5. Conclusions |
This paper evaluates Spectral Angle Mapper (SAM) and Maximum likelihood classifier (MLC) algorithms for classifying two different products of the MODIS data (MOD 09 surface reflectance and MOD 02 Level-1B Calibrated Geolocation Data Set). Accuracy assessment was done using ground truth obtained from field, at a administrative boundary level and was also compared with the high resolution LISS-3 classified map on a pixel by pixel basis. The results obtained from accuracy assessment showed that MLC on MODIS 7 bands was good for land cover mapping at regional scale followed by SAM on the same 7 bands.
We thank the Ministry of Science and Technology,Government of India and Indian Institute of Science for the Financial assistance and infrastructure support.
