Next Article in Journal
Landslide Monitoring Using Multi-Temporal SAR Interferometry with Advanced Persistent Scatterers Identification Methods and Super High-Spatial Resolution TerraSAR-X Images
Next Article in Special Issue
Automatic Raft Labeling for Remote Sensing Images via Dual-Scale Homogeneous Convolutional Neural Network
Previous Article in Journal
Monitoring the Agung (Indonesia) Ash Plume of November 2017 by Means of Infrared Himawari 8 Data
Previous Article in Special Issue
Multimodal Ground-Based Cloud Classification Using Joint Fusion Convolutional Neural Network
Article Menu
Issue 6 (June) cover image

Export Article

Open AccessArticle
Remote Sens. 2018, 10(6), 920; https://doi.org/10.3390/rs10060920

High-Resolution Remote Sensing Image Classification Method Based on Convolutional Neural Network and Restricted Conditional Random Field

1,2,* and 1
1
School of Computer & Information Technology, Changchun Institute of Technology, Changchun 130012, China
2
The Key Laboratory of Changbai Mountain Historical Culture and VR Technology Reconfiguration, Changchun 130012, China
*
Author to whom correspondence should be addressed.
Received: 18 April 2018 / Revised: 25 May 2018 / Accepted: 8 June 2018 / Published: 10 June 2018
(This article belongs to the Special Issue Recent Advances in Neural Networks for Remote Sensing)
Full-Text   |   PDF [41363 KB, uploaded 10 June 2018]   |  

Abstract

Convolutional neural networks (CNNs) can adapt to more complex data, extract deeper characteristics from images, and achieve higher classification accuracy in remote sensing image scene classification and object detection compared to traditional shallow-model methods. However, directly applying common-structure CNNs to pixel-based remote sensing image classification will lead to boundary or outline distortions of the land cover and consumes enormous computation time in the image classification stage. To solve this problem, we propose a high-resolution remote sensing image classification method based on CNN and the restricted conditional random field algorithm (CNN-RCRF). CNN-RCRF adopts CNN superpixel classification instead of pixel-based classification and uses the restricted conditional random field algorithm (RCRF) to refine the superpixel result image into a pixel-based result. The proposed method not only takes advantage of the classification ability of CNNs but can also avoid boundary or outline distortions of the land cover and greatly reduce computation time in classifying images. The effectiveness of the proposed method is tested with two high-resolution remote sensing images, and the experimental results show that the CNN-RCRF outperforms the existing traditional methods in terms of overall accuracy, and CNN-RCRF’s computation time is much less than that of traditional pixel-based deep-model methods. View Full-Text
Keywords: deep learning; convolutional neural network; conditional random field; remote sensing images; pixel-based classification deep learning; convolutional neural network; conditional random field; remote sensing images; pixel-based classification
Figures

Graphical abstract

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Pan, X.; Zhao, J. High-Resolution Remote Sensing Image Classification Method Based on Convolutional Neural Network and Restricted Conditional Random Field. Remote Sens. 2018, 10, 920.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Remote Sens. EISSN 2072-4292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top