Global Motion Parameter Extraction and Deformable Block Motion Estimation

Chi-Hsi SU; Hsueh-Ming HANG; David W. LIN

Global Motion Parameter Extraction and Deformable Block Motion Estimation

Chi-Hsi SU, Hsueh-Ming HANG, David W. LIN

Full Text Views

0

Cite this

Summary :

A global motion parameter estimation method is proposed. The method can be used to segment an image sequence into regions of different moving objects. For any two pixels belonging to the same moving object, their associated global motion components have a fixed relationship from the projection geometry of camera imaging. Therefore, by examining the measured motion vectors we are able to group pixels into objects and, at the same time, identify some global motion information. In the presence of camera zoom, the object shape is distorted and conventional translational motion estimation may not yield accurate motion modeling. A deformable block motion estimation scheme is thus proposed to estimate the local motion of an object in this situation. Some simulation results are reported. For an artificially generated sequence containing only zoom activity, we find that the maximum estimation error in the zoom factor is about 2. 8 %. Rather good moving object segmentation results are obtained using the proposed object local motion estimation method after zoom extraction. The deformable block motion compensation is also seen to outperform conventional translational block motion compensation for video material containing zoom activity.

Publication: IEICE TRANSACTIONS on Information Vol.E82-D No.8 pp.1210-1218

Publication Date: 1999/08/25

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Image Processing,Computer Graphics and Pattern Recognition

Cite this

Copy

Chi-Hsi SU, Hsueh-Ming HANG, David W. LIN, "Global Motion Parameter Extraction and Deformable Block Motion Estimation" in IEICE TRANSACTIONS on Information, vol. E82-D, no. 8, pp. 1210-1218, August 1999, doi: .
Abstract: A global motion parameter estimation method is proposed. The method can be used to segment an image sequence into regions of different moving objects. For any two pixels belonging to the same moving object, their associated global motion components have a fixed relationship from the projection geometry of camera imaging. Therefore, by examining the measured motion vectors we are able to group pixels into objects and, at the same time, identify some global motion information. In the presence of camera zoom, the object shape is distorted and conventional translational motion estimation may not yield accurate motion modeling. A deformable block motion estimation scheme is thus proposed to estimate the local motion of an object in this situation. Some simulation results are reported. For an artificially generated sequence containing only zoom activity, we find that the maximum estimation error in the zoom factor is about 2. 8 %. Rather good moving object segmentation results are obtained using the proposed object local motion estimation method after zoom extraction. The deformable block motion compensation is also seen to outperform conventional translational block motion compensation for video material containing zoom activity.
URL: https://global.ieice.org/en_transactions/information/10.1587/e82-d_8_1210/_p

Copy

@ARTICLE{e82-d_8_1210,
author={Chi-Hsi SU, Hsueh-Ming HANG, David W. LIN, },
journal={IEICE TRANSACTIONS on Information},
title={Global Motion Parameter Extraction and Deformable Block Motion Estimation},
year={1999},
volume={E82-D},
number={8},
pages={1210-1218},
abstract={A global motion parameter estimation method is proposed. The method can be used to segment an image sequence into regions of different moving objects. For any two pixels belonging to the same moving object, their associated global motion components have a fixed relationship from the projection geometry of camera imaging. Therefore, by examining the measured motion vectors we are able to group pixels into objects and, at the same time, identify some global motion information. In the presence of camera zoom, the object shape is distorted and conventional translational motion estimation may not yield accurate motion modeling. A deformable block motion estimation scheme is thus proposed to estimate the local motion of an object in this situation. Some simulation results are reported. For an artificially generated sequence containing only zoom activity, we find that the maximum estimation error in the zoom factor is about 2. 8 %. Rather good moving object segmentation results are obtained using the proposed object local motion estimation method after zoom extraction. The deformable block motion compensation is also seen to outperform conventional translational block motion compensation for video material containing zoom activity.},
keywords={},
doi={},
ISSN={},
month={August},}

Copy

TY - JOUR
TI - Global Motion Parameter Extraction and Deformable Block Motion Estimation
T2 - IEICE TRANSACTIONS on Information
SP - 1210
EP - 1218
AU - Chi-Hsi SU
AU - Hsueh-Ming HANG
AU - David W. LIN
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E82-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 1999
AB - A global motion parameter estimation method is proposed. The method can be used to segment an image sequence into regions of different moving objects. For any two pixels belonging to the same moving object, their associated global motion components have a fixed relationship from the projection geometry of camera imaging. Therefore, by examining the measured motion vectors we are able to group pixels into objects and, at the same time, identify some global motion information. In the presence of camera zoom, the object shape is distorted and conventional translational motion estimation may not yield accurate motion modeling. A deformable block motion estimation scheme is thus proposed to estimate the local motion of an object in this situation. Some simulation results are reported. For an artificially generated sequence containing only zoom activity, we find that the maximum estimation error in the zoom factor is about 2. 8 %. Rather good moving object segmentation results are obtained using the proposed object local motion estimation method after zoom extraction. The deformable block motion compensation is also seen to outperform conventional translational block motion compensation for video material containing zoom activity.
ER -