Classification for High Resolution Remote Sensing Imagery Using a Fully Convolutional Network

As a variant of Convolutional Neural Networks (CNNs) in Deep Learning, the Fully Convolutional Network (FCN) model achieved state-of-the-art performance for natural image semantic segmentation. In this paper, an accurate classification approach for high resolution remote sensing imagery based on the...

Full description

Saved in:
Bibliographic Details
Published in:Remote sensing (Basel, Switzerland) Switzerland), 2017-05, Vol.9 (5), p.498
Main Authors: Fu, Gang, Liu, Changjun, Zhou, Rong, Sun, Tao, Zhang, Qijian
Format: Article
Language:English
Subjects:
Aversion learning
Classification
Coefficients
Color
Color imagery
Computer architecture
Conditional random fields
Convolution
Detection
High resolution
Image classification
Image processing
Image resolution
Image segmentation
Learning
Neural networks
Object oriented programming
Post-production processing
Recall
Remote sensing
Serial learning
State of the art
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As a variant of Convolutional Neural Networks (CNNs) in Deep Learning, the Fully Convolutional Network (FCN) model achieved state-of-the-art performance for natural image semantic segmentation. In this paper, an accurate classification approach for high resolution remote sensing imagery based on the improved FCN model is proposed. Firstly, we improve the density of output class maps by introducing Atrous convolution, and secondly, we design a multi-scale network architecture by adding a skip-layer structure to make it capable for multi-resolution image classification. Finally, we further refine the output class map using Conditional Random Fields (CRFs) post-processing. Our classification model is trained on 70 GF-2 true color images, and tested on the other 4 GF-2 images and 3 IKONOS true color images. We also employ object-oriented classification, patch-based CNN classification, and the FCN-8s approach on the same images for comparison. The experiments show that compared with the existing approaches, our approach has an obvious improvement in accuracy. The average precision, recall, and Kappa coefficient of our approach are 0.81, 0.78, and 0.83, respectively. The experiments also prove that our approach has strong applicability for multi-resolution image classification.
ISSN:2072-4292
2072-4292
DOI:10.3390/rs9050498