Back to Search
Start Over
Remote Sensing Data Augmentation Through Adversarial Training
- Source :
- IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 9318-9333 (2021), IGARSS
- Publication Year :
- 2021
- Publisher :
- IEEE, 2021.
-
Abstract
- The lack of remote sensing images and poor quality limit the performance improvement of follow-up research such as remote sensing interpretation. In this article, a generative adversarial network (GAN) is proposed for data augmentation of remote sensing images abstracted from Jiangxi and Anhui Provinces in China, i.e., deeply supervised GAN (D-sGAN). D-sGAN can generate high-quality images that are rich in changes, greatly shorten the generation time, and provide data support for applications such as semantic interpretation of remote sensing images. First, to modulate the layer activations, a downsampling scheme is designed based on the segmentation map. Then, the architecture of the generator is Unet++ with the proposed downsampling module. Next, the generator of this net is deeply supervised by the discriminator using deep convolutional neural network. This article further proved that the proposed downsampling module and the dense connection characteristics of UNet++ are significantly beneficial to the retention of semantic information of remote sensing images. Numerical results demonstrated that the images generated by D-sGAN could be used to improve accuracy of the segmentation network, with the faster generation speed compared to the CoGAN, SimGAN, and CycleGAN models. Furthermore, the remote sensing data generated by the model helped the interpretation network to increase the accuracy by 9%, meeting actual generation requirements.
- Subjects :
- Scheme (programming language)
Atmospheric Science
Discriminator
Data augmentation
Computer science
Semantic interpretation
Geophysics. Cosmic physics
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
02 engineering and technology
010501 environmental sciences
01 natural sciences
Convolutional neural network
Upsampling
0202 electrical engineering, electronic engineering, information engineering
Segmentation
Layer (object-oriented design)
Computers in Earth Sciences
TC1501-1800
0105 earth and related environmental sciences
computer.programming_language
Remote sensing
QC801-809
deep supervision
020206 networking & telecommunications
Image segmentation
GAN
Ocean engineering
Remote sensing (archaeology)
Performance improvement
computer
downsampling
Generator (mathematics)
Subjects
Details
- Language :
- English
- ISSN :
- 21511535
- Volume :
- 14
- Database :
- OpenAIRE
- Journal :
- IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Accession number :
- edsair.doi.dedup.....4b8c89b64f01e40590efb52f845d0f7c