Domain Knowledge-Guided Self-Supervised Change Detection for Remote Sensing Images | IEEE Journals & Magazine | IEEE Xplore

Domain Knowledge-Guided Self-Supervised Change Detection for Remote Sensing Images


Abstract:

As one of the most popular topics in the field of Earth observation using remote sensing images, change detection (CD) provides great practical and valuable significance ...Show More

Abstract:

As one of the most popular topics in the field of Earth observation using remote sensing images, change detection (CD) provides great practical and valuable significance for many fields. Although the majority of supervised methods have made great progress by introducing deep learning in the CD field, they are still limited by manually labeled data. In comparison, unsupervised methods do not require manually labeled data, but the accuracy of CD is difficult to be improved due to the lack of constraints or guidance during training. To tackle these issues, we propose a novel domain knowledge-guided self-supervised learning approach for unsupervised CD by fusing the domain knowledge of remote sensing indices during training and inference. Furthermore, we calculate cosine similarity to select the high-similarity feature vectors outputted by the mean teacher and student networks to implement the hard negative sampling strategy, which effectively improves the CD performance. Compared with other supervised and unsupervised CD methods, our proposed approach achieves state-of-the-art performance with a Kap of 53.34% and an F1 of 55.69% on the Onera Satellite Change Detection dataset. Fusing domain knowledge to guide model training and inference obtains an improvement of 5.83% in Kap and 5.13% in F1, which further narrows the performance gap between unsupervised and supervised CD.
Page(s): 4167 - 4179
Date of Publication: 27 April 2023

ISSN Information:

Funding Agency:

Author image of Li Yan
School of Geodesy and Geomatics, Wuhan University, Wuhan, China
Li Yan (Member, IEEE) received the B.S., M.S., and Ph.D. degrees in photogrammetry and remote sensing from the Wuhan University, Wuhan, China, in 1989, 1992, and 1999, respectively.
He is currently a Luojia Distinguished Professor with the School of Geodesy and Geomatics, Wuhan University. His research interests include photogrammetry, remote sensing, and precise image measurement.
Li Yan (Member, IEEE) received the B.S., M.S., and Ph.D. degrees in photogrammetry and remote sensing from the Wuhan University, Wuhan, China, in 1989, 1992, and 1999, respectively.
He is currently a Luojia Distinguished Professor with the School of Geodesy and Geomatics, Wuhan University. His research interests include photogrammetry, remote sensing, and precise image measurement.View more
Author image of Jianbing Yang
School of Geodesy and Geomatics, Wuhan University, Wuhan, China
Jianbing Yang received the B.S. degree in surveying and mapping engineering from the East China University of Technology, Nanchang, China, in 2017, and the M.S. degree in geodesy and survey engineering from the Institute of Seismology, China Earthquake Administration, Wuhan, China, in 2020. He is currently working toward the Ph.D. degree in photogrammetry and remote sensing with the School of Geodesy and Geomatics, Wuhan ...Show More
Jianbing Yang received the B.S. degree in surveying and mapping engineering from the East China University of Technology, Nanchang, China, in 2017, and the M.S. degree in geodesy and survey engineering from the Institute of Seismology, China Earthquake Administration, Wuhan, China, in 2020. He is currently working toward the Ph.D. degree in photogrammetry and remote sensing with the School of Geodesy and Geomatics, Wuhan ...View more
Author image of Jian Wang
School of Geodesy and Geomatics, Wuhan University, Wuhan, China
Jian Wang (Student Member, IEEE) received the M.S. degree in surveying and mapping engineering from the China University of Mining and Technology Beijing, Beijing, China, in 2021. He is currently working toward the Ph.D. degree in photogrammetry and remote sensing with the Wuhan University, Wuhan, China.
His research interests include processing and object recognition in remote sensing images, deep learning, and interferom...Show More
Jian Wang (Student Member, IEEE) received the M.S. degree in surveying and mapping engineering from the China University of Mining and Technology Beijing, Beijing, China, in 2021. He is currently working toward the Ph.D. degree in photogrammetry and remote sensing with the Wuhan University, Wuhan, China.
His research interests include processing and object recognition in remote sensing images, deep learning, and interferom...View more

Author image of Li Yan
School of Geodesy and Geomatics, Wuhan University, Wuhan, China
Li Yan (Member, IEEE) received the B.S., M.S., and Ph.D. degrees in photogrammetry and remote sensing from the Wuhan University, Wuhan, China, in 1989, 1992, and 1999, respectively.
He is currently a Luojia Distinguished Professor with the School of Geodesy and Geomatics, Wuhan University. His research interests include photogrammetry, remote sensing, and precise image measurement.
Li Yan (Member, IEEE) received the B.S., M.S., and Ph.D. degrees in photogrammetry and remote sensing from the Wuhan University, Wuhan, China, in 1989, 1992, and 1999, respectively.
He is currently a Luojia Distinguished Professor with the School of Geodesy and Geomatics, Wuhan University. His research interests include photogrammetry, remote sensing, and precise image measurement.View more
Author image of Jianbing Yang
School of Geodesy and Geomatics, Wuhan University, Wuhan, China
Jianbing Yang received the B.S. degree in surveying and mapping engineering from the East China University of Technology, Nanchang, China, in 2017, and the M.S. degree in geodesy and survey engineering from the Institute of Seismology, China Earthquake Administration, Wuhan, China, in 2020. He is currently working toward the Ph.D. degree in photogrammetry and remote sensing with the School of Geodesy and Geomatics, Wuhan University, Wuhan.
His research interests include radiometric correction, deep learning, change detection, and instance segmentation.
Jianbing Yang received the B.S. degree in surveying and mapping engineering from the East China University of Technology, Nanchang, China, in 2017, and the M.S. degree in geodesy and survey engineering from the Institute of Seismology, China Earthquake Administration, Wuhan, China, in 2020. He is currently working toward the Ph.D. degree in photogrammetry and remote sensing with the School of Geodesy and Geomatics, Wuhan University, Wuhan.
His research interests include radiometric correction, deep learning, change detection, and instance segmentation.View more
Author image of Jian Wang
School of Geodesy and Geomatics, Wuhan University, Wuhan, China
Jian Wang (Student Member, IEEE) received the M.S. degree in surveying and mapping engineering from the China University of Mining and Technology Beijing, Beijing, China, in 2021. He is currently working toward the Ph.D. degree in photogrammetry and remote sensing with the Wuhan University, Wuhan, China.
His research interests include processing and object recognition in remote sensing images, deep learning, and interferometric synthetic aperture radar.
Jian Wang (Student Member, IEEE) received the M.S. degree in surveying and mapping engineering from the China University of Mining and Technology Beijing, Beijing, China, in 2021. He is currently working toward the Ph.D. degree in photogrammetry and remote sensing with the Wuhan University, Wuhan, China.
His research interests include processing and object recognition in remote sensing images, deep learning, and interferometric synthetic aperture radar.View more

References

References is not available for this document.