Advanced search
1 file | 278.46 KB Add to list

Behavior analysis for aging-in-place using similarity heatmaps

Mohamed Eldib, Bo Bo Nyan (UGent) , Francis Deboeverie (UGent) , Xingzhe Xie (UGent) , Hamid Aghajan (UGent) and Wilfried Philips (UGent)
Author
Organization
Abstract
The demand for healthcare services for an increasing population of older adults is faced with the shortage of skilled caregivers and a constant increase in healthcare costs. In addition, the strong preference of the elderly to live independently has been driving much research on "ambient-assisted living" (AAL) systems to support aging-in-place. In this paper, we propose to employ a low-resolution image sensor network for behavior analysis of a home occupant. A network of 10 low-resolution cameras (30x30 pixels) is installed in a service flat of an elderly, based on which the user's mobility tracks are extracted using a maximum likelihood tracker. We propose a novel measure to find similar patterns of behavior between each pair of days from the user's detected positions, based on heatmaps and Earth mover's distance (EMD). Then, we use an exemplar-based approach to identify sleeping, eating, and sitting activities, and walking patterns of the elderly user for two weeks of real-life recordings. The proposed system achieves an overall accuracy of about 94%.
Keywords
Low-Resolution Cameras, Behaviour Analysis, Aging-in-Place

Downloads

  • sigproc-sp-v5.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 278.46 KB

Citation

Please use this url to cite or link to this publication:

MLA
Eldib, Mohamed, et al. “Behavior Analysis for Aging-in-Place Using Similarity Heatmaps.” 8th ACM/IEEE International Conference on Distributed Smart Cameras, Proceedings, ACM/IEEE, 2014, p. 34:1-34:6, doi:10.1145/2659021.2659038.
APA
Eldib, M., Nyan, B. B., Deboeverie, F., Xie, X., Aghajan, H., & Philips, W. (2014). Behavior analysis for aging-in-place using similarity heatmaps. 8th ACM/IEEE International Conference on Distributed Smart Cameras, Proceedings, 34:1-34:6. https://doi.org/10.1145/2659021.2659038
Chicago author-date
Eldib, Mohamed, Bo Bo Nyan, Francis Deboeverie, Xingzhe Xie, Hamid Aghajan, and Wilfried Philips. 2014. “Behavior Analysis for Aging-in-Place Using Similarity Heatmaps.” In 8th ACM/IEEE International Conference on Distributed Smart Cameras, Proceedings, 34:1-34:6. New York, NY, USA: ACM/IEEE. https://doi.org/10.1145/2659021.2659038.
Chicago author-date (all authors)
Eldib, Mohamed, Bo Bo Nyan, Francis Deboeverie, Xingzhe Xie, Hamid Aghajan, and Wilfried Philips. 2014. “Behavior Analysis for Aging-in-Place Using Similarity Heatmaps.” In 8th ACM/IEEE International Conference on Distributed Smart Cameras, Proceedings, 34:1-34:6. New York, NY, USA: ACM/IEEE. doi:10.1145/2659021.2659038.
Vancouver
1.
Eldib M, Nyan BB, Deboeverie F, Xie X, Aghajan H, Philips W. Behavior analysis for aging-in-place using similarity heatmaps. In: 8th ACM/IEEE international conference on Distributed Smart Cameras, Proceedings. New York, NY, USA: ACM/IEEE; 2014. p. 34:1-34:6.
IEEE
[1]
M. Eldib, B. B. Nyan, F. Deboeverie, X. Xie, H. Aghajan, and W. Philips, “Behavior analysis for aging-in-place using similarity heatmaps,” in 8th ACM/IEEE international conference on Distributed Smart Cameras, Proceedings, Venezia Mestre, Italy, 2014, p. 34:1-34:6.
@inproceedings{5671229,
  abstract     = {{The demand for healthcare services for an increasing population of older adults is faced with the shortage of skilled caregivers and a constant increase in healthcare costs. In addition, the strong preference of the elderly to live independently has been driving much research on "ambient-assisted living" (AAL) systems to support aging-in-place. In this paper, we propose to employ a low-resolution image sensor network for behavior analysis of a home occupant. A network of 10 low-resolution cameras (30x30 pixels) is installed in a service flat of an elderly, based on which the user's mobility tracks are extracted using a maximum likelihood tracker. We propose a novel measure to find similar patterns of behavior between each pair of days from the user's detected positions, based on heatmaps and Earth mover's distance (EMD). Then, we use an exemplar-based approach to identify sleeping, eating, and sitting activities, and walking patterns of the elderly user for two weeks of real-life recordings. The proposed system achieves an overall accuracy of about 94%.}},
  articleno    = {{34}},
  author       = {{Eldib, Mohamed and Nyan, Bo Bo and Deboeverie, Francis and Xie, Xingzhe and Aghajan, Hamid and Philips, Wilfried}},
  booktitle    = {{8th ACM/IEEE international conference on Distributed Smart Cameras, Proceedings}},
  isbn         = {{978-1-4503-2925-5}},
  keywords     = {{Low-Resolution Cameras,Behaviour Analysis,Aging-in-Place}},
  language     = {{eng}},
  location     = {{Venezia Mestre, Italy}},
  pages        = {{34:34:1--34:34:6}},
  publisher    = {{ACM/IEEE}},
  title        = {{Behavior analysis for aging-in-place using similarity heatmaps}},
  url          = {{http://doi.org/10.1145/2659021.2659038}},
  year         = {{2014}},
}

Altmetric
View in Altmetric