Computer Vision, Graphics, and Image Processing
Applying temporal constraints to the dynamic stereo problem
References (19)
- et al.
Psychophysical and computational studies towards a theory of human stereopsis
Artif. Intell.
(1981) A program to generate synthetic walkers as dynamic point-light displays
Behav. Res. Methods Instrum.
(1978)- et al.
On the frame-to-frame correspondence between greyvalue characteristics
- et al.
Pattern Classification and Scene Analysis
(1973) - et al.
Extension of Panum's fusional area in binocularly stabilized vision
J. Opt. Soc. Amer.
(1967) From Images to Surfaces
(1981)- et al.
The Interpretation of Biological Motion
MIT A. I. Memo 608
(1980) Foundations of Cyclopean Perception
(1971)Tracking three dimensional moving light displays
Cited by (38)
Stereo and motion correspondences using nonlinear optimization method
2006, Computer Vision and Image UnderstandingCitation 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 ComputingCitation 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.
Optimal error discretization under depth and range constraints
1998, Pattern Recognition LettersEstablishing motion-based feature point correspondence
1998, Pattern RecognitionCooperative fusion of stereo and motion
1996, Pattern RecognitionOptical flow estimation using smoothness of intensity trajectories
1994, Computer Vision and Image Understanding
- ∗
Fellow, Canadian Institute for Advanced Research.