Matching two perspective views

Juyang Weng, Narendra Ahuja, Thomas S. Huang

Research output: Contribution to journalArticlepeer-review


Establishing correspondences between different perspective images of the same scene is one of the most challenging and critical steps in motion and scene analysis. Part of the difficulty is due to a wide variety of 3-D structural discontinuities and occlusions that occur in real-world scenes. This paper describes a computational approach to image matching that uses multiple attributes associated with each image point to yield a generally overdetermined system of constraints, taking into account possible structural discontinuities and occlusions. In the algorithm implemented, intensity, edgeness, and cornerness attributes are used in conjunction with the constraints arising from intraregional smoothness, field continuity and discontinuity, and occlusions to compute dense displacement fields and occlusion maps along the pixel grids. The intensity, edgeness, and cornerness are invariant under rigid motion in the image plane. In order to cope with large disparities, a multiresolution multigrid structure is employed. Coarser level edgeness and cornerness measures are obtained by blurring the finer level measures. The algorithm has been tested on real-world scenes with depth discontinuities and occlusions. A special case of two-view matching is stereo matching, where the motion between two images is known. The algorithm can be easily specialized to perform stereo matching using the epipolar constraint.

Original languageEnglish (US)
Pages (from-to)806-825
Number of pages20
JournalIEEE transactions on pattern analysis and machine intelligence
Issue number8
StatePublished - Aug 1992


  • Dynamic scene analysis
  • motion estimation
  • optical flow
  • stereo matching
  • structure from motion
  • two-view matching

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics


Dive into the research topics of 'Matching two perspective views'. Together they form a unique fingerprint.

Cite this