6533b870fe1ef96bd12cf1fa
RESEARCH PRODUCT
PRACTICAL APPROACH FOR HYPERSPECTRAL IMAGE PROCESSING IN PYTHON
Ilkka PölönenJyri HamalainenMatti A. EskelinenLeevi AnnalaAamos Riihinensubject
lcsh:Applied optics. Photonicsmedicine.medical_specialtySoftware_GENERALhyperspectral imagingComputer sciencedata analysis0208 environmental biotechnologyImage processing02 engineering and technologykuvankäsittelylcsh:Technologyopen sourceavoin lähdekoodimedicinecomputer.programming_languagelcsh:Tbusiness.industrylcsh:TA1501-1820Hyperspectral imagingPython (programming language)Hyperspectral image processing020801 environmental engineeringSpectral imagingpythonkoneoppiminenlcsh:TA1-2040lcsh:Engineering (General). Civil engineering (General)businessSoftware engineeringcomputerAgile software developmentdescription
Abstract. Python is a very popular programming language among data scientists around the world. Python can also be used in hyperspectral data analysis. There are some toolboxes designed for spectral imaging, such as Spectral Python and HyperSpy, but there is a need for analysis pipeline, which is easy to use and agile for different solutions. We propose a Python pipeline which is built on packages xarray, Holoviews and scikit-learn. We have developed some of own tools, MaskAccessor, VisualisorAccessor and a spectral index library. They also fulfill our goal of easy and agile data processing. In this paper we will present our processing pipeline and demonstrate it in practice.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2018-04-30 | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |