A Multi-View Pedestrian Tracking Method in an Uncalibrated Camera Network

Domonkos Varga, T. Szirányi, Attila Kiss, László Spórás, László Havasi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Combining multiple observation views has proven beneficial for pedestrian tracking. In this paper, we present a methodology for tracking pedestrians in an uncalibrated multi-view camera network. Using a set of color and infrared cameras, we can accurately tracking pedestrians for a general scene configuration. We design an algorithmic framework that can be generalized to an arbitrary number of cameras. A novel pedestrian detection algorithm based on Center-symmetric Local Binary Patterns is integrated into the proposed system. In our experiments the common field of view of two neighboring cameras was about 30%. The system improves upon existing systems in the following ways: (1) The system registers partially overlapping camera-views automatically and does not require any manual input. (2) The system reaches the state-of-the-art performance when the common field of view of any two cameras is low and successfully integrates optical and infrared cameras. Our experiments also demonstrate that the proposed architecture is able to provide robust, real-time input to a video surveillance system. Our system was tested in a multi-view, outdoor environment with uncalibrated cameras.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Computer Vision
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages184-191
Number of pages8
Volume2016-February
ISBN (Print)9781467383905
DOIs
Publication statusPublished - Feb 11 2016
Event15th IEEE International Conference on Computer Vision Workshops, ICCVW 2015 - Santiago, Chile
Duration: Dec 11 2015Dec 18 2015

Other

Other15th IEEE International Conference on Computer Vision Workshops, ICCVW 2015
CountryChile
CitySantiago
Period12/11/1512/18/15

Fingerprint

Cameras
Infrared radiation
Experiments
Color

Keywords

  • Cameras
  • Detectors
  • Distortion
  • Feature extraction
  • Histograms
  • Robustness
  • Tracking

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Varga, D., Szirányi, T., Kiss, A., Spórás, L., & Havasi, L. (2016). A Multi-View Pedestrian Tracking Method in an Uncalibrated Camera Network. In Proceedings of the IEEE International Conference on Computer Vision (Vol. 2016-February, pp. 184-191). [7406382] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCVW.2015.33

A Multi-View Pedestrian Tracking Method in an Uncalibrated Camera Network. / Varga, Domonkos; Szirányi, T.; Kiss, Attila; Spórás, László; Havasi, László.

Proceedings of the IEEE International Conference on Computer Vision. Vol. 2016-February Institute of Electrical and Electronics Engineers Inc., 2016. p. 184-191 7406382.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Varga, D, Szirányi, T, Kiss, A, Spórás, L & Havasi, L 2016, A Multi-View Pedestrian Tracking Method in an Uncalibrated Camera Network. in Proceedings of the IEEE International Conference on Computer Vision. vol. 2016-February, 7406382, Institute of Electrical and Electronics Engineers Inc., pp. 184-191, 15th IEEE International Conference on Computer Vision Workshops, ICCVW 2015, Santiago, Chile, 12/11/15. https://doi.org/10.1109/ICCVW.2015.33
Varga D, Szirányi T, Kiss A, Spórás L, Havasi L. A Multi-View Pedestrian Tracking Method in an Uncalibrated Camera Network. In Proceedings of the IEEE International Conference on Computer Vision. Vol. 2016-February. Institute of Electrical and Electronics Engineers Inc. 2016. p. 184-191. 7406382 https://doi.org/10.1109/ICCVW.2015.33
Varga, Domonkos ; Szirányi, T. ; Kiss, Attila ; Spórás, László ; Havasi, László. / A Multi-View Pedestrian Tracking Method in an Uncalibrated Camera Network. Proceedings of the IEEE International Conference on Computer Vision. Vol. 2016-February Institute of Electrical and Electronics Engineers Inc., 2016. pp. 184-191
@inproceedings{2ec846ec17314f82a2d41894abbd547c,
title = "A Multi-View Pedestrian Tracking Method in an Uncalibrated Camera Network",
abstract = "Combining multiple observation views has proven beneficial for pedestrian tracking. In this paper, we present a methodology for tracking pedestrians in an uncalibrated multi-view camera network. Using a set of color and infrared cameras, we can accurately tracking pedestrians for a general scene configuration. We design an algorithmic framework that can be generalized to an arbitrary number of cameras. A novel pedestrian detection algorithm based on Center-symmetric Local Binary Patterns is integrated into the proposed system. In our experiments the common field of view of two neighboring cameras was about 30{\%}. The system improves upon existing systems in the following ways: (1) The system registers partially overlapping camera-views automatically and does not require any manual input. (2) The system reaches the state-of-the-art performance when the common field of view of any two cameras is low and successfully integrates optical and infrared cameras. Our experiments also demonstrate that the proposed architecture is able to provide robust, real-time input to a video surveillance system. Our system was tested in a multi-view, outdoor environment with uncalibrated cameras.",
keywords = "Cameras, Detectors, Distortion, Feature extraction, Histograms, Robustness, Tracking",
author = "Domonkos Varga and T. Szir{\'a}nyi and Attila Kiss and L{\'a}szl{\'o} Sp{\'o}r{\'a}s and L{\'a}szl{\'o} Havasi",
year = "2016",
month = "2",
day = "11",
doi = "10.1109/ICCVW.2015.33",
language = "English",
isbn = "9781467383905",
volume = "2016-February",
pages = "184--191",
booktitle = "Proceedings of the IEEE International Conference on Computer Vision",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - A Multi-View Pedestrian Tracking Method in an Uncalibrated Camera Network

