Unsupervised change detection method in SAR images based on deep belief network using an improved fuzzy C‐means clustering algorithm

Deep learning methods have recently displayed ground‐breaking results for synthetic aperture radar image change detection problem. However, they still face the challenges of intrinsic noise and the difficulty of acquiring labeled data. To sort out these issues, we aim to develop a change detection a...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IET image processing Ročník 15; číslo 4; s. 974 - 982
Hlavní autoři:	Attioui, Sanae, Najah, Said
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Wiley 01.03.2021
Témata:	Algebra, set theory, and graph theory Data and information; acquisition, processing, storage and dissemination in geophysics Filtering methods in signal processing Image recognition Instrumentation and techniques for geophysical, hydrospheric and lower atmosphere research Radar theory
ISSN:	1751-9659, 1751-9667
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	Deep learning methods have recently displayed ground‐breaking results for synthetic aperture radar image change detection problem. However, they still face the challenges of intrinsic noise and the difficulty of acquiring labeled data. To sort out these issues, we aim to develop a change detection approach specifically designed for analyzing synthetic aperture radar images based on Deep Belief Network as the deep architecture which includes unsupervised feature learning and supervised network fine‐tuning. The deep neural networks can reach the final change maps directly from the two original images. A pre‐classification based on Morphological Reconstruction and Membership Filtering is employed in order to minimize the effect of noise. Appropriate diversity samples are provided by a virtual sample generation method in order to mitigate overfitting raised by limited synthetic aperture radar data. Visual and quantitative analysis as well as comparisons with advanced algorithms show that our algorithm not only achieves better results but also requires less implementation time.
ISSN:	1751-9659 1751-9667
DOI:	10.1049/ipr2.12078