Classification of Hyperspectral Images Using SVM with Shape-Adaptive Reconstruction and Smoothed Total Variation (2022-03-29T00:00:00.000000Z)

TL;DR

Experiments show that SaR-SVM- STY outperforms the SVM-STV method with a few training labels, demonstrating the significance of reconstructing hy-perspectral images before classification.

Abstract

In this work, a novel algorithm called SVM with Shape-adaptive Reconstruction and Smoothed Total Variation (SaR-SVM-STV) is introduced to classify hyperspectral images, which makes full use of spatial and spectral information. The Shape-adaptive Reconstruction (SaR) is introduced to preprocess each pixel based on the Pearson Correlation be-tween pixels in its shape-adaptive (SA) region. Support Vector Machines (SVMs) are trained to estimate the pixel-wise probability maps of each class. Then the Smoothed Total Variation (STV) model is applied to denoise and generate the final classification map. Experiments show that SaR-SVM-STY outperforms the SVM-STV method with a few training labels, demonstrating the significance of reconstructing hy-perspectral images before classification.

Authors

Kangning Cui

3 papers

R. Li

2 papers

R. Plemmons

2 papers

Classification of Hyperspectral Images Using SVM with Shape-Adaptive Reconstruction and Smoothed Total Variation

TL;DR

Abstract

Authors

References26 items

The minimal exponent and k-rationality for local complete intersections

Active Diffusion and VCA-Assisted Image Segmentation of Hyperspectral Images

Change Detection of Amazonian Alluvial Gold Mining Using Deep Learning and Sentinel-2 Imagery

Unsupervised Classification of Aviris-NG Hyperspectral Images

A Multiscale Environment for Learning by Diffusion

An SVM-Based Nested Sliding Window Approach for Spectral-Spatial Classification of Hyperspectral Images

Bio-inspired synthesis of xishacorenes A, B, and C, and a new congener from fuscol

A two-stage method for spectral–spatial classification of hyperspectral images

Learning Spatial–Spectral Features for Hyperspectral Image Classification

Modern Trends in Hyperspectral Image Analysis: A Review

Nonlinear Unsupervised Clustering of Hyperspectral Images with Applications to Anomaly Detection and Active Learning

Hyperspectral Image Classification Via Shape-Adaptive Joint Sparse Representation

A Three-Stage Approach for Segmenting Degraded Color Images: Smoothing, Lifting and Thresholding (SLaT)

A Nonlocal Weighted Joint Sparse Representation Classification Method for Hyperspectral Imagery

Spatial-Spectral Kernel Sparse Representation for Hyperspectral Image Classification

Hyperspectral Remote Sensing

A Two-Stage Image Segmentation Method Using a Convex Variant of the Mumford-Shah Model and Thresholding

LIBSVM: A library for support vector machines

Pointwise Shape-Adaptive DCT for High-Quality Denoising and Deblocking of Grayscale and Color Images

Composite kernels for hyperspectral image classification

Classification of hyperspectral remote sensing images with support vector machines

Diffusion and Volume Maximization-Based Clustering of Highly Mixed Hyperspectral Images

Change Detection of Small Water Bodies in Alluvial Gold Min-2 ing Satellite Imagery

and Murphy J

I and J

AND T

Field of Study

Journal Information

Name

Page

Venue Information

Name

Type

URL

Alternate Names