Noise-Tolerant Unsupervised Classification for PolSAR Images Via Deep Clustering And Markov Random Field

Sihan Yang; Haixia Bi; Xiaotian Wang; Danfeng Hong

doi:10.1109/IGARSS52108.2023.10281880

Noise-Tolerant Unsupervised Classification for PolSAR Images Via Deep Clustering And Markov Random Field

Sihan Yang
, Haixia Bi
, Xiaotian Wang
, Danfeng Hong

Faculty of Electronic and Information Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

Due to the difficulty of obtaining manual annotations for polarimetric synthetic aperture radar (PolSAR) images, the problem of analyzing these images without or with few labels has become a current challenge. Considering the scarcity of labels, this paper proposes a noise-tolerant deep clustering-based PolSAR image classification that mainly uses autoencoders to learn discriminative features. In addition, in order to improve the performance and noise resistance of this method, we adopt Markov Random Field (MRF) to enhance the smoothness of class labels. We conducted experiments on a real benchmark PolSAR image, and the results show that our method achieves state-of-the-art PolSAR image classification results without any manual annotations.

Original language	English
Title of host publication	IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	5970-5973
Number of pages	4
ISBN (Electronic)	9798350320107
DOIs	https://doi.org/10.1109/IGARSS52108.2023.10281880
State	Published - 2023
Event	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 - Pasadena, United States Duration: 16 Jul 2023 → 21 Jul 2023

Publication series

Name	International Geoscience and Remote Sensing Symposium (IGARSS)
Volume	2023-July

Conference

Conference	2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023
Country/Territory	United States
City	Pasadena
Period	16/07/23 → 21/07/23

Keywords

Markov random field (MRF)
Unsupervised feature learning
autoencoder (AE)
polarimetric synthetic aperture radar (PolSAR) image classification

Access to Document

10.1109/IGARSS52108.2023.10281880

Cite this

Yang, S., Bi, H., Wang, X., & Hong, D. (2023). Noise-Tolerant Unsupervised Classification for PolSAR Images Via Deep Clustering And Markov Random Field. In IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings (pp. 5970-5973). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2023-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS52108.2023.10281880

Yang, Sihan ; Bi, Haixia ; Wang, Xiaotian et al. / Noise-Tolerant Unsupervised Classification for PolSAR Images Via Deep Clustering And Markov Random Field. IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 5970-5973 (International Geoscience and Remote Sensing Symposium (IGARSS)).

@inproceedings{344a965fd3da4ee5a89b8b6c471716c4,

title = "Noise-Tolerant Unsupervised Classification for PolSAR Images Via Deep Clustering And Markov Random Field",

abstract = "Due to the difficulty of obtaining manual annotations for polarimetric synthetic aperture radar (PolSAR) images, the problem of analyzing these images without or with few labels has become a current challenge. Considering the scarcity of labels, this paper proposes a noise-tolerant deep clustering-based PolSAR image classification that mainly uses autoencoders to learn discriminative features. In addition, in order to improve the performance and noise resistance of this method, we adopt Markov Random Field (MRF) to enhance the smoothness of class labels. We conducted experiments on a real benchmark PolSAR image, and the results show that our method achieves state-of-the-art PolSAR image classification results without any manual annotations.",

keywords = "Markov random field (MRF), Unsupervised feature learning, autoencoder (AE), polarimetric synthetic aperture radar (PolSAR) image classification",

author = "Sihan Yang and Haixia Bi and Xiaotian Wang and Danfeng Hong",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023 ; Conference date: 16-07-2023 Through 21-07-2023",

year = "2023",

doi = "10.1109/IGARSS52108.2023.10281880",

language = "英语",

series = "International Geoscience and Remote Sensing Symposium (IGARSS)",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "5970--5973",

booktitle = "IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings",

}

Yang, S, Bi, H, Wang, X & Hong, D 2023, Noise-Tolerant Unsupervised Classification for PolSAR Images Via Deep Clustering And Markov Random Field. in IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2023-July, Institute of Electrical and Electronics Engineers Inc., pp. 5970-5973, 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023, Pasadena, United States, 16/07/23. https://doi.org/10.1109/IGARSS52108.2023.10281880

Noise-Tolerant Unsupervised Classification for PolSAR Images Via Deep Clustering And Markov Random Field. / Yang, Sihan; Bi, Haixia; Wang, Xiaotian et al.
IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. p. 5970-5973 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2023-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Noise-Tolerant Unsupervised Classification for PolSAR Images Via Deep Clustering And Markov Random Field

AU - Yang, Sihan

AU - Bi, Haixia

AU - Wang, Xiaotian

AU - Hong, Danfeng

PY - 2023

Y1 - 2023

N2 - Due to the difficulty of obtaining manual annotations for polarimetric synthetic aperture radar (PolSAR) images, the problem of analyzing these images without or with few labels has become a current challenge. Considering the scarcity of labels, this paper proposes a noise-tolerant deep clustering-based PolSAR image classification that mainly uses autoencoders to learn discriminative features. In addition, in order to improve the performance and noise resistance of this method, we adopt Markov Random Field (MRF) to enhance the smoothness of class labels. We conducted experiments on a real benchmark PolSAR image, and the results show that our method achieves state-of-the-art PolSAR image classification results without any manual annotations.

AB - Due to the difficulty of obtaining manual annotations for polarimetric synthetic aperture radar (PolSAR) images, the problem of analyzing these images without or with few labels has become a current challenge. Considering the scarcity of labels, this paper proposes a noise-tolerant deep clustering-based PolSAR image classification that mainly uses autoencoders to learn discriminative features. In addition, in order to improve the performance and noise resistance of this method, we adopt Markov Random Field (MRF) to enhance the smoothness of class labels. We conducted experiments on a real benchmark PolSAR image, and the results show that our method achieves state-of-the-art PolSAR image classification results without any manual annotations.

KW - Markov random field (MRF)

KW - Unsupervised feature learning

KW - autoencoder (AE)

KW - polarimetric synthetic aperture radar (PolSAR) image classification

UR - https://www.scopus.com/pages/publications/85178344796

U2 - 10.1109/IGARSS52108.2023.10281880

DO - 10.1109/IGARSS52108.2023.10281880

M3 - 会议稿件

AN - SCOPUS:85178344796

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 5970

EP - 5973

BT - IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2023

Y2 - 16 July 2023 through 21 July 2023

ER -

Yang S, Bi H, Wang X, Hong D. Noise-Tolerant Unsupervised Classification for PolSAR Images Via Deep Clustering And Markov Random Field. In IGARSS 2023 - 2023 IEEE International Geoscience and Remote Sensing Symposium, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. p. 5970-5973. (International Geoscience and Remote Sensing Symposium (IGARSS)). doi: 10.1109/IGARSS52108.2023.10281880

Noise-Tolerant Unsupervised Classification for PolSAR Images Via Deep Clustering And Markov Random Field

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this