IDENTIFICATION OF MATERIALS USING AERIAL HYPERSPECTRAL IMAGES
Kati Laakso and
Acta Carolus Robertus, 2016, vol. 06, issue 1
The aerial hyperspectral imagery has a large information content and contains data not just only in the visible light spectra but in the near-infrared and the short-wave infrared spectra as well. Due to this, the technology is applicable to examine and detect preferences and conditions that visible identification is not possible or limited. During the last decade, hyperspectral imagery was successfully used for the analysis of vegetation, soil or minerals. During our research the AISA Fenix1K hyperspectral sensor of the Research Institute was used for data collection with the collaboration of experts from the Finnish sensor producer company near to Siófok. The collected aerial hyperspectral data and the ground spectral data as reference were compared and a spectral library of the examined materials was developed for future classifications. The ability to separate various materials was examined with statistical analyses with which we can determine the spectral separability of target objects. The analysis was fulfilled on the original and on transformed channels as well. According to the results we can conclude that the transformed channels are more applicable to separate these materials which was demonstrated on scatter plots too.
Keywords: hyperspectral; airborne remote sensing; target detection; ground truth acquisition; separability; Environmental Economics and Policy; Research Methods/ Statistical Methods; C89 (search for similar items in EconPapers)
References: View complete reference list from CitEc
Citations Track citations by RSS feed
Downloads: (external link)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:ags:hukruc:233819
Access Statistics for this article
More articles in Acta Carolus Robertus from Karoly Robert University College
Series data maintained by AgEcon Search ().