Independent motion detection in 3D scenes
- 1 January 1999
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 612-619 vol.1
- https://doi.org/10.1109/iccv.1999.791281
Abstract
Presents an algorithmic approach to the problem of detecting independently moving objects in 3D scenes that are viewed under camera motion. There are two fundamental constraints that can be exploited for the problem: (i) a two- (or multi-)view camera motion constraint (for instance, the epipolar/trilinear constraint), and (ii) a shape constancy constraint. Previous approaches to the problem either only used partial constraints or relied on dense correspondences or flow. We employ both of these fundamental constraints in an algorithm that does not demand a-priori availability of correspondences or flow. Our approach uses the plane-plus-parallax decomposition to enforce the two constraints. It is also demonstrated, for a class of scenes called sparse 3D scenes, in which genuine parallax and independent motions may be confounded, how the plane-plus-parallax decomposition allows progressive introduction and verification of the fundamental constraints. The results of applying the algorithm to some difficult sparse 3D scenes look promising.Keywords
This publication has 15 references indexed in Scilit:
- Computing matched-epipolar projectionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- What can projections of flow fields tell us about the visual motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Model-based brightness constraints: on direct estimation of structure and motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Model-based 2D&3D dominant motion estimation for mosaicing and video representationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Robust Detection of Degenerate Configurations while Estimating the Fundamental MatrixComputer Vision and Image Understanding, 1998
- Geometric motion segmentation and model selectionPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1998
- The Robust Estimation of Multiple Motions: Parametric and Piecewise-Smooth Flow FieldsComputer Vision and Image Understanding, 1996
- A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometryArtificial Intelligence, 1995
- Algebraic functions for recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- 3D geometry from planar parallaxPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994