2013
DOI: 10.1109/jstars.2013.2255981
|View full text |Cite
|
Sign up to set email alerts
|

Statistical Classification for Assessing PRISMA Hyperspectral Potential for Agricultural Land Use

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

1
14
0

Year Published

2013
2013
2024
2024

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 30 publications
(15 citation statements)
references
References 26 publications
1
14
0
Order By: Relevance
“…Moreover, the selection of the best Hyperspectral Narrow-Bands (HNBs) allows one to get rid of the Hughes phenomenon in the context of supervised classification using hyperspectral data. For example, Amato et al [57] obtained close performances with a limited number of spectral bands, mainly spread on the VNIR PRISMA spectrum in order to classify agricultural land use. However, some studies have also demonstrated that SVC can overcome this phenomenon [58,59].…”
Section: Preliminary Analysis Of the Literature Databasementioning
confidence: 99%
“…Moreover, the selection of the best Hyperspectral Narrow-Bands (HNBs) allows one to get rid of the Hughes phenomenon in the context of supervised classification using hyperspectral data. For example, Amato et al [57] obtained close performances with a limited number of spectral bands, mainly spread on the VNIR PRISMA spectrum in order to classify agricultural land use. However, some studies have also demonstrated that SVC can overcome this phenomenon [58,59].…”
Section: Preliminary Analysis Of the Literature Databasementioning
confidence: 99%
“…Unfortunately, we did not have a land-use classification map for two dates, and therefore could not calibrate the model at one date and compare the forecast land-use pattern with the observed land use at the other date. To generate a land-use map, we performed a discriminant function-based land-use classification, an approach common in remote sensing disciplines [44][45][46]. LANDSAT reflectance bands for 2010 [47] were used to calibrate discriminant functions for each land-use type from a known land-use map for 2008.…”
Section: Validationmentioning
confidence: 99%
“…One study, of two different regions in Italy, analyzed Multispectral Visible and Infrared Imaging Spectrometer (MIVIS) imagery [62]. For the Tessera region near Venice, researchers differentiated several types of cultivated vegetationsoybeans, corn, sugar beets, alfalfa, wheat stubble, along with mixed woods, water, and urban.…”
Section: Hyperspectral Imagerymentioning
confidence: 99%