NDVI Versus CNN Features in Deep Learning for Land Cover Clasification of Aerial Images

Agriculture plays a strategic role in the economic development of a country. Appropriate classification of land cover images is vital for planning the right agricultural practices and maintaining sustainable environment. This paper provides methods and analysis for land cover classification of remote sensing images. Satellite images form the input while mapping of every image to a distinct class is obtained as output. The objective is to compare the hand-crafted features based on Normalized Difference Vegetation Index (NDVI) and feature learning from Convolutional Neural Networks (CNN). The rationale of this work is to take advantage of techniques that are illumination invariant. NDVI versus CNN features have been compared on a linear Support Vector Machine (SVM). However, no comparative study has been carried out related to DVI based features and CNN based features on a deep learning classifier. This paper compares the performance of different classifiers and evaluates them based on test accuracy.