Image-Based Template Generation of Road Networks for Virtual Maps

Jing Sun, George Baciu, Xiaobo Yu, Mark Green

Research output: Journal article publicationJournal articleAcademic researchpeer-review

4 Citations (Scopus)


Modern urban regions are dynamic systems exhibiting complex patterns of transportation networks that can often be analyzed and synthesized from the superimposition of more basic network patterns. In this paper, we propose and investigate new methods for the synthesis of complex 3D traffic networks resembling the patterns of traffic networks in real urban regions. Our approach is based on two main synthesis tools: (1) image-derived templates, and (2) a rule-based generating system. Using 2D images as input maps, various road maps with varying patterns can be produced. The generating model accounts for restricted geographical areas, the terrain gradient and urban feature constraints. The generative model follows directions of elevation and connects road ends in such a way as to allow various types of breakpoints.

Original languageEnglish
Pages (from-to)701-720
Number of pages20
JournalInternational Journal of Image and Graphics
Issue number4
Publication statusPublished - 1 Oct 2004


  • 3D modeling, urban synthesis
  • Geographic Information Systems
  • Virtual reality

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Image-Based Template Generation of Road Networks for Virtual Maps'. Together they form a unique fingerprint.

Cite this