Deep learning for Landslide recognition in Satellite architecture

Using the optical camera in remote sensing is limited in various environmental conditions. This paper presents a system of combining deep learning and image transform algorithms to detect landslide location in satellite images. In the deep learning part, a convolution neural network is used to class...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2020-01, Vol.8, p.1-1
Main Authors: Bui, Trong-An, Lee, Pei-Jun, Lum, Kei-Yew, Loh, Clarissa, Tan, Kyo
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Artificial satellites
CNN
Convolution
Deep learning
Earth
Empirical mode decomposition
H-BEMD
Image classification
landslide localization
Landslides
Landslides & mudslides
Machine learning
object recognition
Remote sensing
satellite image
Satellite imagery
Satellites
Terrain factors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Using the optical camera in remote sensing is limited in various environmental conditions. This paper presents a system of combining deep learning and image transform algorithms to detect landslide location in satellite images. In the deep learning part, a convolution neural network is used to classify satellite images contain landslides. From landslide images classified, in order to accurately identify landslides under different lighting conditions, this paper proposes a transformation algorithm Hue - Bi-dimensional empirical mode decomposition (H-BEMD) to determine the landslide region and size. After the location of landslide is detected, we discover the size change of the landslide based on different time points. In this study, we record an accuracy of up to 96% in the classification process, and the accuracy of landslide location almost absolute.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2020.3014305