cogcom 18: e4

Research Article

Comparative Analysis of Scene Classification Methods for Remotely Sensed Images using Various Convolutional Neural Network

Download106 downloads
  • @ARTICLE{10.4108/eai.11-2-2021.168714,
        author={P. Deepan and L.R. Sudha},
        title={Comparative  Analysis  of  Scene  Classification  Methods  for Remotely Sensed Images using Various Convolutional Neural Network},
        journal={EAI Endorsed Transactions on Cognitive Communications: Online First},
        volume={},
        number={},
        publisher={EAI},
        journal_a={COGCOM},
        year={2021},
        month={2},
        keywords={Remote sensing images, scene classification, dilated convolutional, convolutional layer and feature fusion},
        doi={10.4108/eai.11-2-2021.168714}
    }
    
  • P. Deepan
    L.R. Sudha
    Year: 2021
    Comparative Analysis of Scene Classification Methods for Remotely Sensed Images using Various Convolutional Neural Network
    COGCOM
    EAI
    DOI: 10.4108/eai.11-2-2021.168714
P. Deepan1,*, L.R. Sudha2
  • 1: Research Scholar, Department of Computer Science and Engineering, Annamalai University, Chidambaram, Tamil nadu
  • 2: Associate Professor, Department of Computer Science and Engineering, Annamalai University, Chidambaram, Tamil nadu
*Contact email: deepanp87@gmail.com

Abstract

Remote sensing image (RSI) scene classification has received growing attention from the research community in recent days. Over the past few decades, with the rapid development of deep learning models particularly Convolutional Neural Network (CNN), the performance of RSI scene classifications has been drastically improved due to the hierarchical feature representation learning through traditional CNN. But, we found that these models suffer from characterizing complex patterns in remote sensing imagery because of small inter class variations and large intra class variations. In order to tackle these problems, we have finetuned and proposed three different CNN models namely, Dilated CNN (D-CNN), RSI Scene Classification model (RSISC-16 Net) and fused the features of CNN and RSISC-16Net to improve the performance of RSI scene classification. The aim of proposed CNN models is to incorporate more relevant information by increasing the receptive field of convolutional layer. In addition, we have performed feature fusion of two CNN models and finetuned by varying hyper parameters such as activation function, dropout probability and batch size to reduce over fitting problem and to improve the performance of our proposed work. For evaluating the proposed approach, we have collected 7,000 remote sensing images from NWPU 45-class dataset and the experiments are carried out using different CNN models and results. The obtained accuracy is 89.85%, 94.7% and 96.5% respectively.