Abstract

Several statistical separability measures have been analysed to determine the best subset of bands from six bands (excluding thermal IR) of Landsat Thematic Mapper data to obtain the best combination for discrimination between oilseed crop, orchards, scrubs, acacia and forests. The effects of the addition of the middle-infrared band to the visible and near-infrared bands have also been studied. The inclusion of the middle-infrared bands has led to considerable improvement in crop classification. Band combinations 2-3-4-5 and 1-2-4-5 are found to be the best four band combinations and 3-4-5 and 1-4-5 are found to be the best band triplets for crop discrimination.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call