Continuous human action recognition in ambient assisted living scenarios

Alexandros Andre Chaaraoui; Francisco Florez-Revuelta

doi:10.1007/978-3-319-16292-8_25

Continuous human action recognition in ambient assisted living scenarios

Alexandros Andre Chaaraoui
, Francisco Florez-Revuelta

Research output: Contribution to conference › Paper › peer-review

3 Downloads (Pure)

Abstract

Ambient assisted living technologies and services make it possible to help elderly and impaired people and increase their personal autonomy. Specifically, vision-based approaches enable the recognition of human behaviour, which in turn allows to build valuable services upon. However, a main constraint is that these have to be able to work online and in real time. In this work, a human action recognition method based on a bag-of-key-poses model and sequence alignment is extended to support continuous human action recognition. The detection of action zones is proposed to locate the most discriminative segments of an action. For the recognition, a method based on a sliding and growing window approach is presented. Furthermore, an evaluation scheme particularly designed for ambient assisted living scenarios is introduced. Experimental results on two publicly available datasets are provided. These show that the proposed action zones lead to a significant improvement and allow real-time processing.

Original language	English
DOIs	https://doi.org/10.1007/978-3-319-16292-8_25
Publication status	Published - Sept 2014
Externally published	Yes
Event	MONAMI 2014 International Conference on Mobile Networks and Management - Wurzburg, Germany Duration: 22 Sept 2014 → 26 Sept 2014

Conference

Conference	MONAMI 2014 International Conference on Mobile Networks and Management
Period	22/09/14 → 26/09/14

Bibliographical note

Note: Published in: Ramón Agüero, Thomas Zinner, Rossitza Goleva, Andreas Timm-Giel, Phuoc Tran-Gia (2015), Mobile Networks and Management 6th International Conference, MONAMI 2014, Würzburg, Germany, September 22-26, 2014, Revised Selected Papers, Cham, Springer, pp. 344-357, ISBN: 9783319162911, ISSN: 1867-8211.

Organising Body: MONAMI

Keywords

Architecture and the built environment
action zones
ambient assisted living
continuous recognition
human action recognition
real time

Access to Document

10.1007/978-3-319-16292-8_25

Florez-Revuelta-F-34990-AAMAccepted author manuscript, 1.57 MBLicence: Unspecified

http://dx.doi.org/10.1007/978-3-319-16292-8_25

Continuous human action recognition in ambient assisted living scenarios
Andre Chaaraoui, A. & Florez-Revuelta, F., Sept 2014, Published in: Ramón Agüero, Thomas Zinner, Rossitza Goleva, Andreas Timm-Giel, Phuoc Tran-Gia (2015), Mobile Networks and Management 6th International Conference, MONAMI 2014, Würzburg, Germany, September 22-26, 2014, Revised Selected Papers, Cham, Springer, pp. 344-357, ISBN: 9783319162911, ISSN: 1867-8211. Organising Body: MONAMI Organising Body: MONAMI.
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Open Access
File
2 Downloads (Pure)

Cite this

@conference{50ea9ecb42124a12b426860d02cb4145,

title = "Continuous human action recognition in ambient assisted living scenarios",

abstract = "Ambient assisted living technologies and services make it possible to help elderly and impaired people and increase their personal autonomy. Specifically, vision-based approaches enable the recognition of human behaviour, which in turn allows to build valuable services upon. However, a main constraint is that these have to be able to work online and in real time. In this work, a human action recognition method based on a bag-of-key-poses model and sequence alignment is extended to support continuous human action recognition. The detection of action zones is proposed to locate the most discriminative segments of an action. For the recognition, a method based on a sliding and growing window approach is presented. Furthermore, an evaluation scheme particularly designed for ambient assisted living scenarios is introduced. Experimental results on two publicly available datasets are provided. These show that the proposed action zones lead to a significant improvement and allow real-time processing.",

keywords = "Architecture and the built environment, action zones, ambient assisted living, continuous recognition, human action recognition, real time",

author = "\{Andre Chaaraoui\}, Alexandros and Francisco Florez-Revuelta",

note = "Note: Published in: Ram{\'o}n Ag{\"u}ero, Thomas Zinner, Rossitza Goleva, Andreas Timm-Giel, Phuoc Tran-Gia (2015), Mobile Networks and Management 6th International Conference, MONAMI 2014, W{\"u}rzburg, Germany, September 22-26, 2014, Revised Selected Papers, Cham, Springer, pp. 344-357, ISBN: 9783319162911, ISSN: 1867-8211. Organising Body: MONAMI; MONAMI 2014 International Conference on Mobile Networks and Management ; Conference date: 22-09-2014 Through 26-09-2014",

year = "2014",

month = sep,

doi = "10.1007/978-3-319-16292-8\_25",

language = "English",

}

TY - CONF

T1 - Continuous human action recognition in ambient assisted living scenarios

AU - Andre Chaaraoui, Alexandros

AU - Florez-Revuelta, Francisco

N1 - Note: Published in: Ramón Agüero, Thomas Zinner, Rossitza Goleva, Andreas Timm-Giel, Phuoc Tran-Gia (2015), Mobile Networks and Management 6th International Conference, MONAMI 2014, Würzburg, Germany, September 22-26, 2014, Revised Selected Papers, Cham, Springer, pp. 344-357, ISBN: 9783319162911, ISSN: 1867-8211. Organising Body: MONAMI

PY - 2014/9

Y1 - 2014/9

N2 - Ambient assisted living technologies and services make it possible to help elderly and impaired people and increase their personal autonomy. Specifically, vision-based approaches enable the recognition of human behaviour, which in turn allows to build valuable services upon. However, a main constraint is that these have to be able to work online and in real time. In this work, a human action recognition method based on a bag-of-key-poses model and sequence alignment is extended to support continuous human action recognition. The detection of action zones is proposed to locate the most discriminative segments of an action. For the recognition, a method based on a sliding and growing window approach is presented. Furthermore, an evaluation scheme particularly designed for ambient assisted living scenarios is introduced. Experimental results on two publicly available datasets are provided. These show that the proposed action zones lead to a significant improvement and allow real-time processing.

AB - Ambient assisted living technologies and services make it possible to help elderly and impaired people and increase their personal autonomy. Specifically, vision-based approaches enable the recognition of human behaviour, which in turn allows to build valuable services upon. However, a main constraint is that these have to be able to work online and in real time. In this work, a human action recognition method based on a bag-of-key-poses model and sequence alignment is extended to support continuous human action recognition. The detection of action zones is proposed to locate the most discriminative segments of an action. For the recognition, a method based on a sliding and growing window approach is presented. Furthermore, an evaluation scheme particularly designed for ambient assisted living scenarios is introduced. Experimental results on two publicly available datasets are provided. These show that the proposed action zones lead to a significant improvement and allow real-time processing.

KW - Architecture and the built environment

KW - action zones

KW - ambient assisted living

KW - continuous recognition

KW - human action recognition

KW - real time

U2 - 10.1007/978-3-319-16292-8_25

DO - 10.1007/978-3-319-16292-8_25

M3 - Paper

T2 - MONAMI 2014 International Conference on Mobile Networks and Management

Y2 - 22 September 2014 through 26 September 2014

ER -

Continuous human action recognition in ambient assisted living scenarios

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Research output

Continuous human action recognition in ambient assisted living scenarios

Cite this