Local All-Pass filters for optical flow estimation

Christopher Gilliam; Thierry Blu

doi:10.1109/ICASSP.2015.7178227

Local All-Pass filters for optical flow estimation

Christopher Gilliam, Thierry Blu

Electronic, Electrical and Systems Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

19 Citations (Scopus)

Abstract

The optical flow is a velocity field that describes the motion of pixels within a sequence (or set) of images. Its estimation plays an important role in areas such as motion compensation, object tracking and image registration. In this paper, we present a novel framework to estimate the optical flow using local all-pass filters. Instead of using the optical flow equation, the framework is based on relating one image to another, on a local level, using an all-pass filter and then extracting the optical flow from the filter. Using this framework, we present a fast novel algorithm for estimating a smoothly varying optical flow, which we term the Local All-Pass (LAP) algorithm. We demonstrate that this algorithm is consistent and accurate, and that it outperforms three state-of-the-art algorithms when estimating constant and smoothly varying flows. We also show initial competitive results for real images.

Original language	English
Title of host publication	2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1533-1537
Number of pages	5
ISBN (Electronic)	9781467369978
DOIs	https://doi.org/10.1109/ICASSP.2015.7178227
Publication status	Published - 4 Aug 2015
Event	40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Brisbane, Australia Duration: 19 Apr 2014 → 24 Apr 2014

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2015-August
ISSN (Print)	1520-6149

Conference

Conference	40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015
Country/Territory	Australia
City	Brisbane
Period	19/04/14 → 24/04/14

Bibliographical note

Publisher Copyright:
© 2015 IEEE.

Keywords

All-pass Filters
Approximation
Motion Estimation
Optical Flow

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP.2015.7178227

Cite this

Gilliam, C., & Blu, T. (2015). Local All-Pass filters for optical flow estimation. In 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings (pp. 1533-1537). Article 7178227 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2015-August). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICASSP.2015.7178227

Gilliam, Christopher ; Blu, Thierry. / Local All-Pass filters for optical flow estimation. 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Institute of Electrical and Electronics Engineers (IEEE), 2015. pp. 1533-1537 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{5a8347a5492740609f9b572546fff3af,

title = "Local All-Pass filters for optical flow estimation",

abstract = "The optical flow is a velocity field that describes the motion of pixels within a sequence (or set) of images. Its estimation plays an important role in areas such as motion compensation, object tracking and image registration. In this paper, we present a novel framework to estimate the optical flow using local all-pass filters. Instead of using the optical flow equation, the framework is based on relating one image to another, on a local level, using an all-pass filter and then extracting the optical flow from the filter. Using this framework, we present a fast novel algorithm for estimating a smoothly varying optical flow, which we term the Local All-Pass (LAP) algorithm. We demonstrate that this algorithm is consistent and accurate, and that it outperforms three state-of-the-art algorithms when estimating constant and smoothly varying flows. We also show initial competitive results for real images.",

keywords = "All-pass Filters, Approximation, Motion Estimation, Optical Flow",

author = "Christopher Gilliam and Thierry Blu",

note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 ; Conference date: 19-04-2014 Through 24-04-2014",

year = "2015",

month = aug,

day = "4",

doi = "10.1109/ICASSP.2015.7178227",

language = "English",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "1533--1537",

booktitle = "2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings",

}

Gilliam, C & Blu, T 2015, Local All-Pass filters for optical flow estimation. in 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings., 7178227, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2015-August, Institute of Electrical and Electronics Engineers (IEEE), pp. 1533-1537, 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015, Brisbane, Australia, 19/04/14. https://doi.org/10.1109/ICASSP.2015.7178227

Local All-Pass filters for optical flow estimation. / Gilliam, Christopher; Blu, Thierry.
2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Institute of Electrical and Electronics Engineers (IEEE), 2015. p. 1533-1537 7178227 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2015-August).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Local All-Pass filters for optical flow estimation

AU - Gilliam, Christopher

AU - Blu, Thierry

PY - 2015/8/4

Y1 - 2015/8/4

N2 - The optical flow is a velocity field that describes the motion of pixels within a sequence (or set) of images. Its estimation plays an important role in areas such as motion compensation, object tracking and image registration. In this paper, we present a novel framework to estimate the optical flow using local all-pass filters. Instead of using the optical flow equation, the framework is based on relating one image to another, on a local level, using an all-pass filter and then extracting the optical flow from the filter. Using this framework, we present a fast novel algorithm for estimating a smoothly varying optical flow, which we term the Local All-Pass (LAP) algorithm. We demonstrate that this algorithm is consistent and accurate, and that it outperforms three state-of-the-art algorithms when estimating constant and smoothly varying flows. We also show initial competitive results for real images.

AB - The optical flow is a velocity field that describes the motion of pixels within a sequence (or set) of images. Its estimation plays an important role in areas such as motion compensation, object tracking and image registration. In this paper, we present a novel framework to estimate the optical flow using local all-pass filters. Instead of using the optical flow equation, the framework is based on relating one image to another, on a local level, using an all-pass filter and then extracting the optical flow from the filter. Using this framework, we present a fast novel algorithm for estimating a smoothly varying optical flow, which we term the Local All-Pass (LAP) algorithm. We demonstrate that this algorithm is consistent and accurate, and that it outperforms three state-of-the-art algorithms when estimating constant and smoothly varying flows. We also show initial competitive results for real images.

KW - All-pass Filters

KW - Approximation

KW - Motion Estimation

KW - Optical Flow

UR - http://www.scopus.com/inward/record.url?scp=84946077634&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2015.7178227

DO - 10.1109/ICASSP.2015.7178227

M3 - Conference contribution

AN - SCOPUS:84946077634

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 1533

EP - 1537

BT - 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

Y2 - 19 April 2014 through 24 April 2014

ER -

Gilliam C, Blu T. Local All-Pass filters for optical flow estimation. In 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015 - Proceedings. Institute of Electrical and Electronics Engineers (IEEE). 2015. p. 1533-1537. 7178227. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). doi: 10.1109/ICASSP.2015.7178227

Local All-Pass filters for optical flow estimation

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this