Dimension Reduction of Combined Image and Elevation Remote Sensing Data Using UMAP, Autoencoders, and Variational Autoencoders: Investigation on Shaded Regions

Dimension reduction is a commonplace tool to visualize multi-dimensional data and reparametrize the features to have uniform, metric scales. With a concept of training a Machine Learning method with scarce training data in mind, we wish to investigate to what extent several well-known dimension redu...

Full description

Saved in:
Bibliographic Details
Published inIGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium pp. 7443 - 7446
Main Authors Bulatov, Dimitri, Boge, Melanie, Debroize, Denis, Haufel, Gisela, Qiu, Kevin
Format Conference Proceeding
LanguageEnglish
Published IEEE 16.07.2023
Subjects
Automobiles
classification
clustering
dimension reduction
Dimensionality reduction
features
Measurement
Point cloud compression
shadows
Three-dimensional displays
Training
Training data
Online AccessGet full text

Cover

More Information
Summary:Dimension reduction is a commonplace tool to visualize multi-dimensional data and reparametrize the features to have uniform, metric scales. With a concept of training a Machine Learning method with scarce training data in mind, we wish to investigate to what extent several well-known dimension reducers are suitable to separate very challenging remote sensing data, in particular, in shadow regions. The Potsdam data includes not only plenty of these regions, but also several seldom classes, such as vehicles or clutter. Hence, optical and elevation data as well as some additional features will be used as input for dimension reduction algorithms.
ISSN:2153-7003
DOI:10.1109/IGARSS52108.2023.10283014