A multi-scale optical flow algorithm based on oriented smoothness constraint optimization

Zexu Zhang; Pingyuan Cui; Hutao Cui

A multi-scale optical flow algorithm based on oriented smoothness constraint optimization

Zexu Zhang^*
, Pingyuan Cui
, Hutao Cui

^*Corresponding author for this work

School of Astronautics

Harbin Institute of Technology

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

3 Scopus citations

Abstract

A multi-scale optical flow algorithm was proposed, which uses oriented smoothness constraint to propagate and optimize the local and rough estimation of the optical flow. Under the frame of multi-scaled Laplacian pyramid, the sum-of-squared difference (SSD) matching technique estimates the flow velocity and the covariance matrix in searching area. Then the oriented smoothness constraint is employed to propagate and optimize the flow velocity estimated, which can suppress the over-smoothness across the occlusions area and motion discontinuities. The experiments obtained encouraging results using synthetic and real image sequences.

Original language	English
Pages (from-to)	153-158
Number of pages	6
Journal	Gaojishu Tongxin/Chinese High Technology Letters
Volume	17
Issue number	2
State	Published - Feb 2007

Keywords

Laplacian pyramid
Multi-scale
Optical flow
Oriented smoothness constraint
Sum-of-squared difference (SSD)

Cite this

@article{45bceea5af4c4d56987c3847f0f25840,

title = "A multi-scale optical flow algorithm based on oriented smoothness constraint optimization",

abstract = "A multi-scale optical flow algorithm was proposed, which uses oriented smoothness constraint to propagate and optimize the local and rough estimation of the optical flow. Under the frame of multi-scaled Laplacian pyramid, the sum-of-squared difference (SSD) matching technique estimates the flow velocity and the covariance matrix in searching area. Then the oriented smoothness constraint is employed to propagate and optimize the flow velocity estimated, which can suppress the over-smoothness across the occlusions area and motion discontinuities. The experiments obtained encouraging results using synthetic and real image sequences.",

keywords = "Laplacian pyramid, Multi-scale, Optical flow, Oriented smoothness constraint, Sum-of-squared difference (SSD)",

author = "Zexu Zhang and Pingyuan Cui and Hutao Cui",

year = "2007",

month = feb,

language = "英语",

volume = "17",

pages = "153--158",

journal = "Gaojishu Tongxin/Chinese High Technology Letters",

issn = "1002-0470",

publisher = "Institute of Scientific and Technical Information of China ",

number = "2",

}

TY - JOUR

T1 - A multi-scale optical flow algorithm based on oriented smoothness constraint optimization

AU - Zhang, Zexu

AU - Cui, Pingyuan

AU - Cui, Hutao

PY - 2007/2

Y1 - 2007/2

N2 - A multi-scale optical flow algorithm was proposed, which uses oriented smoothness constraint to propagate and optimize the local and rough estimation of the optical flow. Under the frame of multi-scaled Laplacian pyramid, the sum-of-squared difference (SSD) matching technique estimates the flow velocity and the covariance matrix in searching area. Then the oriented smoothness constraint is employed to propagate and optimize the flow velocity estimated, which can suppress the over-smoothness across the occlusions area and motion discontinuities. The experiments obtained encouraging results using synthetic and real image sequences.

AB - A multi-scale optical flow algorithm was proposed, which uses oriented smoothness constraint to propagate and optimize the local and rough estimation of the optical flow. Under the frame of multi-scaled Laplacian pyramid, the sum-of-squared difference (SSD) matching technique estimates the flow velocity and the covariance matrix in searching area. Then the oriented smoothness constraint is employed to propagate and optimize the flow velocity estimated, which can suppress the over-smoothness across the occlusions area and motion discontinuities. The experiments obtained encouraging results using synthetic and real image sequences.

KW - Laplacian pyramid

KW - Multi-scale

KW - Optical flow

KW - Oriented smoothness constraint

KW - Sum-of-squared difference (SSD)

UR - https://www.scopus.com/pages/publications/34047110811

M3 - 文章

AN - SCOPUS:34047110811

SN - 1002-0470

VL - 17

SP - 153

EP - 158

JO - Gaojishu Tongxin/Chinese High Technology Letters

JF - Gaojishu Tongxin/Chinese High Technology Letters

IS - 2

ER -

A multi-scale optical flow algorithm based on oriented smoothness constraint optimization

Abstract

Keywords

Other files and links

Fingerprint

Cite this