Segmentation of dynamic scenes from image intensities
- 27 August 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
We present an algebraic geometric approach for segmenting both static and dynamic scenes from image intensities. We introduce the multibody affine constraint as a geometric relationship between the motion of multiple objects and the image intensities generated by them. This constraint is satisfied by all the pixels, regardless of the body to which they belong and regardless of depth discontinuities or perspective effects. We propose a polynomial factorization technique that estimates the number of affine motion models as well as their motion parameters in polynomial time. The factorization technique is used to initialize a nonlinear algorithm that minimizes the algebraic error defined by the multibody affine constraint. Our approach is based solely on image intensities, hence it does not require feature tracking or correspondences. It is therefore a natural generalization of the so-called direct methods in single-body structure from motion to multiple moving objects. We present simulation and experimental results that validate our approach.Keywords
This publication has 9 references indexed in Scilit:
- Mixture models for optical flow computationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Robust dynamic motion estimation over timePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Smoothness in layers: Motion segmentation using nonparametric mixture estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A multi-body factorization method for motion analysisPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Multi-frame infinitesimal motion model for the reconstruction of (dynamic) scenes with multiple linearly moving objectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Reconstruction of a scene with multiple linearly moving objectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Segmentation using eigenvectors: a unifying viewPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- A unified approach to moving object detection in 2D and 3D scenesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- Geometric motion segmentation and model selectionPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1998