Snow Avalanche Segmentation in SAR Images With Fully Convolutional Neural Networks

Knowledge about frequency and location of snow avalanche activity is essential for forecasting and mapping of snow avalanche hazard. Traditional field monitoring of avalanche activity has limitations, especially when surveying large and remote areas. In recent years, avalanche detection in Sentinel-...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in applied earth observations and remote sensing 2021-01, Vol.14, p.75-82
Main Authors: Bianchi, Filippo Maria, Grahn, Jakob, Eckerstorfer, Markus, Malnes, Eirik, Vickers, Hannah
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Avalanches
Backscatter
Backscattering
Convolutional neural networks (CNNs)
Deep learning
Detection
Image processing
Image segmentation
Imagery
Informasjons- og kommunikasjonsteknologi: 550
Information and communication technology: 550
Information processing
Inspection
Landslides
Machine learning
Monitoring
Neural networks
Peak to average power ratio
Radar
Radar detection
Radar imaging
Radar satellites
saliency segmentation
SAR (radar)
Satellite imagery
Sentinel-1 (S1)
Signal processing
Snow
Snow avalanches
Spaceborne remote sensing
Surveying
Synthetic aperture radar
synthetic aperture radar (SAR)
Technology: 500
Teknologi: 500
VDP
Visual inspection
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:Knowledge about frequency and location of snow avalanche activity is essential for forecasting and mapping of snow avalanche hazard. Traditional field monitoring of avalanche activity has limitations, especially when surveying large and remote areas. In recent years, avalanche detection in Sentinel-1 radar satellite imagery has been developed to improve monitoring. However, the current state-of-the-art detection algorithms, based on radar signal processing techniques, are still much less accurate than human experts. To reduce this gap, we propose a deep learning architecture for detecting avalanches in Sentinel-1 radar images. We trained a neural network on 6345 manually labeled avalanches from 117 Sentinel-1 images, each one consisting of six channels that include backscatter and topographical information. Then, we tested our trained model on a new synthetic aperture radar image. Comparing to the manual labeling (the gold standard), we achieved an F1 score above 66%, whereas the state-of-the-art detection algorithm sits at an F1 score of only 38%. A visual inspection of the results generated by our deep learning model shows that only small avalanches are undetected, whereas some avalanches that were originally not labeled by the human expert are discovered.
ISSN:1939-1404
1558-0644
0196-2892
2151-1535
1558-0644
DOI:10.1109/JSTARS.2020.3036914