Show simple item record

dc.contributor.authorMorales, Giorgio
dc.contributor.authorSheppard, John W.
dc.contributor.authorScherrer, Bryan
dc.contributor.authorShaw, Joseph A.
dc.identifier.citationMorales, Giorgio, John W. Sheppard, Bryan Scherrer, and Joseph A. Shaw. “Reduced-Cost Hyperspectral Convolutional Neural Networks.” Journal of Applied Remote Sensing 14, no. 03 (September 29, 2020). doi:10.1117/1.jrs.14.036519.en_US
dc.description.abstractHyperspectral imaging provides a useful tool for extracting complex information when visual spectral bands are not enough to solve certain tasks. However, processing hyperspectral images (HSIs) is usually computationally expensive due to the great amount of both spatial and spectral data they incorporate. We present a low-cost convolutional neural network designed for HSI classification. Its architecture consists of two parts: a series of densely connected three-dimensional (3-D) convolutions used as a feature extractor, and a series of two-dimensional (2-D) separable convolutions used as a spatial encoder. We show that this design involves fewer trainable parameters compared to other approaches, yet without detriment to its performance. What is more, we achieve comparable state-of-the-art results testing our architecture on four public remote sensing datasets: Indian Pines, Pavia University, Salinas, and EuroSAT; and a dataset of Kochia leaves [Bassia scoparia] with three different levels of herbicide resistance. The source code and datasets are available online.en_US
dc.rights© 2020 Society of Photo-Optical Instrumentation Engineers (SPIE)en_US
dc.titleReduced-cost hyperspectral convolutional neural networksen_US
mus.relation.collegeCollege of Engineeringen_US
mus.relation.departmentComputer Science.en_US
mus.relation.departmentElectrical & Computer Engineering.en_US
mus.relation.universityMontana State University - Bozemanen_US

Files in this item


This item appears in the following Collection(s)

Show simple item record

MSU uses DSpace software, copyright © 2002-2017  Duraspace. For library collections that are not accessible, we are committed to providing reasonable accommodations and timely access to users with disabilities. For assistance, please submit an accessibility request for library material.