A multi-body factorization method for motion analysis
- 19 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1071-1076
- https://doi.org/10.1109/iccv.1995.466815
Abstract
The structure from motion problem has been extensively studied in the field of computer vision. Yet, the bulk of the existing work assumes that the scene contains only a single moving object. The more realistic case where an unknown number of objects move in the scene has received little attention, especially for its theoretical treatment. We present a new method for separating and recovering the motion and shape of multiple independently moving objects in a sequence of images. The method does not require prior knowledge of the number of objects, nor is dependent on any grouping of features into an object at the image level. For this purpose, we introduce a mathematical construct of object shapes, called the shape interaction matrix, which is invariant to both the object motions and the selection of coordinate systems. This invariant structure is computable solely from the observed trajectories of image features without grouping them into individual objects. Once the structure is computed, it allows for segmenting features into objects by the process of transforming it into a canonical form, as well as recovering the shape and motion of each object.Keywords
This publication has 10 references indexed in Scilit:
- Motion segmentation and local structurePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Feature grouping in moving objectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Factorization-based segmentation of motionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Computing two motions from three framesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Computing occluding and transparent motionsInternational Journal of Computer Vision, 1994
- A paraperspective factorization method for shape and motion recoveryPublished by Springer Nature ,1994
- Shape and motion from image streams under orthography: a factorization methodInternational Journal of Computer Vision, 1992
- Perceptual motion transparency: the role of geometrical informationJournal of the Optical Society of America A, 1992
- Affine structure from motionJournal of the Optical Society of America A, 1991
- Spatiotemporal energy models for the perception of motionJournal of the Optical Society of America A, 1985