An automated system for the creation of an urban infrastructure 3D model using image processing techniques

Junhao Zou, Byungil Kim, Hyoungkwan Kim, M. Al-Hussein

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

Image database creation for infrastructure management is an interdisciplinary endeavor in computer vision, database, and structural engineering. In response to increasing demands for multimedia information in infrastructure management, image databases are becoming an ever more active research area. This paper proposes an automated system for creating an urban infrastructure 3D model using an image database; the system is built by images shot in public areas to record changes of urban infrastructure in three-dimensional (3D) space, such as the addition of new buildings, new overpasses, loss of traffic signs, and growth/change of trees. The system architecture is presented with an emphasis on a 3D information capture and extraction module. Initial experiments with the 3D information capture module show that the proposed system has the potential to efficiently develop a large-scale 3D model of the streets of a municipality.

Original languageEnglish
Pages (from-to)9-17
Number of pages9
JournalKSCE Journal of Civil Engineering
Volume16
Issue number1
DOIs
Publication statusPublished - 2012 Jan

Bibliographical note

Funding Information:
This work was supported by a grant (2010-0014365) from the National Research Foundation and Ministry of Education, Science and Technology of Korea. The writers also would like to express their appreciation to the City of Edmonton, AB, Canada and Siri Feranando, Engineering Manager of Drainage Services, City of Edmonton for allowing the experiment to be conducted at the Coronation Yard.

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering

Fingerprint

Dive into the research topics of 'An automated system for the creation of an urban infrastructure 3D model using image processing techniques'. Together they form a unique fingerprint.

Cite this