Stacked Sparse Autoencoder in PolSAR Data Classification Using Local Spatial Information

Terrain classification is an important topic in polarimetric synthetic aperture radar (PolSAR) image processing. Among various classification techniques, the stacked sparse autoencoder (SSAE) is a kind of deep learning method that can automatically learn useful features layer by layer in an unsuperv...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE geoscience and remote sensing letters Ročník 13; číslo 9; s. 1359 - 1363
Hlavní autoři: Zhang, Lu, Ma, Wenping, Zhang, Dan
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 01.09.2016
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Classification
Cost function
Data mining
Deep learning
Feature extraction
Image classification
Image processing
Learning
local spatial information
Machine learning
Pixels
polarimetric synthetic aperture radar (PolSAR)
Remote sensing
Scattering
sparse
Speckle
stacked sparse autoencoder (SSAE)
Synthetic aperture radar
Training
ISSN:1545-598X, 1558-0571
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Terrain classification is an important topic in polarimetric synthetic aperture radar (PolSAR) image processing. Among various classification techniques, the stacked sparse autoencoder (SSAE) is a kind of deep learning method that can automatically learn useful features layer by layer in an unsupervised manner. However, the scattering measurements of individual pixels in PolSAR images are affected by the speckle; hence, the performance of pixel-based classification approaches would be poor. In this situation, a novel framework is proposed to learn robust features of PolSAR data. The local spatial information is introduced into SSAE to learn the deep spatial sparse features automatically for the first time. Furthermore, the influences of the neighbor pixels on the central pixel are controlled depending on the spatial distances from the neighbor pixels to the central pixel. Experimental results with fully PolSAR data indicate that the proposed method provides a competitive solution.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2016.2586109