Cascaded hybrid convolutional autoencoder network for spectral-spatial nonlinear hyperspectral unmixing

Due to the complex interaction of photons between materials, linear hyperspectral unmixing (HU) is limited in real scenarios, making nonlinear unmixing a promising alternative. With the advancement of deep learning (DL), nonlinear unmixing methods based on the convolutional autoencoder (CAE) have ga...

Full description

Saved in:
Bibliographic Details
Published in:International journal of remote sensing Vol. 45; no. 24; pp. 9267 - 9286
Main Authors: Wu, Jinbin, Zhao, Jiankang, Long, Haihui
Format: Journal Article
Language:English
Published: London Taylor & Francis 16.12.2024
Taylor & Francis Ltd
Subjects:
data collection
Hybrid convolution
hybrids
hyperspectral image (HSI)
Image reconstruction
nonlinear unmixing
Perception
Self image
self-perception
Spatial data
Traction
ISSN:0143-1161, 1366-5901, 1366-5901
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Due to the complex interaction of photons between materials, linear hyperspectral unmixing (HU) is limited in real scenarios, making nonlinear unmixing a promising alternative. With the advancement of deep learning (DL), nonlinear unmixing methods based on the convolutional autoencoder (CAE) have gained considerable traction in HU. However, these unmixing methods struggle to integrate spectral and spatial information while reducing the loss of material details during the unmixing process. Therefore, we propose a cascaded hybrid CAE nonlinear unmixing network, called CHCANet, which effectively leverages convolutional combinations to deeply explore the spectral-spatial information from hyperspectral data and preserve the material details through self-perception. Specifically, each CAE in CHCANet combines 1-D and 2-D convolutions, fully utilizing the flexibility and simplicity of 1-D convolutions to capture spectral features and the spatial correlation handling capability of the 2-D convolution. Moreover, we apply the self-perception mechanism to the nonlinear HU task, which can establish the cycle consistency of the network, strengthen mutual connections between encoders, and effectively preserve high-level semantic information. Following this, the optimized self-perception loss further enhances CHCANet's perception capability of nonlinear components and strengthens the connection between the decoder directly associated with image reconstruction. Extensive experiments on synthetic and real datasets demonstrate the effectiveness of CHCANet and show excellent competitiveness compared to state-of-the-art unmixing methods.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:0143-1161
1366-5901
1366-5901
DOI:10.1080/01431161.2024.2408038