Profile hidden Markov models for foreground object modelling

Ioannis Kazantzidis; Francisco Florez-Revuelta; Jean Christophe Nebel

doi:10.1109/ICIP.2018.8451476

Profile hidden Markov models for foreground object modelling

Ioannis Kazantzidis
, Francisco Florez-Revuelta
, Jean Christophe Nebel

Kingston University
University of Alicante

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

3 Downloads (Pure)

Abstract

Accurate background/foreground segmentation is a preliminary process essential to most visual surveillance applications. With the increasing use of freely moving cameras, strategies have been proposed to refine initial segmentation. In this paper, it is proposed to exploit the Vide-omics paradigm, and Profile Hidden Markov Models in particular, to create a new type of object descriptors relying on spatiotemporal information. Performance of the proposed methodology has been evaluated using a standard dataset of videos captured by moving cameras. Results show that usage of the proposed object descriptors allows better foreground extraction than standard approaches.

Original language	English
Title of host publication	Published in: 2018 25th IEEE International Conference on Image Processing (ICIP). Piscataway, U.S. : Institute of Electrical and Electronics Engineers, Inc. ISSN (online) 2381-8549 ISBN 9781479970629 Organising Body: IEEE Organising Body: IEEE
DOIs	https://doi.org/10.1109/ICIP.2018.8451476
Publication status	Published - Oct 2018

Bibliographical note

Note: Published in: 2018 25th IEEE International Conference on Image Processing (ICIP). Piscataway, U.S. : Institute of Electrical and Electronics Engineers, Inc. ISSN (online) 2381-8549 ISBN 9781479970629

Organising Body: IEEE

Organising Body: IEEE

Keywords

Computer science and informatics

Access to Document

10.1109/ICIP.2018.8451476

Kazantzidis-I-42430-AAMAccepted author manuscript, 402 KBLicence: Unspecified

http://dx.doi.org/10.1109/ICIP.2018.8451476

Profile hidden Markov models for foreground object modelling
Kazantzidis, I., Florez Revuelta, F. & Nebel, J.-C., Oct 2018.
Research output: Contribution to conference › Paper › peer-review

Open Access
File
4 Downloads (Pure)

Cite this

Kazantzidis, I., Florez-Revuelta, F., & Nebel, J. C. (2018). Profile hidden Markov models for foreground object modelling. In Published in: 2018 25th IEEE International Conference on Image Processing (ICIP). Piscataway, U.S. : Institute of Electrical and Electronics Engineers, Inc. ISSN (online) 2381-8549 ISBN 9781479970629 Organising Body: IEEE Organising Body: IEEE https://doi.org/10.1109/ICIP.2018.8451476

Kazantzidis, Ioannis ; Florez-Revuelta, Francisco ; Nebel, Jean Christophe. / Profile hidden Markov models for foreground object modelling. Published in: 2018 25th IEEE International Conference on Image Processing (ICIP). Piscataway, U.S. : Institute of Electrical and Electronics Engineers, Inc. ISSN (online) 2381-8549 ISBN 9781479970629 Organising Body: IEEE Organising Body: IEEE. 2018.

@inproceedings{ce65da78357d422193b7dac8084e5976,

title = "Profile hidden Markov models for foreground object modelling",

abstract = "Accurate background/foreground segmentation is a preliminary process essential to most visual surveillance applications. With the increasing use of freely moving cameras, strategies have been proposed to refine initial segmentation. In this paper, it is proposed to exploit the Vide-omics paradigm, and Profile Hidden Markov Models in particular, to create a new type of object descriptors relying on spatiotemporal information. Performance of the proposed methodology has been evaluated using a standard dataset of videos captured by moving cameras. Results show that usage of the proposed object descriptors allows better foreground extraction than standard approaches.",

keywords = "Computer science and informatics",

author = "Ioannis Kazantzidis and Francisco Florez-Revuelta and Nebel, \{Jean Christophe\}",

note = "Note: Published in: 2018 25th IEEE International Conference on Image Processing (ICIP). Piscataway, U.S. : Institute of Electrical and Electronics Engineers, Inc. ISSN (online) 2381-8549 ISBN 9781479970629 Organising Body: IEEE Organising Body: IEEE",

year = "2018",

month = oct,

doi = "10.1109/ICIP.2018.8451476",

language = "English",

booktitle = "Published in: 2018 25th IEEE International Conference on Image Processing (ICIP). Piscataway, U.S. : Institute of Electrical and Electronics Engineers, Inc. ISSN (online) 2381-8549 ISBN 9781479970629 Organising Body: IEEE Organising Body: IEEE",

