Unsupervised Change Detection in Satellite Images With Generative Adversarial Network

被引:38
|
作者
Ren, Caijun [1 ]
Wang, Xiangyu [1 ]
Gao, Jian [2 ]
Zhou, Xiren [3 ]
Chen, Huanhuan [1 ]
机构
[1] Univ Sci & Technol China USTC, Sch Comp Sci & Technol, UBRI, Hefei 230027, Peoples R China
[2] StarGIS Technol Dev Co Ltd, Tianjin 300384, Peoples R China
[3] Iflytek Co Ltd, Hefei 230088, Peoples R China
来源
基金
中国国家自然科学基金;
关键词
Feature extraction; Generative adversarial networks; Deep learning; Satellites; Task analysis; Gallium nitride; Generators; Change detection; deep learning; generative adversarial networks (GANs); satellite images; unsupervised; CHANGE VECTOR ANALYSIS; SLOW FEATURE ANALYSIS;
D O I
10.1109/TGRS.2020.3043766
中图分类号
P3 [地球物理学]; P59 [地球化学];
学科分类号
0708 ; 070902 ;
摘要
Detecting changed regions in paired satellite images plays a key role in many remote sensing applications. The evolution of recent techniques could provide satellite images with a very high spatial resolution (VHR) but made it challenging to apply image coregistration, and many change detection methods are dependent on its accuracy. Two images of the same scene taken at different times or from different angles would introduce unregistered objects and the existence of both unregistered areas and actual changed areas would lower the performance of many change detection algorithms in unsupervised conditions. To alleviate the effect of unregistered objects in the paired images, we propose a novel change detection framework utilizing a special neural network architecture Generative Adversarial Network (GAN) to generate many better coregistered images. In this article, we show that the GAN model can be trained upon a pair of images by using the proposed expanding strategy to create a training set and optimizing designed objective functions. The optimized GAN model would produce better coregistered images where changes can be easily spotted and then the change map can be presented through a comparison strategy using these generated images explicitly. Compared to other deep learning-based methods, our method is less sensitive to the problem of unregistered images and makes most of the deep learning structure. Experimental results on synthetic images and real data with many different scenes could demonstrate the effectiveness of the proposed approach.
引用
收藏
页码:10047 / 10061
页数:15
相关论文
共 50 条
  • [1] GAN-FuzzyNN: Optimization Based Generative Adversarial Network and Fuzzy Neural Network Classification for Change Detection in Satellite Images
    K. R. Gite
    Praveen Gupta
    Sensing and Imaging, 24
  • [2] GAN-FuzzyNN: Optimization Based Generative Adversarial Network and Fuzzy Neural Network Classification for Change Detection in Satellite Images
    Gite, K. R.
    Gupta, Praveen
    SENSING AND IMAGING, 2023, 24 (01):
  • [3] Method for unsupervised change detection in satellite images
    Celik, T.
    ELECTRONICS LETTERS, 2010, 46 (09) : 624 - U41
  • [4] Fully Convolutional Change Detection Framework With Generative Adversarial Network for Unsupervised, Weakly Supervised and Regional Supervised Change Detection
    Wu, Chen
    Du, Bo
    Zhang, Liangpei
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2023, 45 (08) : 9774 - 9788
  • [5] Prediction of a typhoon track using a generative adversarial network and satellite images
    Ruttgers, Mario
    Lee, Sangseung
    Jeon, Soohwan
    You, Donghyun
    SCIENTIFIC REPORTS, 2019, 9 (1)
  • [6] Prediction of a typhoon track using a generative adversarial network and satellite images
    Mario Rüttgers
    Sangseung Lee
    Soohwan Jeon
    Donghyun You
    Scientific Reports, 9
  • [7] Unsupervised Feature Extraction in Hyperspectral Images Based on Wasserstein Generative Adversarial Network
    Zhang, Mingyang
    Gong, Maoguo
    Mao, Yishun
    Li, Jun
    Wu, Yue
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2019, 57 (05): : 2669 - 2688
  • [8] Descriptors based Unsupervised Change Detection in Satellite Images
    Pillai, Gargi V.
    Gupta, Neha
    Ari, Samit
    2017 INTERNATIONAL CONFERENCE ON COMMUNICATION AND SIGNAL PROCESSING (ICCSP), 2017, : 1629 - 1633
  • [9] Transferemble: a classification method for the detection of fake satellite images created with deep convolutional generative adversarial network
    Surucu, Selim
    Diri, Banu
    JOURNAL OF ELECTRONIC IMAGING, 2023, 32 (04)
  • [10] Unsupervised Multiple Change Detection in Remote Sensing Images via Generative Representation Learning Network
    Shi, Jiao
    Zhang, Zeping
    Tan, Chunhui
    Liu, Xiaodong
    Lei, Yu
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2022, 19