CNN-SkelPose: a CNN-based skeleton estimation algorithm for clinical applications

Luis Zavala Mondragon, B. Lamichhane (Corresponding author), Lu Zhang, Gerard de Haan

Research output: Contribution to journalArticleAcademicpeer-review

1 Citation (Scopus)

Abstract

Computer vision based patient activity monitoring systems can be attractive for various unobtrusive clinical applications. Such a monitoring system can be developed using movement information derived from the skeleton model of the current body pose, e.g. obtained using a depth camera. Earlier research using estimated skeleton models have been focused mostly on gaming applications. In this paper, we propose CNN-SkelPose as a skeleton model estimation method for clinical applications. CNN-SkelPose uses a trained Convolutional Neural Network to extract both the local and global information from the depth image. CNN-SkelPose outperforms the baseline model of Skeltrack for reliable skeleton model estimation in patient monitoring scenarios. Our results show the inadequacy of existing methods for skeleton model estimation when applied to a clinical scenario and suggests CNN-SkelPose as an improvement towards this application.
Original languageEnglish
Number of pages12
JournalJournal of Ambient Intelligence and Humanized Computing
DOIs
Publication statusPublished - 28 Feb 2019

Fingerprint

Patient monitoring
Monitoring
Computer vision
Cameras
Neural networks

Keywords

  • Actigraphy
  • CNN
  • Clinical application
  • Skeleton model

Cite this

@article{778767576e9c4919add0580e020a021f,
title = "CNN-SkelPose: a CNN-based skeleton estimation algorithm for clinical applications",
abstract = "Computer vision based patient activity monitoring systems can be attractive for various unobtrusive clinical applications. Such a monitoring system can be developed using movement information derived from the skeleton model of the current body pose, e.g. obtained using a depth camera. Earlier research using estimated skeleton models have been focused mostly on gaming applications. In this paper, we propose CNN-SkelPose as a skeleton model estimation method for clinical applications. CNN-SkelPose uses a trained Convolutional Neural Network to extract both the local and global information from the depth image. CNN-SkelPose outperforms the baseline model of Skeltrack for reliable skeleton model estimation in patient monitoring scenarios. Our results show the inadequacy of existing methods for skeleton model estimation when applied to a clinical scenario and suggests CNN-SkelPose as an improvement towards this application.",
keywords = "Actigraphy, CNN, Clinical application, Skeleton model",
author = "{Zavala Mondragon}, Luis and B. Lamichhane and Lu Zhang and {de Haan}, Gerard",
year = "2019",
month = "2",
day = "28",
doi = "10.1007/s12652-019-01259-5",
language = "English",
journal = "Journal of Ambient Intelligence and Humanized Computing",
issn = "1868-5137",
publisher = "Springer",

}

CNN-SkelPose : a CNN-based skeleton estimation algorithm for clinical applications. / Zavala Mondragon, Luis; Lamichhane, B. (Corresponding author); Zhang, Lu; de Haan, Gerard.

In: Journal of Ambient Intelligence and Humanized Computing, 28.02.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - CNN-SkelPose

T2 - a CNN-based skeleton estimation algorithm for clinical applications

AU - Zavala Mondragon, Luis

AU - Lamichhane, B.

AU - Zhang, Lu

AU - de Haan, Gerard

PY - 2019/2/28

Y1 - 2019/2/28

N2 - Computer vision based patient activity monitoring systems can be attractive for various unobtrusive clinical applications. Such a monitoring system can be developed using movement information derived from the skeleton model of the current body pose, e.g. obtained using a depth camera. Earlier research using estimated skeleton models have been focused mostly on gaming applications. In this paper, we propose CNN-SkelPose as a skeleton model estimation method for clinical applications. CNN-SkelPose uses a trained Convolutional Neural Network to extract both the local and global information from the depth image. CNN-SkelPose outperforms the baseline model of Skeltrack for reliable skeleton model estimation in patient monitoring scenarios. Our results show the inadequacy of existing methods for skeleton model estimation when applied to a clinical scenario and suggests CNN-SkelPose as an improvement towards this application.

AB - Computer vision based patient activity monitoring systems can be attractive for various unobtrusive clinical applications. Such a monitoring system can be developed using movement information derived from the skeleton model of the current body pose, e.g. obtained using a depth camera. Earlier research using estimated skeleton models have been focused mostly on gaming applications. In this paper, we propose CNN-SkelPose as a skeleton model estimation method for clinical applications. CNN-SkelPose uses a trained Convolutional Neural Network to extract both the local and global information from the depth image. CNN-SkelPose outperforms the baseline model of Skeltrack for reliable skeleton model estimation in patient monitoring scenarios. Our results show the inadequacy of existing methods for skeleton model estimation when applied to a clinical scenario and suggests CNN-SkelPose as an improvement towards this application.

KW - Actigraphy

KW - CNN

KW - Clinical application

KW - Skeleton model

UR - http://www.scopus.com/inward/record.url?scp=85062636137&partnerID=8YFLogxK

U2 - 10.1007/s12652-019-01259-5

DO - 10.1007/s12652-019-01259-5

M3 - Article

JO - Journal of Ambient Intelligence and Humanized Computing

JF - Journal of Ambient Intelligence and Humanized Computing

SN - 1868-5137

ER -