SAR Image Generation Using a Modified CycleGAN
- 주제(키워드) SAR , Deep Learning , CycleGAN , Filter
- 주제(DDC) 004.6
- 발행기관 아주대학교
- 지도교수 김재현
- 발행년도 2022
- 학위수여년월 2022. 2
- 학위명 석사
- 학과 및 전공 일반대학원 AI융합네트워크학과
- 실제URI http://www.dcollection.net/handler/ajou/000000031528
- 본문언어 한국어
- 저작권 아주대학교 논문은 저작권에 의해 보호받습니다.
초록/요약
The important issue of synthetic aperture radar (SAR) image is the amount of dataset, because it is hard to obtain the image suitable for the purpose. This shortcoming can be complemented through using deep learning. Deep learning processes a large amount of data and performs the desired research, which is used in various fields. This thesis propose the method using deep learning model to generate images similar to original optical and SAR images, and we adopt CycleGAN as our model. CycleGAN is a method to generate images by using unpaired datasets. To remove speckle noise, we apply several filters to enhance the accuracy of the model. Moreover, this thesis uses other deep learning models to compare the precision, and performs quantitative analysis using several indexes. Experiment result shows that the generated images maintain the features of original images, and filtered images are more similar to original SAR images than non-filtered images.
more목차
1. Introduction 1
1.1 Background 1
1.2 Motivation and contributions 3
1.3 Overview 4
2. Related Works 5
2.1 GAN 5
2.2 Image filters 11
2.3 SAR image processing 13
2.4 Process of sentinel's application platform (SNAP) 16
3. Proposed Deep Learning Model with SAR 18
3.1 Proposed Model 18
3.2 Environment 24
3.3 Indicators 27
4. Experiment Result 29
4.1 Original image and generated image by CycleGAN 29
4.2 Generated images by different models 31
4.3 Generated images before and after the filtering 32
4.4 Generated images by several filters 34
5. Conclusion 36
