A morphology-based approach for cloud detection

Authors

Sravan Danda, Indian Statistical Institute Bangalore
Aditya Challa, Indian Statistical Institute Bangalore
B. S. Daya Sagar, Indian Statistical Institute Bangalore

Document Type

Conference Article

Publication Title

International Geoscience and Remote Sensing Symposium (IGARSS)

Abstract

The aim of this paper is to present a simple and robust morphology-based approach to detect clouds in remote sensing images based on a single band. The algorithm generates for every pixel, a possibility value of not being a cloud pixel and thus provides an additional advantage over hard classification of pixels for further processing of these images. We have validated the performance of our algorithm on Moderate Resolution Imaging Spectroradiometer (MODIS) images and established its superiority over the results obtained by thresholding techniques in presence of noise such as clouds in presence of ice land cover.

First Page

80

Last Page

83

DOI

10.1109/IGARSS.2016.7729011

Publication Date

11-1-2016

Recommended Citation

Danda, Sravan; Challa, Aditya; and Daya Sagar, B. S., "A morphology-based approach for cloud detection" (2016). Conference Articles. 651.
https://digitalcommons.isical.ac.in/conf-articles/651