Affine invariant detection of periodic motion
- 1 January 1994
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 970-975
- https://doi.org/10.1109/cvpr.1994.323936
Abstract
Current approaches for detecting periodic motion assume a stationary camera and place limits on an object's motion. These approaches rely on the assumption that a periodic motion projects to a set of periodic image curves, an assumption that fails in general. Using affine-invariance, we derive necessary and sufficient conditions for an image sequence to be the projection of a periodic motion. No restrictions are placed on either the motion of the camera or the object. Our algorithm is shown to be provably-correct for noise-free data and is easily extended to be robust with respect to occlusions and noise. The extended algorithm is evaluated with real and synthetic image sequences.Keywords
This publication has 5 references indexed in Scilit:
- Detecting activitiesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Incremental recognition of pedestrians from image sequencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Cyclic motion detection using spatiotemporal surfaces and curvesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Affine invariant detection of periodic motionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Shape and motion from image streams under orthography: a factorization methodInternational Journal of Computer Vision, 1992