The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Um método de estimativa de parâmetros de movimento global é proposto. O método pode ser usado para segmentar uma sequência de imagens em regiões de diferentes objetos em movimento. Para quaisquer dois pixels pertencentes ao mesmo objeto em movimento, seus componentes de movimento global associados têm uma relação fixa com a geometria de projeção da imagem da câmera. Portanto, ao examinar os vetores de movimento medidos, somos capazes de agrupar pixels em objetos e, ao mesmo tempo, identificar algumas informações de movimento global. Na presença do zoom da câmera, o formato do objeto fica distorcido e a estimativa convencional do movimento translacional pode não produzir uma modelagem precisa do movimento. Um esquema de estimativa de movimento de bloco deformável é então proposto para estimar o movimento local de um objeto nesta situação. Alguns resultados de simulação são relatados. Para uma sequência gerada artificialmente contendo apenas atividade de zoom, descobrimos que o erro máximo de estimativa no fator de zoom é de cerca de 2%. Resultados bastante bons de segmentação de objetos em movimento são obtidos usando o método proposto de estimativa de movimento local de objetos após a extração de zoom. A compensação de movimento de bloco deformável também supera a compensação de movimento de bloco translacional convencional para material de vídeo contendo atividade de zoom.
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.
Copiar
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
Copiar
@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},}
Copiar
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 -