Visual recognition to access and analyze people density and flow patterns in indoor environments

C. Ruz, C. Pieringer, B. Peralta, I. Lillo, P. Espinace, R. Gonzalez, B. Wendt, D. Mery, A. Soto

Resultado de la investigación: Conference contribution

1 Cita (Scopus)

Resumen

This work describes our experience developing a system to access density and flow of people in large indoor spaces using a network of RGB cameras. The proposed system is based on a set of overlapped and calibrated cameras. This facilitates the use of geometric constraints that help to reduce visual ambiguities. These constraints are combined with classifiers based on visual appearance to produce an efficient and robust method to detect and track humans. In this work, we argue that flow and density of people are low level measurements that need to be complemented with suitable analytic tools to bridge semantic gaps and become useful information for a target application. Consequently, we also propose a set of analytic tools that help a human user to effectively take advantage of the measurements provided by the system. Finally, we report results that demonstrate the relevance of the proposed ideas.

Idioma originalEnglish
Título de la publicación alojadaProceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas1-8
Número de páginas8
ISBN (versión digital)9781479966820
DOI
EstadoPublished - 1 ene 2015
Evento2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015 - Waikoloa, United States
Duración: 5 ene 20159 ene 2015

Conference

Conference2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015
PaísUnited States
CiudadWaikoloa
Período5/01/159/01/15

Huella dactilar

Flow patterns
Cameras
Level measurement
Classifiers
Semantics

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Citar esto

Ruz, C., Pieringer, C., Peralta, B., Lillo, I., Espinace, P., Gonzalez, R., ... Soto, A. (2015). Visual recognition to access and analyze people density and flow patterns in indoor environments. En Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015 (pp. 1-8). [7045862] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/WACV.2015.8
Ruz, C. ; Pieringer, C. ; Peralta, B. ; Lillo, I. ; Espinace, P. ; Gonzalez, R. ; Wendt, B. ; Mery, D. ; Soto, A. / Visual recognition to access and analyze people density and flow patterns in indoor environments. Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 1-8
@inproceedings{caf0ce0693ed4626b6224b52d7368df4,
title = "Visual recognition to access and analyze people density and flow patterns in indoor environments",
abstract = "This work describes our experience developing a system to access density and flow of people in large indoor spaces using a network of RGB cameras. The proposed system is based on a set of overlapped and calibrated cameras. This facilitates the use of geometric constraints that help to reduce visual ambiguities. These constraints are combined with classifiers based on visual appearance to produce an efficient and robust method to detect and track humans. In this work, we argue that flow and density of people are low level measurements that need to be complemented with suitable analytic tools to bridge semantic gaps and become useful information for a target application. Consequently, we also propose a set of analytic tools that help a human user to effectively take advantage of the measurements provided by the system. Finally, we report results that demonstrate the relevance of the proposed ideas.",
author = "C. Ruz and C. Pieringer and B. Peralta and I. Lillo and P. Espinace and R. Gonzalez and B. Wendt and D. Mery and A. Soto",
year = "2015",
month = "1",
day = "1",
doi = "10.1109/WACV.2015.8",
language = "English",
pages = "1--8",
booktitle = "Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Ruz, C, Pieringer, C, Peralta, B, Lillo, I, Espinace, P, Gonzalez, R, Wendt, B, Mery, D & Soto, A 2015, Visual recognition to access and analyze people density and flow patterns in indoor environments. En Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015., 7045862, Institute of Electrical and Electronics Engineers Inc., pp. 1-8, 2015 15th IEEE Winter Conference on Applications of Computer Vision, WACV 2015, Waikoloa, United States, 5/01/15. https://doi.org/10.1109/WACV.2015.8

Visual recognition to access and analyze people density and flow patterns in indoor environments. / Ruz, C.; Pieringer, C.; Peralta, B.; Lillo, I.; Espinace, P.; Gonzalez, R.; Wendt, B.; Mery, D.; Soto, A.

Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1-8 7045862.

Resultado de la investigación: Conference contribution

TY - GEN

T1 - Visual recognition to access and analyze people density and flow patterns in indoor environments

AU - Ruz, C.

AU - Pieringer, C.

AU - Peralta, B.

AU - Lillo, I.

AU - Espinace, P.

AU - Gonzalez, R.

AU - Wendt, B.

AU - Mery, D.

AU - Soto, A.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - This work describes our experience developing a system to access density and flow of people in large indoor spaces using a network of RGB cameras. The proposed system is based on a set of overlapped and calibrated cameras. This facilitates the use of geometric constraints that help to reduce visual ambiguities. These constraints are combined with classifiers based on visual appearance to produce an efficient and robust method to detect and track humans. In this work, we argue that flow and density of people are low level measurements that need to be complemented with suitable analytic tools to bridge semantic gaps and become useful information for a target application. Consequently, we also propose a set of analytic tools that help a human user to effectively take advantage of the measurements provided by the system. Finally, we report results that demonstrate the relevance of the proposed ideas.

AB - This work describes our experience developing a system to access density and flow of people in large indoor spaces using a network of RGB cameras. The proposed system is based on a set of overlapped and calibrated cameras. This facilitates the use of geometric constraints that help to reduce visual ambiguities. These constraints are combined with classifiers based on visual appearance to produce an efficient and robust method to detect and track humans. In this work, we argue that flow and density of people are low level measurements that need to be complemented with suitable analytic tools to bridge semantic gaps and become useful information for a target application. Consequently, we also propose a set of analytic tools that help a human user to effectively take advantage of the measurements provided by the system. Finally, we report results that demonstrate the relevance of the proposed ideas.

UR - http://www.scopus.com/inward/record.url?scp=84925433410&partnerID=8YFLogxK

U2 - 10.1109/WACV.2015.8

DO - 10.1109/WACV.2015.8

M3 - Conference contribution

SP - 1

EP - 8

BT - Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ruz C, Pieringer C, Peralta B, Lillo I, Espinace P, Gonzalez R y otros. Visual recognition to access and analyze people density and flow patterns in indoor environments. En Proceedings - 2015 IEEE Winter Conference on Applications of Computer Vision, WACV 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 1-8. 7045862 https://doi.org/10.1109/WACV.2015.8