A method for accurate road centerline extraction from a classified image

Zelang Miao, Bin Wang, Wenzhong Shi, Hao Wu

Research output: Journal article publicationJournal articleAcademic researchpeer-review

31 Citations (Scopus)


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.
Original languageEnglish
Article number6781035
Pages (from-to)4762-4771
Number of pages10
JournalIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Issue number12
Publication statusPublished - 1 Dec 2014


  • Accurate centerline extraction
  • Classified images
  • Geodesic method
  • Principal curves
  • Tensor voting

ASJC Scopus subject areas

  • Computers in Earth Sciences
  • Atmospheric Science

Cite this