Automatic estimation of pose and falls in videos using computer vision model

Daniela Andrea Calvache Briceño; Hernán A. Bernal; Juan F. Guarín; Karen Aguía; Alvaro D. Orjuela-Cañón; Oscar J. Perdomo

doi:10.1117/12.2579615

Automatic estimation of pose and falls in videos using computer vision model

Daniela Andrea Calvache Briceño, Hernán A. Bernal, Juan F. Guarín, Karen Aguía, Alvaro D. Orjuela-Cañón, Oscar J. Perdomo

Producción científica: Capítulo en Libro/Reporte › Capítulo (revisado por pares) › revisión exhaustiva

4 Citas (Scopus)

Resumen

Human pose estimation is defined as the process of locating joints of a person or a crowd given an image or video. Currently, this estimation is widely used for the evaluation of athletes, workers, and the monitoring of patients in clinical settings. However, human pose estimation is not an easy task as it requires experts to manually assess the person’s position by using specialized equipment such as e-health devices (watches, bands, handles), markers, and high-cost cameras to monitor a limited scenario. The main goal of this article is to evaluate a marker-less low-cost computer vision system to get the automatic estimation of poses and fall detection on video by calculating the person’s joint angle with a high level of adaptability to any space. The proposed model is the first step in the construction of a tool that allows monitoring and generating alerts to prevent falls at home and clinical settings.

Idioma original	Inglés estadounidense
Título de la publicación alojada	16th International Symposium on Medical Information Processing and Analysis
Editores	Eduardo Romero, Natasha Lepore, Jorge Brieva, Marius Linguraru
Editorial	SPIE
ISBN (versión digital)	9781510639911
DOI	https://doi.org/10.1117/12.2579615
Estado	Publicada - nov. 3 2020
Evento	16th International Symposium on Medical Information Processing and Analysis 2020 - Lima, Virtual, Perú Duración: oct. 3 2020 → oct. 4 2020

Serie de la publicación

Nombre	Proceedings of SPIE - The International Society for Optical Engineering
Volumen	11583
ISSN (versión impresa)	0277-786X
ISSN (versión digital)	1996-756X

Conferencia

Conferencia	16th International Symposium on Medical Information Processing and Analysis 2020
País/Territorio	Perú
Ciudad	Lima, Virtual
Período	10/3/20 → 10/4/20

Áreas temáticas de ASJC Scopus

Materiales electrónicos, ópticos y magnéticos
Física de la materia condensada
Informática aplicada
Matemáticas aplicadas
Ingeniería eléctrica y electrónica

ODS de las Naciones Unidas

Este resultado contribuye a los siguientes Objetivos de Desarrollo Sostenible

Acceder al documento

10.1117/12.2579615

Otros archivos y enlaces

Citar esto

Calvache Briceño, D. A., Bernal, H. A., Guarín, J. F., Aguía, K., Orjuela-Cañón, A. D., & Perdomo, O. J. (2020). Automatic estimation of pose and falls in videos using computer vision model. En E. Romero, N. Lepore, J. Brieva, & M. Linguraru (Eds.), 16th International Symposium on Medical Information Processing and Analysis Artículo 115830W (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11583). SPIE. https://doi.org/10.1117/12.2579615

Calvache Briceño, Daniela Andrea ; Bernal, Hernán A. ; Guarín, Juan F. et al. / Automatic estimation of pose and falls in videos using computer vision model. 16th International Symposium on Medical Information Processing and Analysis. editor / Eduardo Romero ; Natasha Lepore ; Jorge Brieva ; Marius Linguraru. SPIE, 2020. (Proceedings of SPIE - The International Society for Optical Engineering).

@inbook{5f333e3a01ef450d84b53e48a249b289,

title = "Automatic estimation of pose and falls in videos using computer vision model",

abstract = "Human pose estimation is defined as the process of locating joints of a person or a crowd given an image or video. Currently, this estimation is widely used for the evaluation of athletes, workers, and the monitoring of patients in clinical settings. However, human pose estimation is not an easy task as it requires experts to manually assess the person{\textquoteright}s position by using specialized equipment such as e-health devices (watches, bands, handles), markers, and high-cost cameras to monitor a limited scenario. The main goal of this article is to evaluate a marker-less low-cost computer vision system to get the automatic estimation of poses and fall detection on video by calculating the person{\textquoteright}s joint angle with a high level of adaptability to any space. The proposed model is the first step in the construction of a tool that allows monitoring and generating alerts to prevent falls at home and clinical settings.",

author = "{Calvache Brice{\~n}o}, {Daniela Andrea} and Bernal, {Hern{\'a}n A.} and Guar{\'i}n, {Juan F.} and Karen Agu{\'i}a and Orjuela-Ca{\~n}{\'o}n, {Alvaro D.} and Perdomo, {Oscar J.}",

