Cycle-Consistent Adversarial Networks for Realistic Pervasive Change Generation in Remote Sensing Imagery

This paper introduces a new method of generating realistic pervasive changes in the context of evaluating the effectiveness of change detection algorithms in controlled settings. The method - a cycle-consistent adversarial network (CycleGAN) - requires low quantities of training data to generate rea...

Full description

Saved in:
Bibliographic Details
Published in2020 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI) Vol. 2020; pp. 42 - 45
Main Authors Ren, Christopher X., Ziemann, Amanda, Theiler, James, Durieux, Alice M.S.
Format Conference Proceeding Journal Article
LanguageEnglish
Published United States IEEE 01.03.2020
Subjects
change detection
Change detection algorithms
Data models
Deep learning
Detection algorithms
Gallium nitride
generative adversarial networks
image analysis
Machine Learning
MATHEMATICS AND COMPUTING
multispectral
Remote Sensing
Robustness
Terrain factors
Online AccessGet full text

Cover

More Information
Summary:This paper introduces a new method of generating realistic pervasive changes in the context of evaluating the effectiveness of change detection algorithms in controlled settings. The method - a cycle-consistent adversarial network (CycleGAN) - requires low quantities of training data to generate realistic changes. Here we show an application of CycleGAN in creating realistic snow-covered scenes of multispectral Sentinel-2 imagery, and demonstrate how these images can be used as a test bed for anomalous change detection algorithms.
Bibliography:USDOE Laboratory Directed Research and Development (LDRD) Program
LA-UR-19-31936
89233218CNA000001
ISSN:2473-3598
2473-3598
DOI:10.1109/SSIAI49293.2020.9094603