Re-DLinkNet: Based on DLinkNet and ReNet for Road Extraction from High Resolution Satellite Imagery

In order to speed up the update of existing road maps, it is crucial to develop a more efficient road extraction method from remote sensing images. In recent years, deep learning techniques have been widely used for road extraction applications. Among current CNN-based deep networks for road extract...

Full description

Saved in:
Bibliographic Details
Main Authors: Wang, Yuchuan, Tong, Ling, Wen, Jiang, Xiao, Fanghong, Gao, Yaqi, He, Liubei, Li, DingMao
Format: Conference Proceeding
Language:English
Subjects:
Convolution
DenseRe-Block
DLinkNet
Feature extraction
Image Processing
Optical fiber networks
Remote Sensing
Road Extraction
Roads
Satellites
Shape
Urban areas
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In order to speed up the update of existing road maps, it is crucial to develop a more efficient road extraction method from remote sensing images. In recent years, deep learning techniques have been widely used for road extraction applications. Among current CNN-based deep networks for road extraction, few works study the shape of the convolution kernel, and the remote contextual features dependency relationship is not fully utilized. In view of these problems, an improved DLinkNet is proposed in this paper. Firstly, a convolutional layer which fuses information of multiple scales is used to replace the InitBlock in the front of the network. Secondly, instead of using the D-Block, the DenseRe-Block is applied to the center structure of DLinkNet. The experimental results show that the improved network has a higher IoU score than DLinkNet when extracting roads from optical images in both city and mountain town areas.
ISSN:2153-7003
DOI:10.1109/IGARSS47720.2021.9553728