Classifiers for motion

Mithun Das Gupta, Shyamsundar Rajaram, Nemanja Petrovic, Thomas S. Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution


In this paper, we present a supervised learning based approach for sub-pixel motion estimation. The novelty of this work is the learning based method itself which tries to learn the shifts from a large training database. Integer pixel shift is sub-divided and discretized to levels in both the horizontal and vertical direction. We pose the problem of motion estimation in a polar coordinate system. Shift estimation in the x and y direction has been posed as a problem of estimating r and θ. The ordinal property of τ has been used, and consequently, we employ a ranking based approach for estimating τ. For θ estimation we employ multi-class classification techniques. We demonstrate how very simplistic features can be used to differentiate between different subpixel shifts.

Original languageEnglish (US)
Title of host publicationProceedings - 18th International Conference on Pattern Recognition, ICPR 2006
Number of pages4
StatePublished - 2006
Event18th International Conference on Pattern Recognition, ICPR 2006 - Hong Kong, China
Duration: Aug 20 2006Aug 24 2006

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651


Other18th International Conference on Pattern Recognition, ICPR 2006
CityHong Kong

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition


Dive into the research topics of 'Classifiers for motion'. Together they form a unique fingerprint.

Cite this