A COMPARATIVE STUDY OF CONVOLUTIONAL NEURAL NETWORKS FOR SEGMENTATION AND CLASSIFICATION OF REMOTE SENSING IMAGES

Abstract

Geographical satellite images that are used for the analysis of environmental and geographical plains are obtained through remote sensing techniques. The raw images collected from the satellites are not well suited for statistical analysis and accurate report preparation. So, the raw images undergo the usual image processing procedure such as preprocessing, segmentation, feature extraction and classification. Traditional image classification techniques have several spatial and spectral resolution issues. A novel image classification technique, namely, Convolutional Neural Networks (CNN) technique is an emerging research criterion. It is an extension of neural networks and deep learning approaches. In this paper, several CNN based image classification techniques are analyzed and their performance is compared. The techniques involved in this analysis include Full Convolutional Network (FCN), Patch-based classification, pixel-to-pixel based segmentation and convnet-based feature extraction. Each technique utilized different datasets for its own performance evaluation. Finally, the performance evaluations are analyzed in terms of accuracy.