Title
Image Translation Between High-Resolution Remote Sensing Optical and SAR Data Using Conditional GAN.
Abstract
This paper presents a study on a new problem: applying machine learning approaches to translate remote sensing images between high-resolution optical and Synthetic Aperture Radar (SAR) data. To this end, conditional Generative Adversarial Networks (GAN) have been explored. Efficiency of the conditional GAN have been verified with different SAR parameters on three regions from the world: Toronto, Vancouver in Canada and Shanghai in China. The generated SAR images have been evaluated by pixel-based image classification with detailed land cover types including: low and high density residential area, industry area, construction site, golf course, water, forest, pasture and crops. In comparison with an unsupervised GAN translation approach, the proposed conditional GAN could effectively keep many land cover types with compatible classification accuracy to the ground truth SAR data. This is one of first study on multi-source remote sensing data translation by machine learning.
Year
DOI
Venue
2018
10.1007/978-3-030-00764-5_23
ADVANCES IN MULTIMEDIA INFORMATION PROCESSING, PT III
Keywords
Field
DocType
Remote sensing,Generative Adversarial Network,Deep learning
Image translation,Computer vision,Synthetic aperture radar,Computer science,Remote sensing,Residential area,Ground truth,Pixel,Artificial intelligence,Deep learning,Contextual image classification,Land cover
Conference
Volume
ISSN
Citations 
11166
0302-9743
0
PageRank 
References 
Authors
0.34
11
5
Name
Order
Citations
PageRank
Xin Niu15611.39
Di Yang2395.66
Ke Yang351.78
Hengyue Pan400.34
Yong Dou563289.67