Skip navigation.

UCSD Computer Vision

Segmentation and Reconstruction from Periodic Motion

Serge Belongie, Josh Wills


A method for detecting and segmenting periodic motion is presented. We exploit periodicity as a cue and detect periodic motion in complex scenes where common methods for motion segmentation are likely to fail. We note that periodic motion detection can be seen as an approximate case of sequence alignment where an image sequence is matched to itself over one or more periods of time. To use this observation, we first consider alignment of two video sequences obtained by independently moving cameras. Under assumption of constant translation, the fundamental matrices and the homographies are shown to be time-linear matrix functions. These dynamic quantities can be estimated by matching corresponding space-time points with similar local motion and shape. For periodic motion, we match corresponding points across periods and develop a RANSAC procedure to simultaneously estimate the period and the dynamic geometric transformations between periodic views. Using this method, we demonstrate detection and segmentation of human periodic motion in complex scenes with non-rigid backgrounds, moving camera and motion parallax.

More info on:

Non UCSD Vision People also Involved

Ivan Laptev and Patrick Pérez (IRISA/INRIA)


Segmentation demo (0.5Mb)

Related Publications

Laptev I., Belongie S., PĂ©rez P., Wills J., "Periodic Motion Detection and Segmentation via Approximate Sequence Alignment", ICCV, vol. 1, Beijing, China, pp. 816-823, 2005. [BibTex]
Belongie S., Wills J., "Structure from Periodic Motion", Workshop on Spatial Coherence for Visual Motion Analysis (SCVMA), Prague, Czech Republic, Springer Verlag, 2004. [BibTex][pdf]