RELIABLE DETECTION OF CAMERA MOTION BASED ON WEIGHTED OPTICAL FLOW FITTING

Rodrigo Minetto, Neucimar J. Leite, Jorge Stolfi

2007

Abstract

Our goal in this paper is the reliable detection of camera motion (pan/zoom/tilt) in video records. We propose an algorithm based on weighted optical flow least-square fitting, where an iterative procedure is used to improve the corresponding weights. To the optical flow computation we used the Kanade-Lucas-Tomasi feature tracker. Besides detecting camera motion, our algorithm provides a precise and reliable quantitative analysis of the movements. It also provides a rough segmentation of each frame into “foreground” and “background” regions, corresponding to the moving and stationary parts of the scene, respectively. Tests with two real videos show that the algorithm is fast and efficient, even in the presence of large objects movements.

Paper Citation

in Harvard Style

Minetto R., J. Leite N. and Stolfi J. (2007). RELIABLE DETECTION OF CAMERA MOTION BASED ON WEIGHTED OPTICAL FLOW FITTING . In Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, ISBN 978-972-8865-74-0, pages 435-440. DOI: 10.5220/0002051504350440

in Bibtex Style

@conference{visapp07,
author={Rodrigo Minetto and Neucimar J. Leite and Jorge Stolfi},
title={RELIABLE DETECTION OF CAMERA MOTION BASED ON WEIGHTED OPTICAL FLOW FITTING},
booktitle={Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,},
year={2007},
pages={435-440},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002051504350440},
isbn={978-972-8865-74-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Second International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP,
TI - RELIABLE DETECTION OF CAMERA MOTION BASED ON WEIGHTED OPTICAL FLOW FITTING
SN - 978-972-8865-74-0
AU - Minetto R.
AU - J. Leite N.
AU - Stolfi J.
PY - 2007
SP - 435
EP - 440
DO - 10.5220/0002051504350440