Segmentation via annealed motion estimates

Ikhlas Abdel-Qader; Tomislav Bujanovic

doi:10.1109/EIT.2004.4569396

Segmentation via annealed motion estimates

Research output: Chapter in Book/Entry/Poem › Conference contribution

Abstract

A segmentation and motion estimation are two problems that require accurate estimation for many applications in computer vision and image analysis. In this paper, an algorithm that is based on motion information and restored spatial information to segment the scene is presented. This algorithm has minimum dependency on noisy data and the motion vectors are estimated using a deterministic mean field annealing (MFA) framework. The algorithms results are very good using synthetic and real world sequences.

Original language	English (US)
Title of host publication	2009 IEEE MTT-S International Microwave Workshop Series on Signal Integrity and High-Speed Interconnects, IMWS 2009
Publisher	IEEE Computer Society
Pages	297-301
Number of pages	5
ISBN (Print)	9780780387508
DOIs	https://doi.org/10.1109/EIT.2004.4569396
State	Published - 2004
Externally published	Yes
Event	2004 IEEE Electro/Information Technology Conference, EIT 2004 - Milwaukee, WI, United States Duration: Aug 26 2004 → Aug 27 2004

Publication series

Name	2004 IEEE Electro/Information Technology Conference, EIT 2004

Other

Other	2004 IEEE Electro/Information Technology Conference, EIT 2004
Country/Territory	United States
City	Milwaukee, WI
Period	8/26/04 → 8/27/04

ASJC Scopus subject areas

Software
Information Systems
Electrical and Electronic Engineering
Biomedical Engineering

Access to Document

10.1109/EIT.2004.4569396

Cite this

Segmentation via annealed motion estimates. / Abdel-Qader, Ikhlas; Bujanovic, Tomislav.
2009 IEEE MTT-S International Microwave Workshop Series on Signal Integrity and High-Speed Interconnects, IMWS 2009. IEEE Computer Society, 2004. p. 297-301 4569396 (2004 IEEE Electro/Information Technology Conference, EIT 2004).

Research output: Chapter in Book/Entry/Poem › Conference contribution

Abdel-Qader, I & Bujanovic, T 2004, Segmentation via annealed motion estimates. in 2009 IEEE MTT-S International Microwave Workshop Series on Signal Integrity and High-Speed Interconnects, IMWS 2009., 4569396, 2004 IEEE Electro/Information Technology Conference, EIT 2004, IEEE Computer Society, pp. 297-301, 2004 IEEE Electro/Information Technology Conference, EIT 2004, Milwaukee, WI, United States, 8/26/04. https://doi.org/10.1109/EIT.2004.4569396

@inproceedings{60fe822d4f5e4149b2bc5f6db59a55a2,

title = "Segmentation via annealed motion estimates",

abstract = "A segmentation and motion estimation are two problems that require accurate estimation for many applications in computer vision and image analysis. In this paper, an algorithm that is based on motion information and restored spatial information to segment the scene is presented. This algorithm has minimum dependency on noisy data and the motion vectors are estimated using a deterministic mean field annealing (MFA) framework. The algorithms results are very good using synthetic and real world sequences.",

author = "Ikhlas Abdel-Qader and Tomislav Bujanovic",

year = "2004",

doi = "10.1109/EIT.2004.4569396",

language = "English (US)",

isbn = "9780780387508",

series = "2004 IEEE Electro/Information Technology Conference, EIT 2004",

publisher = "IEEE Computer Society",

pages = "297--301",

booktitle = "2009 IEEE MTT-S International Microwave Workshop Series on Signal Integrity and High-Speed Interconnects, IMWS 2009",

address = "United States",

note = "2004 IEEE Electro/Information Technology Conference, EIT 2004 ; Conference date: 26-08-2004 Through 27-08-2004",

}

TY - GEN

T1 - Segmentation via annealed motion estimates

AU - Abdel-Qader, Ikhlas

AU - Bujanovic, Tomislav

PY - 2004

Y1 - 2004

N2 - A segmentation and motion estimation are two problems that require accurate estimation for many applications in computer vision and image analysis. In this paper, an algorithm that is based on motion information and restored spatial information to segment the scene is presented. This algorithm has minimum dependency on noisy data and the motion vectors are estimated using a deterministic mean field annealing (MFA) framework. The algorithms results are very good using synthetic and real world sequences.

AB - A segmentation and motion estimation are two problems that require accurate estimation for many applications in computer vision and image analysis. In this paper, an algorithm that is based on motion information and restored spatial information to segment the scene is presented. This algorithm has minimum dependency on noisy data and the motion vectors are estimated using a deterministic mean field annealing (MFA) framework. The algorithms results are very good using synthetic and real world sequences.

UR - http://www.scopus.com/inward/record.url?scp=67650675783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650675783&partnerID=8YFLogxK

U2 - 10.1109/EIT.2004.4569396

DO - 10.1109/EIT.2004.4569396

M3 - Conference contribution

AN - SCOPUS:67650675783

SN - 9780780387508

T3 - 2004 IEEE Electro/Information Technology Conference, EIT 2004

SP - 297

EP - 301

BT - 2009 IEEE MTT-S International Microwave Workshop Series on Signal Integrity and High-Speed Interconnects, IMWS 2009

PB - IEEE Computer Society

T2 - 2004 IEEE Electro/Information Technology Conference, EIT 2004

Y2 - 26 August 2004 through 27 August 2004

ER -

Segmentation via annealed motion estimates

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this