loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Yann Lepoittevin 1 ; Isabelle Herlin 1 and Dominique Béréziat 2

Affiliations: 1 Inria Paris-Rocquencourt, France ; 2 UPMC Univ Paris 06, CNRS and UMR 7606, France

Keyword(s): Data Assimilation, Ensemble Kalman Filter, Localization, Motion Estimation, Optical Flow.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Motion, Tracking and Stereo Vision ; Optical Flow and Motion Analyses

Abstract: This paper designs an Image-based Ensemble Kalman Filter (IEnKF), whose components are defined only from image properties, to estimate motion on image sequences. The key elements of this filter are, first, the construction of the initial ensemble, and second, the propagation in time of this ensemble on the studied temporal interval. Both are analyzed in the paper and their impact on results is discussed with synthetic and real data experiments. The initial ensemble is obtained by adding a Gaussian vector field to an estimate of motion on the first two frames. The standard deviation of this normal law is computed from motion results given by a set of optical flow methods of the literature. It describes the uncertainty on the motion value at initial date. The propagation in time of the ensemble members relies on the following evolution laws: transport by velocity of the image brightness function and Euler equations for the motion function. Shrinking of the ensemble is avoided thanks to a localization method and the use of observation ensembles, both techniques being defined from image characteristics. This Image-based Ensemble Kalman Filter is quantified on synthetic experiments and applied on traffic and meteorological images. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.142.201.93

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Lepoittevin, Y.; Herlin, I. and Béréziat, D. (2015). An Image-based Ensemble Kalman Filter for Motion Estimation. In Proceedings of the 10th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2015) - Volume 1: VISAPP; ISBN 978-989-758-091-8; ISSN 2184-4321, SciTePress, pages 437-445. DOI: 10.5220/0005259804370445

@conference{visapp15,
author={Yann Lepoittevin. and Isabelle Herlin. and Dominique Béréziat.},
title={An Image-based Ensemble Kalman Filter for Motion Estimation},
booktitle={Proceedings of the 10th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2015) - Volume 1: VISAPP},
year={2015},
pages={437-445},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005259804370445},
isbn={978-989-758-091-8},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 10th International Conference on Computer Vision Theory and Applications (VISIGRAPP 2015) - Volume 1: VISAPP
TI - An Image-based Ensemble Kalman Filter for Motion Estimation
SN - 978-989-758-091-8
IS - 2184-4321
AU - Lepoittevin, Y.
AU - Herlin, I.
AU - Béréziat, D.
PY - 2015
SP - 437
EP - 445
DO - 10.5220/0005259804370445
PB - SciTePress