AU - Varga, Domonkos

AU - Szirányi, T.

AU - Kiss, Attila

AU - Spórás, László

AU - Havasi, László

PY - 2016/2/11

Y1 - 2016/2/11

N2 - Combining multiple observation views has proven beneficial for pedestrian tracking. In this paper, we present a methodology for tracking pedestrians in an uncalibrated multi-view camera network. Using a set of color and infrared cameras, we can accurately tracking pedestrians for a general scene configuration. We design an algorithmic framework that can be generalized to an arbitrary number of cameras. A novel pedestrian detection algorithm based on Center-symmetric Local Binary Patterns is integrated into the proposed system. In our experiments the common field of view of two neighboring cameras was about 30%. The system improves upon existing systems in the following ways: (1) The system registers partially overlapping camera-views automatically and does not require any manual input. (2) The system reaches the state-of-the-art performance when the common field of view of any two cameras is low and successfully integrates optical and infrared cameras. Our experiments also demonstrate that the proposed architecture is able to provide robust, real-time input to a video surveillance system. Our system was tested in a multi-view, outdoor environment with uncalibrated cameras.

AB - Combining multiple observation views has proven beneficial for pedestrian tracking. In this paper, we present a methodology for tracking pedestrians in an uncalibrated multi-view camera network. Using a set of color and infrared cameras, we can accurately tracking pedestrians for a general scene configuration. We design an algorithmic framework that can be generalized to an arbitrary number of cameras. A novel pedestrian detection algorithm based on Center-symmetric Local Binary Patterns is integrated into the proposed system. In our experiments the common field of view of two neighboring cameras was about 30%. The system improves upon existing systems in the following ways: (1) The system registers partially overlapping camera-views automatically and does not require any manual input. (2) The system reaches the state-of-the-art performance when the common field of view of any two cameras is low and successfully integrates optical and infrared cameras. Our experiments also demonstrate that the proposed architecture is able to provide robust, real-time input to a video surveillance system. Our system was tested in a multi-view, outdoor environment with uncalibrated cameras.

KW - Cameras

KW - Detectors

KW - Distortion

KW - Feature extraction

KW - Histograms

KW - Robustness

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=84962040329&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962040329&partnerID=8YFLogxK

U2 - 10.1109/ICCVW.2015.33

DO - 10.1109/ICCVW.2015.33

M3 - Conference contribution

AN - SCOPUS:84962040329

SN - 9781467383905

VL - 2016-February

SP - 184

EP - 191

BT - Proceedings of the IEEE International Conference on Computer Vision

PB - Institute of Electrical and Electronics Engineers Inc.

ER -