Annotating Sensor Data to Identify Activities of Daily Living

Mark Donnelly, Tommaso Magherini, CD Nugent, Federico Cruciani, Cristiano Paggetti

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

DANTE is an application, which supports the annotation of ADLs captured using a pair of stereo cameras. DANTE is able to interpret the position and orientation of any object that is tagged with a special marker. Offline, users navigate frame-by-frame through captured scenes to annotate onset/completion of object interactions. The main utility is supporting the development of large annotated datasets, which is essential for the development and evaluation of context-aware models to interpret and monitor occupant behaviour within smart environments. DANTE only records scenes during which ‘tagged’ objects are interacted with therefore significantly reducing the amount of redundant footage recorded. The current study has extended the concepts of DANTE and has used it to support the annotation of additional sensor platforms. Results demonstrated both the capability of DANTE to support annotation of other platforms along with reducing the amount of time previously required to manually annotate such data by more than 45%.
LanguageEnglish
Pages41-48
JournalLecture Notes in Artificial Intelligence
Volume6719
DOIs
Publication statusPublished - 2011

Fingerprint

Cameras
Sensors

Cite this

Donnelly, Mark ; Magherini, Tommaso ; Nugent, CD ; Cruciani, Federico ; Paggetti, Cristiano. / Annotating Sensor Data to Identify Activities of Daily Living. In: Lecture Notes in Artificial Intelligence. 2011 ; Vol. 6719. pp. 41-48.
@article{dacdc7969a004f7a97b555ce3098008d,
title = "Annotating Sensor Data to Identify Activities of Daily Living",
abstract = "DANTE is an application, which supports the annotation of ADLs captured using a pair of stereo cameras. DANTE is able to interpret the position and orientation of any object that is tagged with a special marker. Offline, users navigate frame-by-frame through captured scenes to annotate onset/completion of object interactions. The main utility is supporting the development of large annotated datasets, which is essential for the development and evaluation of context-aware models to interpret and monitor occupant behaviour within smart environments. DANTE only records scenes during which ‘tagged’ objects are interacted with therefore significantly reducing the amount of redundant footage recorded. The current study has extended the concepts of DANTE and has used it to support the annotation of additional sensor platforms. Results demonstrated both the capability of DANTE to support annotation of other platforms along with reducing the amount of time previously required to manually annotate such data by more than 45{\%}.",
author = "Mark Donnelly and Tommaso Magherini and CD Nugent and Federico Cruciani and Cristiano Paggetti",
year = "2011",
doi = "10.1007/978-3-642-21535-3_6",
language = "English",
volume = "6719",
pages = "41--48",
journal = "Lecture Notes in Artificial Intelligence",
issn = "0302-9743",

}

Annotating Sensor Data to Identify Activities of Daily Living. / Donnelly, Mark; Magherini, Tommaso; Nugent, CD; Cruciani, Federico; Paggetti, Cristiano.

In: Lecture Notes in Artificial Intelligence, Vol. 6719, 2011, p. 41-48.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Annotating Sensor Data to Identify Activities of Daily Living

AU - Donnelly, Mark

AU - Magherini, Tommaso

AU - Nugent, CD

AU - Cruciani, Federico

AU - Paggetti, Cristiano

PY - 2011

Y1 - 2011

N2 - DANTE is an application, which supports the annotation of ADLs captured using a pair of stereo cameras. DANTE is able to interpret the position and orientation of any object that is tagged with a special marker. Offline, users navigate frame-by-frame through captured scenes to annotate onset/completion of object interactions. The main utility is supporting the development of large annotated datasets, which is essential for the development and evaluation of context-aware models to interpret and monitor occupant behaviour within smart environments. DANTE only records scenes during which ‘tagged’ objects are interacted with therefore significantly reducing the amount of redundant footage recorded. The current study has extended the concepts of DANTE and has used it to support the annotation of additional sensor platforms. Results demonstrated both the capability of DANTE to support annotation of other platforms along with reducing the amount of time previously required to manually annotate such data by more than 45%.

AB - DANTE is an application, which supports the annotation of ADLs captured using a pair of stereo cameras. DANTE is able to interpret the position and orientation of any object that is tagged with a special marker. Offline, users navigate frame-by-frame through captured scenes to annotate onset/completion of object interactions. The main utility is supporting the development of large annotated datasets, which is essential for the development and evaluation of context-aware models to interpret and monitor occupant behaviour within smart environments. DANTE only records scenes during which ‘tagged’ objects are interacted with therefore significantly reducing the amount of redundant footage recorded. The current study has extended the concepts of DANTE and has used it to support the annotation of additional sensor platforms. Results demonstrated both the capability of DANTE to support annotation of other platforms along with reducing the amount of time previously required to manually annotate such data by more than 45%.

U2 - 10.1007/978-3-642-21535-3_6

DO - 10.1007/978-3-642-21535-3_6

M3 - Article

VL - 6719

SP - 41

EP - 48

JO - Lecture Notes in Artificial Intelligence

T2 - Lecture Notes in Artificial Intelligence

JF - Lecture Notes in Artificial Intelligence

SN - 0302-9743

ER -