}

Kazantzidis, I, Florez-Revuelta, F & Nebel, JC 2018, Profile hidden Markov models for foreground object modelling. in Published in: 2018 25th IEEE International Conference on Image Processing (ICIP). Piscataway, U.S. : Institute of Electrical and Electronics Engineers, Inc. ISSN (online) 2381-8549 ISBN 9781479970629 Organising Body: IEEE Organising Body: IEEE. https://doi.org/10.1109/ICIP.2018.8451476

Profile hidden Markov models for foreground object modelling. / Kazantzidis, Ioannis; Florez-Revuelta, Francisco; Nebel, Jean Christophe.
Published in: 2018 25th IEEE International Conference on Image Processing (ICIP). Piscataway, U.S. : Institute of Electrical and Electronics Engineers, Inc. ISSN (online) 2381-8549 ISBN 9781479970629 Organising Body: IEEE Organising Body: IEEE. 2018.

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

TY - GEN

T1 - Profile hidden Markov models for foreground object modelling

AU - Kazantzidis, Ioannis

AU - Florez-Revuelta, Francisco

AU - Nebel, Jean Christophe

N1 - Note: Published in: 2018 25th IEEE International Conference on Image Processing (ICIP). Piscataway, U.S. : Institute of Electrical and Electronics Engineers, Inc. ISSN (online) 2381-8549 ISBN 9781479970629 Organising Body: IEEE Organising Body: IEEE

PY - 2018/10

Y1 - 2018/10

N2 - Accurate background/foreground segmentation is a preliminary process essential to most visual surveillance applications. With the increasing use of freely moving cameras, strategies have been proposed to refine initial segmentation. In this paper, it is proposed to exploit the Vide-omics paradigm, and Profile Hidden Markov Models in particular, to create a new type of object descriptors relying on spatiotemporal information. Performance of the proposed methodology has been evaluated using a standard dataset of videos captured by moving cameras. Results show that usage of the proposed object descriptors allows better foreground extraction than standard approaches.

AB - Accurate background/foreground segmentation is a preliminary process essential to most visual surveillance applications. With the increasing use of freely moving cameras, strategies have been proposed to refine initial segmentation. In this paper, it is proposed to exploit the Vide-omics paradigm, and Profile Hidden Markov Models in particular, to create a new type of object descriptors relying on spatiotemporal information. Performance of the proposed methodology has been evaluated using a standard dataset of videos captured by moving cameras. Results show that usage of the proposed object descriptors allows better foreground extraction than standard approaches.

KW - Computer science and informatics

U2 - 10.1109/ICIP.2018.8451476

DO - 10.1109/ICIP.2018.8451476

M3 - Conference contribution

BT - Published in: 2018 25th IEEE International Conference on Image Processing (ICIP). Piscataway, U.S. : Institute of Electrical and Electronics Engineers, Inc. ISSN (online) 2381-8549 ISBN 9781479970629 Organising Body: IEEE Organising Body: IEEE

ER -

Kazantzidis I, Florez-Revuelta F, Nebel JC. Profile hidden Markov models for foreground object modelling. In Published in: 2018 25th IEEE International Conference on Image Processing (ICIP). Piscataway, U.S. : Institute of Electrical and Electronics Engineers, Inc. ISSN (online) 2381-8549 ISBN 9781479970629 Organising Body: IEEE Organising Body: IEEE. 2018 doi: 10.1109/ICIP.2018.8451476

Profile hidden Markov models for foreground object modelling

Abstract

Bibliographical note

Keywords

Access to Document

Fingerprint

Research output

Profile hidden Markov models for foreground object modelling

Cite this