Robust unsupervised small area change detection from SAR imagery using deep learning

[Display omitted] •A multiscale superpixel reconstruction method was developed to generate the Difference Image.•A two-stage center-constrained FCM algorithm was designed to deal with imbalanced data clustering.•CWNN combined with DCGAN was adopted to classify hard pixels. Small area change detectio...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:ISPRS journal of photogrammetry and remote sensing Jg. 173; S. 79 - 94
Hauptverfasser: Zhang, Xinzheng, Su, Hang, Zhang, Ce, Gu, Xiaowei, Tan, Xiaoheng, Atkinson, Peter M.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier B.V 01.03.2021
Schlagworte:
algorithms
Change detection
data collection
Deep learning
Difference image
Fuzzy c-means algorithm
photogrammetry
Synthetic aperture radar
wavelet
Deep learning
Fuzzy c-means algorithm
Change detection
Synthetic aperture radar
Difference image
ISSN:0924-2716, 1872-8235
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:[Display omitted] •A multiscale superpixel reconstruction method was developed to generate the Difference Image.•A two-stage center-constrained FCM algorithm was designed to deal with imbalanced data clustering.•CWNN combined with DCGAN was adopted to classify hard pixels. Small area change detection using synthetic aperture radar (SAR) imagery is a highly challenging task, due to speckle noise and imbalance between classes (changed and unchanged). In this paper, a robust unsupervised approach is proposed for small area change detection using deep learning techniques. First, a multi-scale superpixel reconstruction method is developed to generate a difference image (DI), which can suppress the speckle noise effectively and enhance edges by exploiting local, spatially homogeneous information. Second, a two-stage centre-constrained fuzzy c-means clustering algorithm is proposed to divide the pixels of the DI into changed, unchanged and intermediate classes with a parallel clustering strategy. Image patches belonging to the first two classes are then constructed as pseudo-label training samples, and image patches of the intermediate class are treated as testing samples. Finally, a convolutional wavelet neural network (CWNN) is designed and trained to classify testing samples into changed or unchanged classes, coupled with a deep convolutional generative adversarial network (DCGAN) to increase the number of changed class within the pseudo-label training samples. Numerical experiments on four real SAR datasets demonstrate the validity and robustness of the proposed approach, achieving up to 99.61% accuracy for small area change detection.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0924-2716
1872-8235
DOI:10.1016/j.isprsjprs.2021.01.004