Feature-Based Error Concealment for Object-Based Video

Pei-Jun LEE; Homer H. CHEN; Wen-June WANG; Liang-Gee CHEN

doi:10.1093/ietcom/e88-b.6.2616

Feature-Based Error Concealment for Object-Based Video

Pei-Jun LEE, Homer H. CHEN, Wen-June WANG, Liang-Gee CHEN

Full Text Views

0

Cite this

Summary :

In this paper, a new error concealment algorithm for MPEG-4 object-based video is presented. The algorithm consists of a feature matching step to identify temporally corresponding features between video frames and an affine parameter estimation step to find the motion of the feature points. In the feature matching step, an efficient cross-radial search (CRS) method is developed to find the best matching points. In the affine parameter estimation step, a non-iterative least squares estimation algorithm is developed to estimate the affine parameters. An attractive feature of the algorithm is that the shape data and texture data are handled by the same method. Unlike previous methods, this unified approach works for the case where the video object undergoes a drastic movement, such as a sharp turn. Experimental results show that the proposed algorithm performs much better than previous approaches by about 0.3-2.8 dB for shape data and 1.6-5.0 dB for texture data.

Publication: IEICE TRANSACTIONS on Communications Vol.E88-B No.6 pp.2616-2626

Publication Date: 2005/06/01

Publicized

Online ISSN

DOI: 10.1093/ietcom/e88-b.6.2616

Type of Manuscript: PAPER

Category: Multimedia Systems for Communications" Multimedia Systems for Communications

Cite this

Copy

Pei-Jun LEE, Homer H. CHEN, Wen-June WANG, Liang-Gee CHEN, "Feature-Based Error Concealment for Object-Based Video" in IEICE TRANSACTIONS on Communications, vol. E88-B, no. 6, pp. 2616-2626, June 2005, doi: 10.1093/ietcom/e88-b.6.2616.
Abstract: In this paper, a new error concealment algorithm for MPEG-4 object-based video is presented. The algorithm consists of a feature matching step to identify temporally corresponding features between video frames and an affine parameter estimation step to find the motion of the feature points. In the feature matching step, an efficient cross-radial search (CRS) method is developed to find the best matching points. In the affine parameter estimation step, a non-iterative least squares estimation algorithm is developed to estimate the affine parameters. An attractive feature of the algorithm is that the shape data and texture data are handled by the same method. Unlike previous methods, this unified approach works for the case where the video object undergoes a drastic movement, such as a sharp turn. Experimental results show that the proposed algorithm performs much better than previous approaches by about 0.3-2.8 dB for shape data and 1.6-5.0 dB for texture data.
URL: https://global.ieice.org/en_transactions/communications/10.1093/ietcom/e88-b.6.2616/_p

Copy

@ARTICLE{e88-b_6_2616,
author={Pei-Jun LEE, Homer H. CHEN, Wen-June WANG, Liang-Gee CHEN, },
journal={IEICE TRANSACTIONS on Communications},
title={Feature-Based Error Concealment for Object-Based Video},
year={2005},
volume={E88-B},
number={6},
pages={2616-2626},
abstract={In this paper, a new error concealment algorithm for MPEG-4 object-based video is presented. The algorithm consists of a feature matching step to identify temporally corresponding features between video frames and an affine parameter estimation step to find the motion of the feature points. In the feature matching step, an efficient cross-radial search (CRS) method is developed to find the best matching points. In the affine parameter estimation step, a non-iterative least squares estimation algorithm is developed to estimate the affine parameters. An attractive feature of the algorithm is that the shape data and texture data are handled by the same method. Unlike previous methods, this unified approach works for the case where the video object undergoes a drastic movement, such as a sharp turn. Experimental results show that the proposed algorithm performs much better than previous approaches by about 0.3-2.8 dB for shape data and 1.6-5.0 dB for texture data.},
keywords={},
doi={10.1093/ietcom/e88-b.6.2616},
ISSN={},
month={June},}

Copy

TY - JOUR
TI - Feature-Based Error Concealment for Object-Based Video
T2 - IEICE TRANSACTIONS on Communications
SP - 2616
EP - 2626
AU - Pei-Jun LEE
AU - Homer H. CHEN
AU - Wen-June WANG
AU - Liang-Gee CHEN
PY - 2005
DO - 10.1093/ietcom/e88-b.6.2616
JO - IEICE TRANSACTIONS on Communications
SN -
VL - E88-B
IS - 6
JA - IEICE TRANSACTIONS on Communications
Y1 - June 2005
AB - In this paper, a new error concealment algorithm for MPEG-4 object-based video is presented. The algorithm consists of a feature matching step to identify temporally corresponding features between video frames and an affine parameter estimation step to find the motion of the feature points. In the feature matching step, an efficient cross-radial search (CRS) method is developed to find the best matching points. In the affine parameter estimation step, a non-iterative least squares estimation algorithm is developed to estimate the affine parameters. An attractive feature of the algorithm is that the shape data and texture data are handled by the same method. Unlike previous methods, this unified approach works for the case where the video object undergoes a drastic movement, such as a sharp turn. Experimental results show that the proposed algorithm performs much better than previous approaches by about 0.3-2.8 dB for shape data and 1.6-5.0 dB for texture data.
ER -