Title :
Image classification and performance evaluation of IRS 1C LISS-III data
Author :
Muralikrishna, I.V.
Author_Institution :
Center for Remote Sensing, JNT, Hyderabad
Abstract :
LISS-III onboard IRS 1C is very much suitable for land cover mapping. LISS-III provides improved spatial resolution compared to Landsat TM. The study aims at improvement of classification accuracy and as such a performance evaluation of IRS 1C LISS-III bands is taken up. A level II classification scheme with 12 classes has been adopted to classify data. The LISS 1, 2 and 3 combinations provided overall classification accuracy of 93 percent because of higher spatial resolution. The inclusion of an SWIR band in classification improved classification of vegetation classes but decreased overall accuracy to 76 percent
Keywords :
geophysical signal processing; geophysical techniques; image classification; remote sensing; IR imaging; IRS 1C LISS III; Indian Remote Sensing satellite; accuracy; geophysical measurement technique; image classification; improved spatial resolution; land cover; land surface; multispectral remote sensing; optical imaging; performance; terrain mapping; vegetation mapping; Crops; Image classification; Infrared sensors; Remote monitoring; Remote sensing; Satellites; Software packages; Spatial resolution; Thermal sensors; Vegetation mapping;
Conference_Titel :
Geoscience and Remote Sensing, 1997. IGARSS '97. Remote Sensing - A Scientific Vision for Sustainable Development., 1997 IEEE International
Print_ISBN :
0-7803-3836-7
DOI :
10.1109/IGARSS.1997.609065
