Sit-to-Stand Analysis in the Wild using Silhouettes for Longitudinal Health Monitoring

Alessandro Masullo; Tilo Burghardt; Toby Perrett; Dima Aldamen; Majid Mirmehdi

doi:10.1007/978-3-030-27272-2_15

Sit-to-Stand Analysis in the Wild using Silhouettes for Longitudinal Health Monitoring

Alessandro Masullo, Tilo Burghardt, Toby Perrett, Dima Aldamen, Majid Mirmehdi

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

4 Citations (Scopus)

Abstract

We present the first fully automated Sit-to-Stand or Stand-to-Sit (StS) analysis framework for long-term monitoring of patients in free-living environments using video silhouettes. Our method adopts a coarse-to-fine time localisation approach, where a deep learning classifier identifies possible StS sequences from silhouettes, and a smart peak detection stage provides fine localisation based on 3D bounding boxes. We tested our method on data from real homes of participants and monitored patients undergoing total hip or knee replacement. Our results show 94.4% overall accuracy in the coarse localisation and an error of 0.026 m/s in the speed of ascent measurement, highlighting important trends in the recuperation of patients who underwent surgery.

Original language	English
DOIs	https://doi.org/10.1007/978-3-030-27272-2_15
Publication status	Published - 3 Aug 2019
Event	16th International Conference on Image Analysis and Recognition - Waterloo, Canada Duration: 27 Aug 2019 → 29 Aug 2019 Conference number: 16 http://www.aimiconf.org/iciar19/

Conference

Conference	16th International Conference on Image Analysis and Recognition
Abbreviated title	ICIAR
Period	27/08/19 → 29/08/19
Internet address	http://www.aimiconf.org/iciar19/

Research Groups and Themes

Digital Health
SPHERE

Access to Document

10.1007/978-3-030-27272-2_15

Handle.net

Persistent link

SPHERE2
Craddock, I. J. (Principal Investigator), Mirmehdi, M. (Co-Investigator), Piechocki, R. J. (Co-Investigator), Flach, P. A. (Co-Investigator), Oikonomou, G. (Co-Investigator), Burghardt, T. (Co-Investigator), Damen, D. (Co-Investigator), Santos-Rodriguez, R. (Co-Investigator), O'Kane, A. A. (Co-Investigator), McConville, R. (Co-Investigator), Masullo, A. (Co-Investigator) & Gooberman-Hill, R. (Co-Investigator)
1/10/18 → 31/01/23
Project: Research, Parent

Professor Majid Mirmehdi
- m.mirmehdibristol.acuk
- School of Computer Science - Professor of Computer Vision/Engineering Faculty Education Director
- Visual Information Laboratory
- Bristol Vision Institute
Person: Academic , Member

Cite this

@conference{030af4bcf7cb4fd196170e59f496d6ac,

title = "Sit-to-Stand Analysis in the Wild using Silhouettes for Longitudinal Health Monitoring",

abstract = "We present the first fully automated Sit-to-Stand or Stand-to-Sit (StS) analysis framework for long-term monitoring of patients in free-living environments using video silhouettes. Our method adopts a coarse-to-fine time localisation approach, where a deep learning classifier identifies possible StS sequences from silhouettes, and a smart peak detection stage provides fine localisation based on 3D bounding boxes. We tested our method on data from real homes of participants and monitored patients undergoing total hip or knee replacement. Our results show 94.4% overall accuracy in the coarse localisation and an error of 0.026 m/s in the speed of ascent measurement, highlighting important trends in the recuperation of patients who underwent surgery.",

author = "Alessandro Masullo and Tilo Burghardt and Toby Perrett and Dima Aldamen and Majid Mirmehdi",

year = "2019",

month = aug,

day = "3",

doi = "10.1007/978-3-030-27272-2_15",

language = "English",

note = "16th International Conference on<br/>Image Analysis and Recognition, ICIAR ; Conference date: 27-08-2019 Through 29-08-2019",

url = "http://www.aimiconf.org/iciar19/",

}

TY - CONF

T1 - Sit-to-Stand Analysis in the Wild using Silhouettes for Longitudinal Health Monitoring

AU - Masullo, Alessandro

AU - Burghardt, Tilo

AU - Perrett, Toby

AU - Aldamen, Dima

AU - Mirmehdi, Majid

N1 - Conference code: 16

PY - 2019/8/3

Y1 - 2019/8/3

N2 - We present the first fully automated Sit-to-Stand or Stand-to-Sit (StS) analysis framework for long-term monitoring of patients in free-living environments using video silhouettes. Our method adopts a coarse-to-fine time localisation approach, where a deep learning classifier identifies possible StS sequences from silhouettes, and a smart peak detection stage provides fine localisation based on 3D bounding boxes. We tested our method on data from real homes of participants and monitored patients undergoing total hip or knee replacement. Our results show 94.4% overall accuracy in the coarse localisation and an error of 0.026 m/s in the speed of ascent measurement, highlighting important trends in the recuperation of patients who underwent surgery.

AB - We present the first fully automated Sit-to-Stand or Stand-to-Sit (StS) analysis framework for long-term monitoring of patients in free-living environments using video silhouettes. Our method adopts a coarse-to-fine time localisation approach, where a deep learning classifier identifies possible StS sequences from silhouettes, and a smart peak detection stage provides fine localisation based on 3D bounding boxes. We tested our method on data from real homes of participants and monitored patients undergoing total hip or knee replacement. Our results show 94.4% overall accuracy in the coarse localisation and an error of 0.026 m/s in the speed of ascent measurement, highlighting important trends in the recuperation of patients who underwent surgery.

U2 - 10.1007/978-3-030-27272-2_15

DO - 10.1007/978-3-030-27272-2_15

M3 - Conference Paper

T2 - 16th International Conference on<br/>Image Analysis and Recognition

Y2 - 27 August 2019 through 29 August 2019

ER -

Sit-to-Stand Analysis in the Wild using Silhouettes for Longitudinal Health Monitoring

Abstract

Conference

Research Groups and Themes

Access to Document

Handle.net

Fingerprint

Projects

SPHERE2

Profiles

Professor Majid Mirmehdi

Cite this