Integrated point and edge matching on poor textural images constrained by self-adaptive triangulations

Bo Wu, Yunsheng Zhang, Qing Zhu

Research output: Journal article publicationJournal articleAcademic researchpeer-review

58 Citations (Scopus)

Abstract

This paper presents an innovative image matching method for reliable and dense image matching on poor textural images, which is the integrated point and edge matching based on the self-adaptive edge-constrained triangulations. Firstly, several seed points and seed edges are obtained on the stereo images, and they are used to construct a pair of initial edge-constrained triangulations on the images. Then, points and edges are matched based on the triangle constraint and other constraints. The newly matched points and edges are inserted into the triangulations and the constrained triangulations are updated dynamically along with the matching propagation. The final results will be the final edge-constrained triangulations generated from the successfully matched points and edges. Experiments using typical space-borne, airborne, and terrestrial images with poor textures revealed that the integrated point and edge matching method based on self-adaptive triangulations is able to produce dense and reliable matching results. Moreover, from the final matched points and edges, 3D points and edges preserving the physical boundaries of objects can be further derived based on photogrammetric techniques, which is ideal for further object modeling applications. (ISPRS).
Original languageEnglish
Pages (from-to)40-55
Number of pages16
JournalISPRS Journal of Photogrammetry and Remote Sensing
Volume68
Issue number1
DOIs
Publication statusPublished - 1 Mar 2012

Keywords

  • Edge matching
  • Image matching
  • Point matching
  • Self-adaptive propagation
  • Triangle constraint

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Engineering (miscellaneous)
  • Computer Science Applications
  • Computers in Earth Sciences

Cite this