Reconstruction Bias U-Net for Road Extraction From Optical Remote Sensing Images

Automatic road extraction from remote sensing images plays an important role for navigation, intelligent transportation, and road network update, etc. Convolutional neural network (CNN)-based methods have presented many achievements for road extraction from remote sensing images. CNN-based methods r...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in applied earth observations and remote sensing 2021, Vol.14, p.2284-2294
Main Authors: Chen, Ziyi, Wang, Cheng, Li, Jonathan, Xie, Nianci, Han, Yan, Du, Jixiang
Format: Article
Language:English
Subjects:
Artificial neural networks
Asymmetric structures
Bias
CNN model
dataset
Datasets
Feature extraction
Image reconstruction
Image segmentation
Labels
Methods
Navigation
Neural networks
optical remote sensing image
Optical sensors
Reconstruction
Remote sensing
road extraction
Roads
Semantics
Training
Transportation networks
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:Automatic road extraction from remote sensing images plays an important role for navigation, intelligent transportation, and road network update, etc. Convolutional neural network (CNN)-based methods have presented many achievements for road extraction from remote sensing images. CNN-based methods require a large dataset with high quality labels for model training. However, there is still few standard and large dataset, which is specially designed for road extraction from optical remote sensing images. Besides, the existing end-to-end CNN models for road extraction from remote sensing images are usually with symmetric structure, studying on asymmetric structure between encoding and decoding is rare. To address the above problems, this article first provides a publicly available dataset LRSNY for road extraction from optical remote sensing images with manually labelled labels. Second, we propose a reconstruction bias U-Net for road extraction from remote sensing images. In our model, we increase the decoding branches to obtain multiple semantic information from different upsamplings. Experimental results show that our method achieves better performance compared with other six state-of-the-art segmentation models when testing on our LRSNY dataset. We also test on Massachusetts and Shaoshan datasets. The good performances on the two datasets further prove the effectiveness of our method.
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2021.3053603