note = "Publisher Copyright: {\textcopyright} 2020 SPIE Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; 16th International Symposium on Medical Information Processing and Analysis 2020 ; Conference date: 03-10-2020 Through 04-10-2020",

year = "2020",

month = nov,

day = "3",

doi = "10.1117/12.2579615",

language = "English (US)",

series = "Proceedings of SPIE - The International Society for Optical Engineering",

publisher = "SPIE",

editor = "Eduardo Romero and Natasha Lepore and Jorge Brieva and Marius Linguraru",

booktitle = "16th International Symposium on Medical Information Processing and Analysis",

address = "United States",

}

Calvache Briceño, DA, Bernal, HA, Guarín, JF, Aguía, K , Orjuela-Cañón, AD & Perdomo, OJ 2020, Automatic estimation of pose and falls in videos using computer vision model. En E Romero, N Lepore, J Brieva & M Linguraru (eds.), 16th International Symposium on Medical Information Processing and Analysis., 115830W, Proceedings of SPIE - The International Society for Optical Engineering, vol. 11583, SPIE, 16th International Symposium on Medical Information Processing and Analysis 2020, Lima, Virtual, Perú, 10/3/20. https://doi.org/10.1117/12.2579615

Automatic estimation of pose and falls in videos using computer vision model. / Calvache Briceño, Daniela Andrea; Bernal, Hernán A.; Guarín, Juan F. et al.
16th International Symposium on Medical Information Processing and Analysis. ed. / Eduardo Romero; Natasha Lepore; Jorge Brieva; Marius Linguraru. SPIE, 2020. 115830W (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 11583).

Producción científica: Capítulo en Libro/Reporte › Capítulo (revisado por pares) › revisión exhaustiva

TY - CHAP

T1 - Automatic estimation of pose and falls in videos using computer vision model

AU - Calvache Briceño, Daniela Andrea

AU - Bernal, Hernán A.

AU - Guarín, Juan F.

AU - Aguía, Karen

AU - Orjuela-Cañón, Alvaro D.

AU - Perdomo, Oscar J.

PY - 2020/11/3

Y1 - 2020/11/3

N2 - Human pose estimation is defined as the process of locating joints of a person or a crowd given an image or video. Currently, this estimation is widely used for the evaluation of athletes, workers, and the monitoring of patients in clinical settings. However, human pose estimation is not an easy task as it requires experts to manually assess the person’s position by using specialized equipment such as e-health devices (watches, bands, handles), markers, and high-cost cameras to monitor a limited scenario. The main goal of this article is to evaluate a marker-less low-cost computer vision system to get the automatic estimation of poses and fall detection on video by calculating the person’s joint angle with a high level of adaptability to any space. The proposed model is the first step in the construction of a tool that allows monitoring and generating alerts to prevent falls at home and clinical settings.

AB - Human pose estimation is defined as the process of locating joints of a person or a crowd given an image or video. Currently, this estimation is widely used for the evaluation of athletes, workers, and the monitoring of patients in clinical settings. However, human pose estimation is not an easy task as it requires experts to manually assess the person’s position by using specialized equipment such as e-health devices (watches, bands, handles), markers, and high-cost cameras to monitor a limited scenario. The main goal of this article is to evaluate a marker-less low-cost computer vision system to get the automatic estimation of poses and fall detection on video by calculating the person’s joint angle with a high level of adaptability to any space. The proposed model is the first step in the construction of a tool that allows monitoring and generating alerts to prevent falls at home and clinical settings.

UR - http://www.scopus.com/inward/record.url?scp=85096833302&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85096833302&partnerID=8YFLogxK

U2 - 10.1117/12.2579615

DO - 10.1117/12.2579615

M3 - Chapter (peer-reviewed)

AN - SCOPUS:85096833302

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - 16th International Symposium on Medical Information Processing and Analysis

A2 - Romero, Eduardo

A2 - Lepore, Natasha

A2 - Brieva, Jorge

A2 - Linguraru, Marius

PB - SPIE

T2 - 16th International Symposium on Medical Information Processing and Analysis 2020

Y2 - 3 October 2020 through 4 October 2020

ER -

Calvache Briceño DA, Bernal HA, Guarín JF, Aguía K , Orjuela-Cañón AD, Perdomo OJ. Automatic estimation of pose and falls in videos using computer vision model. En Romero E, Lepore N, Brieva J, Linguraru M, editores, 16th International Symposium on Medical Information Processing and Analysis. SPIE. 2020. 115830W. (Proceedings of SPIE - The International Society for Optical Engineering). doi: 10.1117/12.2579615

Automatic estimation of pose and falls in videos using computer vision model

Resumen

Serie de la publicación

Conferencia

Áreas temáticas de ASJC Scopus

ODS de las Naciones Unidas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto