Urban Road Extraction from VHR Images Using a Multiscale Image Model and a Phase Field Model of Network Geometry

Peng, T.; Jermyn, I.H.; Prinet, V.; Zerubia, J.

doi:10.1109/urs.2007.371835

Urban Road Extraction from VHR Images Using a Multiscale Image Model and a Phase Field Model of Network Geometry

Peng, T.; Jermyn, I.H.; Prinet, V.; Zerubia, J.

Authors

T. Peng

Professor Ian Jermyn i.h.jermyn@durham.ac.uk
Professor

V. Prinet

J. Zerubia

Abstract

This paper addresses the problem of automatically extracting the main road network in a dense urban area from a very high resolution optical satellite image using a variational approach. The model energy has two parts: a phase field higher-order active contour energy that describes our prior knowledge of road network geometry, i.e. that it is composed of elongated structures with roughly parallel borders that meet at junctions; and a multi-scale statistical image model describing the image we expect to see given a road network. By minimizing the model energy, an estimate of the road network is obtained. Promising results on 0.6m QuickBird Panchromatic images are presented, and future improvements to the models are outlined. I.

Citation

Peng, T., Jermyn, I., Prinet, V., & Zerubia, J. (2007). Urban Road Extraction from VHR Images Using a Multiscale Image Model and a Phase Field Model of Network Geometry. In 2007 Urban Remote Sensing Joint Event ; proceedings (1-5). https://doi.org/10.1109/urs.2007.371835

Conference Name	2007 Urban Remote Sensing Joint Event
Conference Location	Paris
Publication Date	Apr 1, 2007
Deposit Date	Aug 12, 2011
Publicly Available Date	Apr 20, 2016
Pages	1-5
Series ISSN	2334-0932
Book Title	2007 Urban Remote Sensing Joint Event ; proceedings.
ISBN	14244071177
DOI	https://doi.org/10.1109/urs.2007.371835

Files

Accepted Conference Proceeding (2.3 Mb)
PDF

Copyright Statement
© 2007 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.