Baby-posture classification from pressure-sensor data

Sabri Boughorbel, Fons Bruekers, Jeroen Breebaart

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

11 Citations (Scopus)

Abstract

The activity of babies and more specifically the posture of babies is an important aspect in their safety and development. In this paper, we studied the automatic classification of baby posture using a pressure-sensitive mat. The posture classification problem is formulated as the design of features that describe the pressure patterns induced by the child in combination with generic classifiers. Novel rotation invariant features constructed from high order statistics obtained from the concentric rings around the center of gravity. Non-constant ring radii are used in order to ensure uniform cell areas and therefore equal importance of features. A vote fusion of various generic classifiers is used for classification. Temporal information was shown to improve the classification performance. The obtained results are promising and open new opportunities for applications and further research in the area of baby safety and development.

Original languageEnglish
Title of host publicationProceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010
Pages556-559
Number of pages4
DOIs
Publication statusPublished - 2010
Externally publishedYes
Event2010 20th International Conference on Pattern Recognition, ICPR 2010 - Istanbul, Turkey
Duration: 23 Aug 201026 Aug 2010

Other

Other2010 20th International Conference on Pattern Recognition, ICPR 2010
CountryTurkey
CityIstanbul
Period23/8/1026/8/10

Fingerprint

Pressure sensors
Classifiers
Higher order statistics
Gravitation
Fusion reactions

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Boughorbel, S., Bruekers, F., & Breebaart, J. (2010). Baby-posture classification from pressure-sensor data. In Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010 (pp. 556-559). [5597438] https://doi.org/10.1109/ICPR.2010.141

Baby-posture classification from pressure-sensor data. / Boughorbel, Sabri; Bruekers, Fons; Breebaart, Jeroen.

Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010. 2010. p. 556-559 5597438.

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

Boughorbel, S, Bruekers, F & Breebaart, J 2010, Baby-posture classification from pressure-sensor data. in Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010., 5597438, pp. 556-559, 2010 20th International Conference on Pattern Recognition, ICPR 2010, Istanbul, Turkey, 23/8/10. https://doi.org/10.1109/ICPR.2010.141
Boughorbel S, Bruekers F, Breebaart J. Baby-posture classification from pressure-sensor data. In Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010. 2010. p. 556-559. 5597438 https://doi.org/10.1109/ICPR.2010.141
Boughorbel, Sabri ; Bruekers, Fons ; Breebaart, Jeroen. / Baby-posture classification from pressure-sensor data. Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010. 2010. pp. 556-559
@inproceedings{a286a04a57884ccc96febc2c5fc83f6f,
title = "Baby-posture classification from pressure-sensor data",
abstract = "The activity of babies and more specifically the posture of babies is an important aspect in their safety and development. In this paper, we studied the automatic classification of baby posture using a pressure-sensitive mat. The posture classification problem is formulated as the design of features that describe the pressure patterns induced by the child in combination with generic classifiers. Novel rotation invariant features constructed from high order statistics obtained from the concentric rings around the center of gravity. Non-constant ring radii are used in order to ensure uniform cell areas and therefore equal importance of features. A vote fusion of various generic classifiers is used for classification. Temporal information was shown to improve the classification performance. The obtained results are promising and open new opportunities for applications and further research in the area of baby safety and development.",
author = "Sabri Boughorbel and Fons Bruekers and Jeroen Breebaart",
year = "2010",
doi = "10.1109/ICPR.2010.141",
language = "English",
isbn = "9780769541099",
pages = "556--559",
booktitle = "Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010",

}

TY - GEN

T1 - Baby-posture classification from pressure-sensor data

AU - Boughorbel, Sabri

AU - Bruekers, Fons

AU - Breebaart, Jeroen

PY - 2010

Y1 - 2010

N2 - The activity of babies and more specifically the posture of babies is an important aspect in their safety and development. In this paper, we studied the automatic classification of baby posture using a pressure-sensitive mat. The posture classification problem is formulated as the design of features that describe the pressure patterns induced by the child in combination with generic classifiers. Novel rotation invariant features constructed from high order statistics obtained from the concentric rings around the center of gravity. Non-constant ring radii are used in order to ensure uniform cell areas and therefore equal importance of features. A vote fusion of various generic classifiers is used for classification. Temporal information was shown to improve the classification performance. The obtained results are promising and open new opportunities for applications and further research in the area of baby safety and development.

AB - The activity of babies and more specifically the posture of babies is an important aspect in their safety and development. In this paper, we studied the automatic classification of baby posture using a pressure-sensitive mat. The posture classification problem is formulated as the design of features that describe the pressure patterns induced by the child in combination with generic classifiers. Novel rotation invariant features constructed from high order statistics obtained from the concentric rings around the center of gravity. Non-constant ring radii are used in order to ensure uniform cell areas and therefore equal importance of features. A vote fusion of various generic classifiers is used for classification. Temporal information was shown to improve the classification performance. The obtained results are promising and open new opportunities for applications and further research in the area of baby safety and development.

UR - http://www.scopus.com/inward/record.url?scp=78149473783&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78149473783&partnerID=8YFLogxK

U2 - 10.1109/ICPR.2010.141

DO - 10.1109/ICPR.2010.141

M3 - Conference contribution

SN - 9780769541099

SP - 556

EP - 559

BT - Proceedings - 2010 20th International Conference on Pattern Recognition, ICPR 2010

ER -