloud cover
Clouds
Detection
Engineering Sciences
hyperspectral
Hyperspectral imaging
ice
Image acquisition
Imaging spectrometers
Infrared imaging
Infrared spectrometers
Ocean temperature
Optical sensors
Physics
Pixels
Reflectance
Sensors
Snow
Surface treatment
unsupervised
Urban areas
Water vapor
Water vapour
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The Cloud detection in Hyperspectral Images With Atmospheric column WAter vapor (CHIWAWA) cloud detection method is presented. It aims to detect thick and thin clouds in a single hyperspectral image covering the reflective spectral range (400-2500 nm) in an unsupervised way. Its main originality is to combine the complementary information available in the ground reflectance image and the atmospheric column water vapor (WV) map. The method uses criteria based on reflectance to compute a mask of potential cloud pixels and refine it by exploiting the WV map. The use of the WV map is central to the method, as it has the greatest discriminating power. It, therefore, plays a role similar to that of thermal bands that are very useful for cloud detection but are absent in the reflective spectral range. Two specific processings are also proposed to detect snow and ice pixels and reduce the altitude dependence of the WV map in mountain images. CHIWAWA performance is assessed on several hyperspectral images acquired with PRecursore IperSpettrale della Missione Applicativa (PRISMA) and Airborne Visible InfraRed Imaging Spectrometer-Next Generation (AVIRIS-NG) sensors. Overall accuracy ranges from 97% to 100% for both sensors. When cloud cover is above 10%, F_{1} score ranges in 94%-100% for both sensors. For lower cloud covers, F_{1} score ranges in 83%-94% for PRISMA images and in 84%-91% for AVIRIS-NG images. CHIWAWA may encounter difficulties in detecting thin clouds located over urban areas or when the contrast between the cloud and its surroundings is low in the WV map.
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2024.3369401