Parametric Methods to Multispectral Image Classification using Normalized Difference Vegetation Index

Abstract

The key to proper governance of the municipal bodies lies in knowing the geography of the region. The land cover of the region changes with respect to time. Also, there are seasonal variation in the layout of the waterbodies. Manual verification and surveying of these things becomes very difficult for want of resources. Remote Sensing Images play a very important role in mapping the land cover. In this paper, we consider such remotely sensed Multispectral Images, taken from Landsat-8. Parametric Machine learning algorithm like Maximum Likelihood Classifier has been used on those images to classify the land cover. Normalized Difference Vegetation Index (NDVI) has been calculated and integrates with the classification process. Four basic land covers have been identified for the purpose namely Water, Vegetation, Built-up and Barren soil. The area of study is Bangalore urban region where we find that the water bodies are decreasing day by day. An overall efficiency of 82% with a kappa hat 0f 0.67 has been achieved with the method. The user and the producer accuracies have also been tabulated in the Results part. The results show the land cover changes in a temporal manner