Person re-identification visualization tool for object tracking across non-overlapping cameras

Etienne Pot, Maiya Hori, Atsushi Shimada, Hajime Nagahara, Rin-Ichiro Taniguchi

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

Abstract

In this paper, we present a visualization tool for person re-identification when tracking objects across non-overlapping cameras. Tracking objects across non-overlapping cameras is challenging because the observations from different cameras are widely separated in both time and space. Hence, these systems need a large amount of labeled training data. Commonly, this training data is constructed manually at significant human cost. We support this process efficiently by visualizing the correspondences of objects across multiple cameras. Our tool facilitates the construction of a database for person re-identification with ease. Moreover, the accuracy of person re-identification can be increased using the generated database because the amount of training data is increased. In the experiments, we apply the proposed tool to real world situations to verify the validity of the proposed system.

Original languageEnglish
Title of host publicationAVSS 2015 - 12th IEEE International Conference on Advanced Video and Signal Based Surveillance
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467376327
DOIs
Publication statusPublished - Oct 19 2015
Event12th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2015 - Karlsruhe, Germany
Duration: Aug 25 2015Aug 28 2015

Other

Other12th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2015
CountryGermany
CityKarlsruhe
Period8/25/158/28/15

Fingerprint

visualization
Visualization
Cameras
human being
experiment
costs
Costs
Experiments
time

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Electrical and Electronic Engineering
  • Communication

Cite this

Pot, E., Hori, M., Shimada, A., Nagahara, H., & Taniguchi, R-I. (2015). Person re-identification visualization tool for object tracking across non-overlapping cameras. In AVSS 2015 - 12th IEEE International Conference on Advanced Video and Signal Based Surveillance [7301740] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AVSS.2015.7301740

Person re-identification visualization tool for object tracking across non-overlapping cameras. / Pot, Etienne; Hori, Maiya; Shimada, Atsushi; Nagahara, Hajime; Taniguchi, Rin-Ichiro.

AVSS 2015 - 12th IEEE International Conference on Advanced Video and Signal Based Surveillance. Institute of Electrical and Electronics Engineers Inc., 2015. 7301740.

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

Pot, E, Hori, M, Shimada, A, Nagahara, H & Taniguchi, R-I 2015, Person re-identification visualization tool for object tracking across non-overlapping cameras. in AVSS 2015 - 12th IEEE International Conference on Advanced Video and Signal Based Surveillance., 7301740, Institute of Electrical and Electronics Engineers Inc., 12th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2015, Karlsruhe, Germany, 8/25/15. https://doi.org/10.1109/AVSS.2015.7301740
Pot E, Hori M, Shimada A, Nagahara H, Taniguchi R-I. Person re-identification visualization tool for object tracking across non-overlapping cameras. In AVSS 2015 - 12th IEEE International Conference on Advanced Video and Signal Based Surveillance. Institute of Electrical and Electronics Engineers Inc. 2015. 7301740 https://doi.org/10.1109/AVSS.2015.7301740
Pot, Etienne ; Hori, Maiya ; Shimada, Atsushi ; Nagahara, Hajime ; Taniguchi, Rin-Ichiro. / Person re-identification visualization tool for object tracking across non-overlapping cameras. AVSS 2015 - 12th IEEE International Conference on Advanced Video and Signal Based Surveillance. Institute of Electrical and Electronics Engineers Inc., 2015.
@inproceedings{cabfaa6dcf5e4922b5bf0487be1ccc29,
title = "Person re-identification visualization tool for object tracking across non-overlapping cameras",
abstract = "In this paper, we present a visualization tool for person re-identification when tracking objects across non-overlapping cameras. Tracking objects across non-overlapping cameras is challenging because the observations from different cameras are widely separated in both time and space. Hence, these systems need a large amount of labeled training data. Commonly, this training data is constructed manually at significant human cost. We support this process efficiently by visualizing the correspondences of objects across multiple cameras. Our tool facilitates the construction of a database for person re-identification with ease. Moreover, the accuracy of person re-identification can be increased using the generated database because the amount of training data is increased. In the experiments, we apply the proposed tool to real world situations to verify the validity of the proposed system.",
author = "Etienne Pot and Maiya Hori and Atsushi Shimada and Hajime Nagahara and Rin-Ichiro Taniguchi",
year = "2015",
month = "10",
day = "19",
doi = "10.1109/AVSS.2015.7301740",
language = "English",
booktitle = "AVSS 2015 - 12th IEEE International Conference on Advanced Video and Signal Based Surveillance",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Person re-identification visualization tool for object tracking across non-overlapping cameras

AU - Pot, Etienne

AU - Hori, Maiya

AU - Shimada, Atsushi

AU - Nagahara, Hajime

AU - Taniguchi, Rin-Ichiro

PY - 2015/10/19

Y1 - 2015/10/19

N2 - In this paper, we present a visualization tool for person re-identification when tracking objects across non-overlapping cameras. Tracking objects across non-overlapping cameras is challenging because the observations from different cameras are widely separated in both time and space. Hence, these systems need a large amount of labeled training data. Commonly, this training data is constructed manually at significant human cost. We support this process efficiently by visualizing the correspondences of objects across multiple cameras. Our tool facilitates the construction of a database for person re-identification with ease. Moreover, the accuracy of person re-identification can be increased using the generated database because the amount of training data is increased. In the experiments, we apply the proposed tool to real world situations to verify the validity of the proposed system.

AB - In this paper, we present a visualization tool for person re-identification when tracking objects across non-overlapping cameras. Tracking objects across non-overlapping cameras is challenging because the observations from different cameras are widely separated in both time and space. Hence, these systems need a large amount of labeled training data. Commonly, this training data is constructed manually at significant human cost. We support this process efficiently by visualizing the correspondences of objects across multiple cameras. Our tool facilitates the construction of a database for person re-identification with ease. Moreover, the accuracy of person re-identification can be increased using the generated database because the amount of training data is increased. In the experiments, we apply the proposed tool to real world situations to verify the validity of the proposed system.

UR - http://www.scopus.com/inward/record.url?scp=84958640175&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958640175&partnerID=8YFLogxK

U2 - 10.1109/AVSS.2015.7301740

DO - 10.1109/AVSS.2015.7301740

M3 - Conference contribution

BT - AVSS 2015 - 12th IEEE International Conference on Advanced Video and Signal Based Surveillance

PB - Institute of Electrical and Electronics Engineers Inc.

ER -