Abstract
Band selection (BS) is a foundational problem for the analysis of high-dimensional hyperspectral image (HSI) cubes. Recent developments in the visual attention mechanism allow for specifically modeling the complex relationship among different components. Inspired by this, this article proposes a novel band selection network, termed as nonlocal band attention network (NBAN), based on using a nonlocal band attention reconstruction network to adaptively calculate band weights. The framework consists of a band attention module, which aims to extract the long-range attention and reweight the original spectral bands, and a reconstruction network which is used to restore the reweighted data, resulting in a flexible architecture. The resulting BS network is able to capture the nonlinear and the long-range dependencies between spectral bands, making it more effective and robust to select the informative bands automatically. Finally, we compare the result of NBAN with six popular existing band selection methods on three hyperspectral datasets, the result showing that the long-range relationship is helpful for band selection processing. Besides, the classification performance shows that the advantage of NBAN is particularly obvious when the size of the selected band subset is small. Extensive experiments strongly evidence that the proposed NBAN method outperforms many current models on three popular HSI images consistently.
Highlights
H YPERSPECTRAL images (HSIs) have been widely applied in various fields, such as agriculture [1], [2], land management [3], medical imaging [4], [5], and forensics [6]
We develop a band selection network framework that considers the global relationship of all bands called nonlocal band attention network (NBAN)
1) By assuming a long-range relationship exists between the spectral bands, we propose a novel method for HSI band selection called NBAN
Summary
H YPERSPECTRAL images (HSIs) have been widely applied in various fields, such as agriculture [1], [2], land management [3], medical imaging [4], [5], and forensics [6]. Hundreds of bands in hyperspectral images contain rich spectral and spatial information and bring a great challenge for hyperspectral data processing. Due to the imaging characteristics of HSIs, there is a high correlation between adjacent. Manuscript received January 6, 2021; revised February 4, 2021; accepted March 7, 2021. Date of publication March 12, 2021; date of current version April 5, 2021. The high dimensional and redundant HSIs data will result in huge expenditure and extravagant computing resources. It often suffers from the so-called curse of dimensionality [8], [9], which will impair the classification ability of classifiers
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
