Learning and Adapting Robust Features for Satellite Image Segmentation on Heterogeneous Data Sets

This paper addresses the problem of training a deep neural network for satellite image segmentation so that it can be deployed over images whose statistics differ from those used for training. For example, in postdisaster damage assessment, the tight time constraints make it impractical to train a n...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on geoscience and remote sensing Jg. 57; H. 9; S. 6517 - 6529
Hauptverfasser: Ghassemi, Sina, Fiandrotti, Attilio, Francini, Gianluca, Magli, Enrico
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 01.09.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Artificial neural networks
Coders
Convolutional neural network (CNN)
Damage assessment
Datasets
deep learning
domain adaptation
encoder–decoder architecture
Human performance
Image processing
Image segmentation
Neural networks
satellite image segmentation
Satellite imagery
Spaceborne remote sensing
Statistical methods
Statistics
Target recognition
Training
ISSN:0196-2892, 1558-0644
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper addresses the problem of training a deep neural network for satellite image segmentation so that it can be deployed over images whose statistics differ from those used for training. For example, in postdisaster damage assessment, the tight time constraints make it impractical to train a network from scratch for each image to be segmented. We propose a convolutional encoder-decoder network able to learn visual representations of increasing semantic level as its depth increases, allowing it to generalize over a wider range of satellite images. Then, we propose two additional methods to improve the network performance over each specific image to be segmented. First, we observe that updating the batch normalization layers' statistics over the target image improves the network performance without human intervention. Second, we show that refining a trained network over a few samples of the image boosts the network performance with minimal human intervention. We evaluate our architecture over three data sets of satellite images, showing the state-of-the-art performance in binary segmentation of previously unseen images and competitive performance with respect to more complex techniques in a multiclass segmentation task.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0196-2892
1558-0644
DOI:10.1109/TGRS.2019.2906689