Home > Research > Publications & Outputs > Robust unsupervised small area change detection...

Electronic data

  • ISPRS_Accepted

    Rights statement: This is the author’s version of a work that was accepted for publication in ISPRS Journal of Photogrammetry and Remote Sensing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in ISPRS Journal of Photogrammetry and Remote Sensing, 173, 2021 DOI: 10.1016/j.isprsjprs.2021.01.004

    Accepted author manuscript, 4.49 MB, PDF document

    Embargo ends: 17/01/22

    Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

Links

Text available via DOI:

View graph of relations

Robust unsupervised small area change detection from SAR imagery using deep learning

Research output: Contribution to journalJournal articlepeer-review

Published

Standard

Robust unsupervised small area change detection from SAR imagery using deep learning. / Zhang, Xinzheng; Su, Hang; Zhang, Ce; Gu, Xiaowei; Tan, Xiaoheng; Atkinson, Peter.

In: ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 173, 01.03.2021, p. 79-94.

Research output: Contribution to journalJournal articlepeer-review

Harvard

Zhang, X, Su, H, Zhang, C, Gu, X, Tan, X & Atkinson, P 2021, 'Robust unsupervised small area change detection from SAR imagery using deep learning', ISPRS Journal of Photogrammetry and Remote Sensing, vol. 173, pp. 79-94. https://doi.org/10.1016/j.isprsjprs.2021.01.004

APA

Zhang, X., Su, H., Zhang, C., Gu, X., Tan, X., & Atkinson, P. (2021). Robust unsupervised small area change detection from SAR imagery using deep learning. ISPRS Journal of Photogrammetry and Remote Sensing, 173, 79-94. https://doi.org/10.1016/j.isprsjprs.2021.01.004

Vancouver

Zhang X, Su H, Zhang C, Gu X, Tan X, Atkinson P. Robust unsupervised small area change detection from SAR imagery using deep learning. ISPRS Journal of Photogrammetry and Remote Sensing. 2021 Mar 1;173:79-94. https://doi.org/10.1016/j.isprsjprs.2021.01.004

Author

Zhang, Xinzheng ; Su, Hang ; Zhang, Ce ; Gu, Xiaowei ; Tan, Xiaoheng ; Atkinson, Peter. / Robust unsupervised small area change detection from SAR imagery using deep learning. In: ISPRS Journal of Photogrammetry and Remote Sensing. 2021 ; Vol. 173. pp. 79-94.

Bibtex

@article{c797281b222a4d62ad68fa3bbb398f0d,
title = "Robust unsupervised small area change detection from SAR imagery using deep learning",
abstract = "Small area change detection using synthetic aperture radar (SAR) imagery is a highly challenging task, due to speckle noise and imbalance between classes (changed and unchanged). In this paper, a robust unsupervised approach is proposed for small area change detection using deep learning techniques. First, a multi-scale superpixel reconstruction method is developed to generate a difference image (DI), which can suppress the speckle noise effectively and enhance edges by exploiting local, spatially homogeneous information. Second, a two-stage centre-constrained fuzzy c-means clustering algorithm is proposed to divide the pixels of the DI into changed, unchanged and intermediate classes with a parallel clustering strategy. Image patches belonging to the first two classes are then constructed as pseudo-label training samples, and image patches of the intermediate class are treated as testing samples. Finally, a convolutional wavelet neural network (CWNN) is designed and trained to classify testing samples into changed or unchanged classes, coupled with a deep convolutional generative adversarial network (DCGAN) to increase the number of changed class within the pseudo-label training samples. Numerical experiments on four real SAR datasets demonstrate the validity and robustness of the proposed approach, achieving up to 99.61% accuracy for small area change detection.",
keywords = "Change detection, Synthetic aperture radar, Difference image, Fuzzy c-means algorithm, Deep learning",
author = "Xinzheng Zhang and Hang Su and Ce Zhang and Xiaowei Gu and Xiaoheng Tan and Peter Atkinson",
note = "This is the author{\textquoteright}s version of a work that was accepted for publication in ISPRS Journal of Photogrammetry and Remote Sensing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in ISPRS Journal of Photogrammetry and Remote Sensing, 173, 2021 DOI: 10.1016/j.isprsjprs.2021.01.004 ",
year = "2021",
month = mar,
day = "1",
doi = "10.1016/j.isprsjprs.2021.01.004",
language = "English",
volume = "173",
pages = "79--94",
journal = "ISPRS Journal of Photogrammetry and Remote Sensing",
issn = "0924-2716",
publisher = "Elsevier Science B.V.",

