Abstract
Hyperspectral (HS) sensors sample reflectance spectrum in very high resolution, which allows us to examine material properties in very fine details. However, their widespread adoption has been hindered because they are very expensive. Reflectance spectra of real materials are high dimensional but sparse signals. By utilizing prior information about the statistics of real HS spectra, many previous studies have reconstructed HS spectra from multispectral (MS) signals (which can be obtained from cheaper, lower spectral resolution sensors). However, most of these techniques assume that the MS bands are known apriori and do not optimize the MS bands to produce more accurate reconstructions. In this paper, we propose a new end-to-end fully convolutional residual neural network architecture that simultaneously learns both the MS bands and the transformation to reconstruct HS spectra from MS signals by analyzing large quantity of HS data. The learned band can be implemented in hardware to obtain an MS sensor that collects data that is best to reconstruct HS spectra using the learned transformation. Using a diverse set of real-world datasets, we show how the proposed approach of optimizing MS bands along with the transformation can drastically increase the reconstruction accuracy. Additionally, we also investigate the prospects of using reconstructed HS spectra for land cover classification.
Highlights
IntroductionThe reconstruction of hyperspectral (HS) spectrum from multispectral (MS) signal is an ill-posed problem
The reconstruction of hyperspectral (HS) spectrum from multispectral (MS) signal is an ill-posed problem. This is because MS bands are broader and fewer in number, so they do not capture fine details in reflectance spectra that are captured by HS bands
The results of the experiments showed that optimizing MS bands along with the transformation from MS signal to HS spectrum can greatly improve the reconstruction accuracy compared to only optimizing the transformation for fixed MS bands
Summary
The reconstruction of hyperspectral (HS) spectrum from multispectral (MS) signal is an ill-posed problem. This is because MS bands are broader and fewer in number, so they do not capture fine details in reflectance spectra that are captured by HS bands. Past studies have successfully utilised machine learning techniques, such as, sparse dictionary learning [1] and deep learning [2], for this purpose. They have only concentrated on learning the transformation from MS signal to HS spectrum for fixed MS bands. Our method is based on a novel end-to-end fully convolutional residual neural network architecture that utilizes a new band re-sampling layer and a new loss layer
Published Version (Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
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.