Spatial and fourier error minimization for motion estimation and segmentation

Alexia Briassouli, Narendra Ahuja

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

Abstract

We present a new approach to motion estimation by minimizing the squared error in both the spatial and frequency domains and we show that the spatially global nature of FT leads to a motion estimation error that is much lower than that obtained via spatial motion estimation. On the other hand, spatial analysis is useful for accurate segmentation. We describe a novel, hybrid approach combining the above two estimates of motion and segmentation. We examine the robustness of minimizing the error terms in both domains, both theoretically and experimentally. Experiments with real and synthetic sequences demonstrate the capabilities of the proposed algorithm.

Original languageEnglish (US)
Title of host publicationProceedings - 18th International Conference on Pattern Recognition, ICPR 2006
Pages94-97
Number of pages4
DOIs
StatePublished - Dec 1 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
Volume1
ISSN (Print)1051-4651

Other

Other18th International Conference on Pattern Recognition, ICPR 2006
CountryChina
CityHong Kong
Period8/20/068/24/06

    Fingerprint

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Briassouli, A., & Ahuja, N. (2006). Spatial and fourier error minimization for motion estimation and segmentation. In Proceedings - 18th International Conference on Pattern Recognition, ICPR 2006 (pp. 94-97). [1698841] (Proceedings - International Conference on Pattern Recognition; Vol. 1). https://doi.org/10.1109/ICPR.2006.1068