Open AccessScene Classification of Remotely Sensed Images via Densely Connected Convolutional Neural Networks and an Ensemble Classifier
Author(s) -
Qu Cheng,
Xu Yuan,
Peng Fu,
Jinling Li,
Wei Wang,
Yu Ren
Publication year - 2021
Publication title -
photogrammetric engineering and remote sensing
Language(s) - English
Resource type - Journals
eISSN - 2374-8079
pISSN - 0099-1112
DOI - 10.14358/pers.87.3.295
Subject(s) - convolutional neural network , artificial intelligence , computer science , classifier (uml) , pattern recognition (psychology) , contextual image classification , robustness (evolution) , feature extraction , remote sensing , computer vision , geography , image (mathematics) , biochemistry , chemistry , gene
Deep learning techniques, especially convolutional neural networks, have boosted performance in analyzing and understanding remotely sensed images to a great extent. However, existing scene-classification methods generally neglect local and spatial information that is vital to scene classification of remotely sensed images. In this study, a method of scene classification for remotely sensed images based on pretrained densely connected convolutional neural networks combined with an ensemble classifier is proposed to tackle the under-utilization of local and spatial information for image classification. Specifically, we first exploit the pretrained DenseNet and fine-tuned it to release its potential in remote-sensing image feature representation. Second, a spatial-pyramid structure and an improved Fisher-vector coding strategy are leveraged to further strengthen representation capability and the robustness of the feature map captured from convolutional layers. Then we integrate an ensemble classifier in our network architecture considering that lower attention to feature descriptors. Extensive experiments are conducted, and the proposed method achieves superior performance on UC Merced, AID, and NWPU-RESISC45 data sets.