Spectral mixture analysis for subpixel classification of coconut

Simple item page
dc.contributor.authorPalaniswami, C.
dc.contributor.authorUpadhyay, A.K.
dc.contributor.authorMaheswarappa, H.P.
dc.date.accessioned2014-08-05T08:38:26Z
dc.date.available2014-08-05T08:38:26Z
dc.date.issued2006-12
dc.description.abstractThe present study was undertaken to test the stability of a spectral mixture modelling method by applying the model to produce land-cover maps of coconut in Kasaragod district, Kerala. Classification results from applying the Spectral Mixture Analysis (SMA) were assessed by comparison with ground-truth data. SMA was performed and evaluated based on Landsat-7 ETM+ (Enhanced Thematic Mapper Plus) data. Landsat- 7 ETM+ was available at 30 m resolution with six spectral bands (excluding the panchromatic band and thermal band). The Landsat-7 ETM+ scene used in this study was acquired on 8 August 2000 from path 135, row 21. The scene was a level-2 product and was radiometrically and geometrically corrected (systematic) and resampled to give 25 m resolution. The commercial image processing software, IDRISI32 was used here for data visualization. The procedure used in this study was based on a linear mixture model to derive continuous fields of coconut, road, laterite outcrops, construction, arecanut and cloud. SMA was done on DN values and corresponding radiance values of the satellite imagery. The accuracy of endmember fraction was estimated as the mean of the percentage absolute difference between actual and modelled estimates. The subpixel accuracy achieved for the coconut land-cover was 87% using SMA of DN values, while it was 93% for SMA of radiance values.en_US
dc.identifier.citationCurrent Science, Vol. 91, No. 12, 25 December 2006 P.1706-1711en_US
dc.identifier.urihttp://hdl.handle.net/123456789/4586
dc.language.isoenen_US
dc.subjectCoconuten_US
dc.subjectremote sensingen_US
dc.subjectspectral mixtureen_US
dc.subjectsubpixel classificationen_US
dc.titleSpectral mixture analysis for subpixel classification of coconuten_US
dc.typeArticleen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Spectral mixture analysis for subpixel classification of coconut.pdf
Size:
717.71 KB
Format:
Adobe Portable Document Format
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

Publications