Kasra Rafiezadeh Shahi, Pedram Ghamisi, Behnood Rasti, Richard Gloaguen, and Paul Scheunders

Illustration of the proposed method.

Illustration of the proposed multiscale spectral–spatial association network.

Remote sensing hyperspectral cameras acquire high spectral-resolution data that reveal valuable composition information on the targets (e.g., for Earth observation and environmental applications). The intrinsic high dimensionality and the lack of sufficient numbers of labeled/training samples prevent efficient processing of hyperspectral images (HSIs). HSI clustering can alleviate these limitations. In this study, we propose a multiscale spectral–spatial association network (MS2A-Net) to cluster HSIs. The backbone of MS2A-Net is an autoencoder architecture that allows the network to capture the nonlinear relation between data points in an unsupervised manner. The network applies a multistream approach. One stream extracts spectral information by deploying a spectral association unit. The other stream derives multiscale contextual and spatial information by employing dilated (atrous) convolutional kernels. The obtained feature representation generated by MS2A-Net is fed into a standard k-means clustering algorithm to produce the final clustering result. Extensive experiments on four HSIs for different types of applications (i.e., geological-, rural-, and urban-mapping) demonstrate the superior performance of MS2A-Net over the state-of-the-art shallow/deep learning-based clustering approaches in terms of clustering accuracy.

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 6518-6530, 2022-08-11.

Download
View paper
IARAI Authors
Dr. Pedram Ghamisi
Research
Algorithms, Remote Sensing
Keywords
Convolutional Autoencoder, Deep Learning, Hyperspectral Image, Image Clustering, Remote Sensing

©2022 IARAI - INSTITUTE OF ADVANCED RESEARCH IN ARTIFICIAL INTELLIGENCE

Imprint | Privacy Policy

Stay in the know with developments at IARAI

We can let you know if there’s any

updates from the Institute.
You can later also tailor your news feed to specific research areas or keywords (Privacy)
Loading

Log in with your credentials

Forgot your details?

Create Account