Interactive Siamese spatial-Spectral cross-layer fusion transformer for hyperspectral image change detection

被引:0
作者
Li, Chenming [1 ]
Feng, Xingyu [1 ]
Zhang, Yiyan [1 ]
Gao, Hongmin [1 ]
Chen, Zhonghao [1 ]
Xu, Shufang [1 ]
机构
[1] Hohai Univ, Coll Informat Sci & Engn, Nanjing 211100, Peoples R China
基金
中国国家自然科学基金; 中国博士后科学基金;
关键词
Hyper Spectral Image (HSI); Change Detection (CD); transformer; siamese network; cross-layer Adaptive Fuse (CAF);
D O I
10.1080/01431161.2024.2379516
中图分类号
TP7 [遥感技术];
学科分类号
081102 ; 0816 ; 081602 ; 083002 ; 1404 ;
摘要
Recently, methods based on Transformer have been widely used in the research field of hyperspectral image (HSI) change detection (CD). However, existing transformer-based CD research does not sufficiently utilize the spatial-spectral features of HSIs. In this article, we propose an interactive Siamese spatial-spectral cross-layer fusion Transformer (IS2CF-Former) network to improve the accuracy of HSI-CD. The proposed Siamese interactive module integrates the Siamese network with the Transformer structure, enhancing communication between bi-temporal images. We have made improvements to the cross-layer adaptive fusion (CAF) Transformer, where the cross-layer fusion module enhances the interaction between layers and the ability to capture local contextual features, concurrently reducing the model's parameter count to mitigate the risk of overfitting. The CAF Transformer is applied to extract spatial and spectral features. Evaluating the detection performance of the proposed model on three bi-temporal HSIs through extensive experiments demonstrates superior accuracy compared to seven excellent CD methods.
引用
收藏
页码:5737 / 5760
页数:24
相关论文
共 57 条
[1]   Lidar System Architectures and Circuits [J].
Behroozpour, Behnam ;
Sandborn, Phillip A. M. ;
Wu, Ming C. ;
Boser, Bernhard E. .
IEEE COMMUNICATIONS MAGAZINE, 2017, 55 (10) :135-142
[2]   A novel approach to unsupervised change detection based on a semisupervised SVM and a similarity measure [J].
Bovolo, Francesca ;
Bruzzone, Lorenzo ;
Marconcini, Mattia .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2008, 46 (07) :2070-2082
[3]   Military applications of hyperspectral imagery [J].
Briottet, X. ;
Boucher, Y. ;
Dimmeler, A. ;
Malaplate, A. ;
Cini, A. ;
Diani, M. ;
Bekman, H. ;
Schwering, P. ;
Skauli, T. ;
Kasen, I. ;
Renhorn, I. ;
Klasen, L. ;
Gilmore, M. ;
Oxford, D. .
Targets and Backgrounds XII: Characterization and Representation, 2006, 6239 :B2390-B2390
[4]   An automatic bridge detection technique for multispectral images [J].
Chaudhuri, D. ;
Samal, Ashok .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2008, 46 (09) :2720-2727
[5]   Hyperspectral Image Classification Based on Global Spectral Projection and Space Aggregation [J].
Chen, Dong ;
Zhang, Junping ;
Guo, Qingle ;
Wang, Linlin .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2023, 20
[6]   TEMDnet: A Novel Deep Denoising Network for Transient Electromagnetic Signal With Signal-to-Image Transformation [J].
Chen, Kecheng ;
Pu, Xiaorong ;
Ren, Yazhou ;
Qiu, Hang ;
Lin, Fanqiang ;
Zhang, Saimin .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[7]   Temporal difference-guided network for hyperspectral image change detection [J].
Chen, Zhonghao ;
Wang, Yuyang ;
Gao, Hongmin ;
Ding, Yao ;
Zhong, Qiqiang ;
Hong, Danfeng ;
Zhang, Bing .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2023, 44 (19) :6033-6059
[8]   Global to Local: A Hierarchical Detection Algorithm for Hyperspectral Image Target Detection [J].
Chen, Zhonghao ;
Lu, Zhengtao ;
Gao, Hongmin ;
Zhang, Yiyan ;
Zhao, Jia ;
Hong, Danfeng ;
Zhang, Bing .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
[9]   Learning a similarity metric discriminatively, with application to face verification [J].
Chopra, S ;
Hadsell, R ;
LeCun, Y .
2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :539-546
[10]  
Coppin P., 2002, Analysis of Multi-Temporal Remote Sensing Images, V25, P3, DOI DOI 10.1142/9789812777249_0001