Fusion of Deep Learning Models for Improving Classification Accuracy of Remote Sensing Images

Over the recent years we have witnessed an increasing number of applications using deep learning techniques such as Convolutional Neural networks (CNNs), Recurrent Neural Networks (RNN) and Deep Neural Networks (DNN) for remote sensing image classification. But, we found that these models suffer for characterizing complex patterns in remote sensing imagery because of small inter class variations and large intra class variations. The intent of this paper is to study the effect of ensemble classifier constructed by combining three Deep Convolutional Neural Networks (DCNN) namely; CNN, VGG-16 and Res Inception models by using average feature fusion techniques. The proposed approach is validated with 7,000 remote sensing images from Northern Western Polytechnical University - Remote Sensing Image Scene Classification (NWPU- RESISC) 45 class dataset and confirmed as an effective technique to improve the robustness over a single deep learning model.