Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/33073
Title: A method for accurate road centerline extraction from a classified image
Authors: Miao, Z
Wang, B
Shi, W 
Wu, H
Keywords: Accurate centerline extraction
Classified images
Geodesic method
Principal curves
Tensor voting
Issue Date: 2014
Publisher: Institute of Electrical and Electronics Engineers
Source: IEEE Journal of selected topics in applied earth observations and remote sensing, 2014, v. 7, no. 12, 6781035, p. 4762-4771 How to cite?
Journal: IEEE journal of selected topics in applied earth observations and remote sensing 
Abstract: Accurate road centerline extraction plays an important role in practical remote sensing applications. Most existing centerline extraction methods have many limitations when the classified image contains complicated objects such as curvilinear, close, or short extent features. To cope with these limitations, this study presents a novel accurate centerline extraction method that integrates tensor voting, principal curves, and the geodesic method. The proposed method consists of three main steps. Tensor voting is first used to extract feature points from the classified image. The extracted feature points are then projected onto the principal curves. Finally, the feature points are linked by the geodesic method to create the central line. The experimental results demonstrate that the proposed method, which is automatic, provides a comparatively accurate solution for centerline extraction from a classified image.
URI: http://hdl.handle.net/10397/33073
ISSN: 1939-1404
EISSN: 2151-1535
DOI: 10.1109/JSTARS.2014.2309613
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

14
Last Week
8
Last month
0
Citations as of Dec 15, 2017

WEB OF SCIENCETM
Citations

12
Last Week
0
Last month
1
Citations as of Dec 12, 2017

Page view(s)

63
Last Week
0
Last month
Checked on Dec 11, 2017

Google ScholarTM

Check

Altmetric



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.