}

RIS

TY - JOUR

T1 - Robust unsupervised small area change detection from SAR imagery using deep learning

AU - Zhang, Xinzheng

AU - Su, Hang

AU - Zhang, Ce

AU - Gu, Xiaowei

AU - Tan, Xiaoheng

AU - Atkinson, Peter

N1 - This is the author’s version of a work that was accepted for publication in ISPRS Journal of Photogrammetry and Remote Sensing. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in ISPRS Journal of Photogrammetry and Remote Sensing, 173, 2021 DOI: 10.1016/j.isprsjprs.2021.01.004

PY - 2021/3/1

Y1 - 2021/3/1

N2 - Small area change detection using synthetic aperture radar (SAR) imagery is a highly challenging task, due to speckle noise and imbalance between classes (changed and unchanged). In this paper, a robust unsupervised approach is proposed for small area change detection using deep learning techniques. First, a multi-scale superpixel reconstruction method is developed to generate a difference image (DI), which can suppress the speckle noise effectively and enhance edges by exploiting local, spatially homogeneous information. Second, a two-stage centre-constrained fuzzy c-means clustering algorithm is proposed to divide the pixels of the DI into changed, unchanged and intermediate classes with a parallel clustering strategy. Image patches belonging to the first two classes are then constructed as pseudo-label training samples, and image patches of the intermediate class are treated as testing samples. Finally, a convolutional wavelet neural network (CWNN) is designed and trained to classify testing samples into changed or unchanged classes, coupled with a deep convolutional generative adversarial network (DCGAN) to increase the number of changed class within the pseudo-label training samples. Numerical experiments on four real SAR datasets demonstrate the validity and robustness of the proposed approach, achieving up to 99.61% accuracy for small area change detection.

AB - Small area change detection using synthetic aperture radar (SAR) imagery is a highly challenging task, due to speckle noise and imbalance between classes (changed and unchanged). In this paper, a robust unsupervised approach is proposed for small area change detection using deep learning techniques. First, a multi-scale superpixel reconstruction method is developed to generate a difference image (DI), which can suppress the speckle noise effectively and enhance edges by exploiting local, spatially homogeneous information. Second, a two-stage centre-constrained fuzzy c-means clustering algorithm is proposed to divide the pixels of the DI into changed, unchanged and intermediate classes with a parallel clustering strategy. Image patches belonging to the first two classes are then constructed as pseudo-label training samples, and image patches of the intermediate class are treated as testing samples. Finally, a convolutional wavelet neural network (CWNN) is designed and trained to classify testing samples into changed or unchanged classes, coupled with a deep convolutional generative adversarial network (DCGAN) to increase the number of changed class within the pseudo-label training samples. Numerical experiments on four real SAR datasets demonstrate the validity and robustness of the proposed approach, achieving up to 99.61% accuracy for small area change detection.

KW - Change detection

KW - Synthetic aperture radar

KW - Difference image

KW - Fuzzy c-means algorithm

KW - Deep learning

U2 - 10.1016/j.isprsjprs.2021.01.004

DO - 10.1016/j.isprsjprs.2021.01.004

M3 - Journal article

VL - 173

SP - 79

EP - 94

JO - ISPRS Journal of Photogrammetry and Remote Sensing

JF - ISPRS Journal of Photogrammetry and Remote Sensing

SN - 0924-2716

ER -