Motion Field Segmentation under the 3-D Movement of Rigid Planar Patches
Summary :
A new motion field segmentation algorithm under the 8-parameters motion model is presented which uses a multipass iterative region-refining techinique. The iterative region-refining module consists of a seed block detection and subsequent region-refining iterations. An initial estimate of an object motion is provided in the seed block detection process. This initial estimate is iteratively updated and approaches to a reliable mapping parameter set in region-refining process. A multipass composition of the module makes it possible to detect multiple motions in a scene. Our simulation results confirm that the proposed method successfully partitions an image into independently moving objects with allowable computation time.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E78-A No.12 pp.1890-1894
- Publication Date
- 1995/12/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- LETTER
- Category
- Image Theory
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
Si-Woong LEE, Seong-Dae KIM, "Motion Field Segmentation under the 3-D Movement of Rigid Planar Patches" in IEICE TRANSACTIONS on Fundamentals,
vol. E78-A, no. 12, pp. 1890-1894, December 1995, doi: .
Abstract: A new motion field segmentation algorithm under the 8-parameters motion model is presented which uses a multipass iterative region-refining techinique. The iterative region-refining module consists of a seed block detection and subsequent region-refining iterations. An initial estimate of an object motion is provided in the seed block detection process. This initial estimate is iteratively updated and approaches to a reliable mapping parameter set in region-refining process. A multipass composition of the module makes it possible to detect multiple motions in a scene. Our simulation results confirm that the proposed method successfully partitions an image into independently moving objects with allowable computation time.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e78-a_12_1890/_p
Copy
@ARTICLE{e78-a_12_1890,
author={Si-Woong LEE, Seong-Dae KIM, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Motion Field Segmentation under the 3-D Movement of Rigid Planar Patches},
year={1995},
volume={E78-A},
number={12},
pages={1890-1894},
abstract={A new motion field segmentation algorithm under the 8-parameters motion model is presented which uses a multipass iterative region-refining techinique. The iterative region-refining module consists of a seed block detection and subsequent region-refining iterations. An initial estimate of an object motion is provided in the seed block detection process. This initial estimate is iteratively updated and approaches to a reliable mapping parameter set in region-refining process. A multipass composition of the module makes it possible to detect multiple motions in a scene. Our simulation results confirm that the proposed method successfully partitions an image into independently moving objects with allowable computation time.},
keywords={},
doi={},
ISSN={},
month={December},}
Copy
TY - JOUR
TI - Motion Field Segmentation under the 3-D Movement of Rigid Planar Patches
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1890
EP - 1894
AU - Si-Woong LEE
AU - Seong-Dae KIM
PY - 1995
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E78-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 1995
AB - A new motion field segmentation algorithm under the 8-parameters motion model is presented which uses a multipass iterative region-refining techinique. The iterative region-refining module consists of a seed block detection and subsequent region-refining iterations. An initial estimate of an object motion is provided in the seed block detection process. This initial estimate is iteratively updated and approaches to a reliable mapping parameter set in region-refining process. A multipass composition of the module makes it possible to detect multiple motions in a scene. Our simulation results confirm that the proposed method successfully partitions an image into independently moving objects with allowable computation time.
ER -
English
