Pedestrian Counting with Occlusion Handling Using Stereo Thermal Cameras

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

16 Citationer (Scopus)

Resumé

The number of pedestrians walking the streets or gathered in public spaces is a valuable piece of information for shop owners, city governments, event organizers and many others. However, automatic counting that takes place day and night is challenging due to changing lighting conditions and the complexity of scenes with many people occluding one another. To address these challenges, this paper introduces the use of a stereo thermal camera setup for pedestrian counting. We investigate the reconstruction of 3D points in a pedestrian street with two thermal cameras and propose an algorithm for pedestrian counting based on clustering and tracking of the 3D point clouds. The method is tested on two five-minute video sequences captured at a public event with a moderate density of pedestrians and heavy occlusions. The counting performance is compared to the manually annotated ground truth and shows success rates of 95.4% and 99.1% for the two sequences.
OriginalsprogEngelsk
Artikelnummer62
TidsskriftSensors
Vol/bind16
Udgave nummer1
ISSN1424-8220
DOI
StatusUdgivet - 5 jan. 2016

Citer dette

@article{d259a4dbcb9c4de080a2f7520ee1129c,
title = "Pedestrian Counting with Occlusion Handling Using Stereo Thermal Cameras",
abstract = "The number of pedestrians walking the streets or gathered in public spaces is a valuable piece of information for shop owners, city governments, event organizers and many others. However, automatic counting that takes place day and night is challenging due to changing lighting conditions and the complexity of scenes with many people occluding one another. To address these challenges, this paper introduces the use of a stereo thermal camera setup for pedestrian counting. We investigate the reconstruction of 3D points in a pedestrian street with two thermal cameras and propose an algorithm for pedestrian counting based on clustering and tracking of the 3D point clouds. The method is tested on two five-minute video sequences captured at a public event with a moderate density of pedestrians and heavy occlusions. The counting performance is compared to the manually annotated ground truth and shows success rates of 95.4{\%} and 99.1{\%} for the two sequences.",
author = "Kristoffersen, {Miklas Str{\o}m} and Dueholm, {Jacob Velling} and Rikke Gade and Moeslund, {Thomas B.}",
year = "2016",
month = "1",
day = "5",
doi = "10.3390/s16010062",
language = "English",
volume = "16",
journal = "Sensors",
issn = "1424-8220",
publisher = "M D P I AG",
number = "1",

}

Pedestrian Counting with Occlusion Handling Using Stereo Thermal Cameras. / Kristoffersen, Miklas Strøm; Dueholm, Jacob Velling; Gade, Rikke; Moeslund, Thomas B.

I: Sensors, Bind 16, Nr. 1, 62, 05.01.2016.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - Pedestrian Counting with Occlusion Handling Using Stereo Thermal Cameras

AU - Kristoffersen, Miklas Strøm

AU - Dueholm, Jacob Velling

AU - Gade, Rikke

AU - Moeslund, Thomas B.

PY - 2016/1/5

Y1 - 2016/1/5

N2 - The number of pedestrians walking the streets or gathered in public spaces is a valuable piece of information for shop owners, city governments, event organizers and many others. However, automatic counting that takes place day and night is challenging due to changing lighting conditions and the complexity of scenes with many people occluding one another. To address these challenges, this paper introduces the use of a stereo thermal camera setup for pedestrian counting. We investigate the reconstruction of 3D points in a pedestrian street with two thermal cameras and propose an algorithm for pedestrian counting based on clustering and tracking of the 3D point clouds. The method is tested on two five-minute video sequences captured at a public event with a moderate density of pedestrians and heavy occlusions. The counting performance is compared to the manually annotated ground truth and shows success rates of 95.4% and 99.1% for the two sequences.

AB - The number of pedestrians walking the streets or gathered in public spaces is a valuable piece of information for shop owners, city governments, event organizers and many others. However, automatic counting that takes place day and night is challenging due to changing lighting conditions and the complexity of scenes with many people occluding one another. To address these challenges, this paper introduces the use of a stereo thermal camera setup for pedestrian counting. We investigate the reconstruction of 3D points in a pedestrian street with two thermal cameras and propose an algorithm for pedestrian counting based on clustering and tracking of the 3D point clouds. The method is tested on two five-minute video sequences captured at a public event with a moderate density of pedestrians and heavy occlusions. The counting performance is compared to the manually annotated ground truth and shows success rates of 95.4% and 99.1% for the two sequences.

U2 - 10.3390/s16010062

DO - 10.3390/s16010062

M3 - Journal article

VL - 16

JO - Sensors

JF - Sensors

SN - 1424-8220

IS - 1

M1 - 62

ER -