Hyperspectral Image Classification for Agricultural Applications

Abstract

The purpose of Hyperspectral image (HSI) classification is for analyzing the remotely sensed images. The need of Convolutional neural network (CNN) is that it is the most frequently worn deep learning method to process the visual data. CNN is required for HSI classification which is also seen in new projects. The 2D CNN mechanisms are widely used. Here, we have proposed a 2-D CNN model along with Support Vector Machine (SVM) and Random Forest classifies for HSI classification. To test the performance of this approach, experiments are performed over Indian Pines, University of Pavia, and Salinas Scene along with WHU-Hi-LongKou, WHU-Hi-HanChuan, and WHU-Hi-HongHu remote sensing data sets. These datasets are used for crop images classification.