Applying temporal constraints to the dynamic stereo problem

https://doi.org/10.1016/0734-189X(86)90219-7Get rights and content

Abstract

An algorithm is presented for the problem of the stereopsis of time-varuing images (the dynamic stereo problem). Dynamic stereopsis is the integration of two problems; static stereopsis and temporal correspondence. Rather than finding the intersection of these problems to be more difficult, it was found that by solving the two problem simultaneously, and thus incorporating the spatio-temporal context within which a scene exists, some of the hard subproblems belonging to stereopsis and temporal correspondence could be avoided. The algorithm relies on a general smoothness assumption to assign both disparity and temporal matches. A simple model of the motion of three-dimensional features is used to guide the matching process and to identify conditional matches which violate a general smoothness assumption. A spatial proximity rule is used to further restrict possible matches. The algorithm has been tested on both synthetic and real input sequences. Input sequences were chosen from three-dimensional moving light displays and from “real” grey-level digitized images.

References (19)

  • J.E.W. Mayhew et al.

    Psychophysical and computational studies towards a theory of human stereopsis

    Artif. Intell.

    (1981)
  • J.E. Cutting

    A program to generate synthetic walkers as dynamic point-light displays

    Behav. Res. Methods Instrum.

    (1978)
  • L. Dreschler et al.

    On the frame-to-frame correspondence between greyvalue characteristics

  • R.O. Duda et al.

    Pattern Classification and Scene Analysis

    (1973)
  • D. Fender et al.

    Extension of Panum's fusional area in binocularly stabilized vision

    J. Opt. Soc. Amer.

    (1967)
  • W.E. Grimson

    From Images to Surfaces

    (1981)
  • D.D. Hoffman et al.

    The Interpretation of Biological Motion

    MIT A. I. Memo 608

    (1980)
  • B. Julesz

    Foundations of Cyclopean Perception

    (1971)
  • M.R.M. Jenkin

    Tracking three dimensional moving light displays

There are more references available in the full text version of this article.

Cited by (38)

  • Stereo and motion correspondences using nonlinear optimization method

    2006, Computer Vision and Image Understanding
    Citation Excerpt :

    Others used controlled camera motions to assist the process of recovering 3D structures from the scene [7,20]. Waxman and Duncan [21], Jenkin and Tsotsos [13], and Aloimonos and Nerve [1] attempt to unify stereo and motion cues to overcome these shortcomings, but these approaches have their own limitations, such as a planarity assumption and extensive computational searching. Another approach is to remove the ambiguity that the motion cue recovers about the world information, only up to a scale factor in the case of an unknown motion.

  • A relaxation algorithm for real-time multiple view 3D-tracking

    2002, Image and Vision Computing
    Citation Excerpt :

    Constraints on the 3D motion are commonly used to reduce the search space such as rigidity [11], co-planarity [12,13], local coherence [14], epipolar geometry [15,45,46] and tri-focal tensor [16]. Symbolic optimisation methods have been employed such as best-first or greedy search [17–20], beam searching [3] and competitive linking [21]. These approaches address the search for the global optima but either still suffer from local optima, or do not reduce the computational complexity to a level where they can be readily employed for real-time vision applications, or both.

  • Optical flow estimation using smoothness of intensity trajectories

    1994, Computer Vision and Image Understanding
View all citing articles on Scopus

Fellow, Canadian Institute for Advanced Research.

View full text