Novel Spectral Loss Function for Unsupervised Hyperspectral Image Segmentation

Neural networks (NNs) have gained importance in hyperspectral image (HSI) segmentation for earth observation due to its unparalleled data-driven feature extraction capability. However, in many real-life situations, ground truth is not available, and the performance of unsupervised NNs is still susce...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters 2023-01, Vol.20, p.1-1
Main Authors: Perez-Garcia, Ambar, Paoletti, Mercedes E., Haut, Juan M., Lopez, Jose F.
Format: Article
Language:English
Subjects:
Artificial neural networks
autoencoder (AE)
Benchmarks
Convolutional codes
Feature extraction
Geoscience and remote sensing
Hyperspectral images (HSIs)
Hyperspectral imaging
Image processing
Image reconstruction
Image segmentation
Neural networks
Neurons
Oil spills
Performance enhancement
semantic segmentation
Source code
Spectral signatures
Three-dimensional displays
unsupervised learning
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Neural networks (NNs) have gained importance in hyperspectral image (HSI) segmentation for earth observation due to its unparalleled data-driven feature extraction capability. However, in many real-life situations, ground truth is not available, and the performance of unsupervised NNs is still susceptible to enhancement. To overcome this challenge, this letter presents a new loss function to improve the performance of unsupervised HSI segmentation models. The spectral loss function, Sl , which can be included in different models, is based on the purity of the unmixing endmembers and the spectral similarity of the clusters provided by the NN to determine the classes. It is incorporated into a 3D convolutional autoencoder to validate its performance on four standard HSI benchmarks. Furthermore, its performance has been qualitatively examined in a real case study, an oil spill without ground truth. The results show that Sl is a breakthrough in unsupervised HS segmentation, obtaining the best overall performance and highlighting the importance of spectral signatures. Additionally, dimensional reduction is also vital in compacting the spectral information, which facilitates its segmentation. Source code available at [https://github.com/mhaut/HSI-3DSpLoss].
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2023.3288809