Three-Dimensional Adaptive Sensing of People in a Multi-Camera Setup

Martin Andersen, Rasmus Skovgaard Andersen, Nikolaos Katsarakis, Aristodemos Pnevmatikakis, Zheng-Hua Tan

Publikation: Bidrag til tidsskriftKonferenceartikel i tidsskriftForskningpeer review

2 Citationer (Scopus)

Resumé

Sensing the presence and state of people is of paramount importance
in assistive living environments. In this paper we
utilise a set of fixed, calibrated cameras to model the bodies
of people directly in three dimensions. An adaptive foreground
segmentation algorithm is run per camera, providing
evidence to be collected in 3D body blobs. A particle
filter tracker allows monitoring the modelled bodies across
time, offering estimations of their state by using hot-spots
and body posture. We apply our system on fall detection
and activity monitoring for the elderly, addressing both emergency
and cognitive care.
OriginalsprogEngelsk
TidsskriftProceedings of the European Signal Processing Conference
Vol/bind2010
Sider (fra-til)964-968
ISSN2076-1465
StatusUdgivet - 2010
BegivenhedEuropean Signal Processing Conference 2010 - Aalborg, Danmark
Varighed: 23 aug. 201027 aug. 2010

Konference

KonferenceEuropean Signal Processing Conference 2010
LandDanmark
ByAalborg
Periode23/08/201027/08/2010

Fingerprint

Cameras
Monitoring
Adaptive algorithms

Citer dette

@inproceedings{dc386a51584346619a3cdb0d0ded4ac1,
title = "Three-Dimensional Adaptive Sensing of People in a Multi-Camera Setup",
abstract = "Sensing the presence and state of people is of paramount importancein assistive living environments. In this paper weutilise a set of fixed, calibrated cameras to model the bodiesof people directly in three dimensions. An adaptive foregroundsegmentation algorithm is run per camera, providingevidence to be collected in 3D body blobs. A particlefilter tracker allows monitoring the modelled bodies acrosstime, offering estimations of their state by using hot-spotsand body posture. We apply our system on fall detectionand activity monitoring for the elderly, addressing both emergencyand cognitive care.",
author = "Martin Andersen and Andersen, {Rasmus Skovgaard} and Nikolaos Katsarakis and Aristodemos Pnevmatikakis and Zheng-Hua Tan",
year = "2010",
language = "English",
volume = "2010",
pages = "964--968",
journal = "Proceedings of the European Signal Processing Conference",
issn = "2076-1465",
publisher = "European Association for Signal Processing (EURASIP)",

}

Three-Dimensional Adaptive Sensing of People in a Multi-Camera Setup. / Andersen, Martin; Andersen, Rasmus Skovgaard; Katsarakis, Nikolaos; Pnevmatikakis, Aristodemos ; Tan, Zheng-Hua.

I: Proceedings of the European Signal Processing Conference, Bind 2010, 2010, s. 964-968.

Publikation: Bidrag til tidsskriftKonferenceartikel i tidsskriftForskningpeer review

TY - GEN

T1 - Three-Dimensional Adaptive Sensing of People in a Multi-Camera Setup

AU - Andersen, Martin

AU - Andersen, Rasmus Skovgaard

AU - Katsarakis, Nikolaos

AU - Pnevmatikakis, Aristodemos

AU - Tan, Zheng-Hua

PY - 2010

Y1 - 2010

N2 - Sensing the presence and state of people is of paramount importancein assistive living environments. In this paper weutilise a set of fixed, calibrated cameras to model the bodiesof people directly in three dimensions. An adaptive foregroundsegmentation algorithm is run per camera, providingevidence to be collected in 3D body blobs. A particlefilter tracker allows monitoring the modelled bodies acrosstime, offering estimations of their state by using hot-spotsand body posture. We apply our system on fall detectionand activity monitoring for the elderly, addressing both emergencyand cognitive care.

AB - Sensing the presence and state of people is of paramount importancein assistive living environments. In this paper weutilise a set of fixed, calibrated cameras to model the bodiesof people directly in three dimensions. An adaptive foregroundsegmentation algorithm is run per camera, providingevidence to be collected in 3D body blobs. A particlefilter tracker allows monitoring the modelled bodies acrosstime, offering estimations of their state by using hot-spotsand body posture. We apply our system on fall detectionand activity monitoring for the elderly, addressing both emergencyand cognitive care.

M3 - Conference article in Journal

VL - 2010

SP - 964

EP - 968

JO - Proceedings of the European Signal Processing Conference

JF - Proceedings of the European Signal Processing Conference

SN - 2076-1465

ER -