CBANet: An End-to-End Cross-Band 2-D Attention Network for Hyperspectral Change Detection in Remote Sensing

doi:10.1109/tgrs.2023.3276589

CIOMP OpenIR

	CBANet: An End-to-End Cross-Band 2-D Attention Network for Hyperspectral Change Detection in Remote Sensing
	Y. H. Li; J. C. Ren; Y. J. Yan; Q. Y. Liu; P. Ma; A. Petrovski and H. J. Sun
	2023
发表期刊	Ieee Transactions on Geoscience and Remote Sensing
ISSN	0196-2892
卷号	61 页码:11
摘要	As a fundamental task in remote sensing (RS) observation of the earth, change detection (CD) using hyperspectral images (HSI) features high accuracy due to the combination of the rich spectral and spatial information, especially for identifying land-cover variations in bi-temporal HSIs. Relying on the image difference, existing HSI CD methods fail to preserve the spectral characteristics and suffer from high data dimensionality, making them extremely challenging to deal with changing areas of various sizes. To tackle these challenges, we propose a cross-band 2-D self-attention network (CBANet) for end-to-end HSI CD. By embedding a cross-band feature extraction module into a 2-D spatial-spectral self-attention module, CBANet is highly capable of extracting the spectral difference of matching pixels by considering the correlation between adjacent pixels. The CBANet has shown three key advantages: 1) less parameters and high efficiency; 2) high efficacy of extracting representative spectral information from bi-temporal images; and 3) high stability and accuracy for identifying both sparse sporadic changing pixels and large changing areas whilst preserving the edges. Comprehensive experiments on three publicly available datasets have fully validated the efficacy and efficiency of the proposed methodology.
DOI	10.1109/tgrs.2023.3276589
URL	查看原文
收录类别	sci ; ei
语种	英语
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/67660
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	Y. H. Li,J. C. Ren,Y. J. Yan,et al. CBANet: An End-to-End Cross-Band 2-D Attention Network for Hyperspectral Change Detection in Remote Sensing[J]. Ieee Transactions on Geoscience and Remote Sensing,2023,61:11.
APA	Y. H. Li,J. C. Ren,Y. J. Yan,Q. Y. Liu,P. Ma,&A. Petrovski and H. J. Sun.(2023).CBANet: An End-to-End Cross-Band 2-D Attention Network for Hyperspectral Change Detection in Remote Sensing.Ieee Transactions on Geoscience and Remote Sensing,61,11.
MLA	Y. H. Li,et al."CBANet: An End-to-End Cross-Band 2-D Attention Network for Hyperspectral Change Detection in Remote Sensing".Ieee Transactions on Geoscience and Remote Sensing 61(2023):11.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
CBANet An End-to-End（2224KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载