Moving Object Detection from Optical Flow without Empirical Thresholds
Summary :
We show that moving objects can be detected from optical flow without using any knowledge about the magnitude of the noise in the flow or any thresholds to be adjusted empirically. The underlying principle is viewing a particular interpretation about the flow as a geometric model and comparing the relative "goodness" of candidate models measured by the geometric AIC.
- Publication
- IEICE TRANSACTIONS on Information Vol.E81-D No.2 pp.243-245
- Publication Date
- 1998/02/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Category
- Image Processing,Computer Graphics and Pattern Recognition
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Naoya OHTA, Kenichi KANATANI, Kazuhiro KIMURA, "Moving Object Detection from Optical Flow without Empirical Thresholds" in IEICE TRANSACTIONS on Information,
vol. E81-D, no. 2, pp. 243-245, February 1998, doi: .
Abstract: We show that moving objects can be detected from optical flow without using any knowledge about the magnitude of the noise in the flow or any thresholds to be adjusted empirically. The underlying principle is viewing a particular interpretation about the flow as a geometric model and comparing the relative "goodness" of candidate models measured by the geometric AIC.
URL: https://global.ieice.org/en_transactions/information/10.1587/e81-d_2_243/_p
Copy
@ARTICLE{e81-d_2_243,
author={Naoya OHTA, Kenichi KANATANI, Kazuhiro KIMURA, },
journal={IEICE TRANSACTIONS on Information},
title={Moving Object Detection from Optical Flow without Empirical Thresholds},
year={1998},
volume={E81-D},
number={2},
pages={243-245},
abstract={We show that moving objects can be detected from optical flow without using any knowledge about the magnitude of the noise in the flow or any thresholds to be adjusted empirically. The underlying principle is viewing a particular interpretation about the flow as a geometric model and comparing the relative "goodness" of candidate models measured by the geometric AIC.},
keywords={},
doi={},
ISSN={},
month={February},}
Copy
TY - JOUR
TI - Moving Object Detection from Optical Flow without Empirical Thresholds
T2 - IEICE TRANSACTIONS on Information
SP - 243
EP - 245
AU - Naoya OHTA
AU - Kenichi KANATANI
AU - Kazuhiro KIMURA
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E81-D
IS - 2
JA - IEICE TRANSACTIONS on Information
Y1 - February 1998
AB - We show that moving objects can be detected from optical flow without using any knowledge about the magnitude of the noise in the flow or any thresholds to be adjusted empirically. The underlying principle is viewing a particular interpretation about the flow as a geometric model and comparing the relative "goodness" of candidate models measured by the geometric AIC.
ER -
English
