Improved global motion estimation based on iterative least-squares with adaptive variable block size

Leiqi Zhu; Dongkai Yang; Qishan Zhang

doi:10.1587/transfun.E94.A.448

Improved global motion estimation based on iterative least-squares with adaptive variable block size

Leiqi Zhu
, Dongkai Yang^*
, Qishan Zhang

^*Corresponding author for this work

School of Electronic and Information Engineering

Beihang University

Research output: Contribution to journal › Article › peer-review

Abstract

In order to reduce the convergence time in an iterative pro cedure, some gradient based preliminary processes are employed to elimi nate outliers. The adaptive variable block size is also introduced to balance the accuracy and computational complexity. Moreover, the use of Can berra distance instead of Euclidean distance illustrates higher performance in measuring motion similarity.

Original language	English
Pages (from-to)	448-451
Number of pages	4
Journal	IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
Volume	E94-A
Issue number	1
DOIs	https://doi.org/10.1587/transfun.E94.A.448
State	Published - Jan 2011

Keywords

Adaptive vari able block size
Global motion estimation
Iterative least squares
Preprocessing

Access to Document

10.1587/transfun.E94.A.448

Cite this

@article{d22f8fc6104c4d00aa1640e64e71fefa,

title = "Improved global motion estimation based on iterative least-squares with adaptive variable block size",

abstract = "In order to reduce the convergence time in an iterative pro cedure, some gradient based preliminary processes are employed to elimi nate outliers. The adaptive variable block size is also introduced to balance the accuracy and computational complexity. Moreover, the use of Can berra distance instead of Euclidean distance illustrates higher performance in measuring motion similarity.",

keywords = "Adaptive vari able block size, Global motion estimation, Iterative least squares, Preprocessing",

author = "Leiqi Zhu and Dongkai Yang and Qishan Zhang",

year = "2011",

month = jan,

doi = "10.1587/transfun.E94.A.448",

language = "英语",

volume = "E94-A",

pages = "448--451",

journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",

issn = "0916-8508",

publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",

number = "1",

}

TY - JOUR

T1 - Improved global motion estimation based on iterative least-squares with adaptive variable block size

AU - Zhu, Leiqi

AU - Yang, Dongkai

AU - Zhang, Qishan

PY - 2011/1

Y1 - 2011/1

N2 - In order to reduce the convergence time in an iterative pro cedure, some gradient based preliminary processes are employed to elimi nate outliers. The adaptive variable block size is also introduced to balance the accuracy and computational complexity. Moreover, the use of Can berra distance instead of Euclidean distance illustrates higher performance in measuring motion similarity.

AB - In order to reduce the convergence time in an iterative pro cedure, some gradient based preliminary processes are employed to elimi nate outliers. The adaptive variable block size is also introduced to balance the accuracy and computational complexity. Moreover, the use of Can berra distance instead of Euclidean distance illustrates higher performance in measuring motion similarity.

KW - Adaptive vari able block size

KW - Global motion estimation

KW - Iterative least squares

KW - Preprocessing

UR - https://www.scopus.com/pages/publications/78650941007

U2 - 10.1587/transfun.E94.A.448

DO - 10.1587/transfun.E94.A.448

M3 - 文章

AN - SCOPUS:78650941007

SN - 0916-8508

VL - E94-A

SP - 448

EP - 451

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

IS - 1

ER -

Improved global motion estimation based on iterative least-squares with adaptive variable block size

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this