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

Thumbnail Image
Files

Files

Automatic estimation of pose and falls in videos using computer vision model (1).pdf (4.92 MB)
View Statistics
Reference Managers
Mendeley
Indexers
Google Scholar CORE
QR Code
QR Code
Authors

Authors

Calvache, Daniela
Bernal, Hernán
Guarín, Juan F.
Aguía, Karen
Orjuela Cañón, Álvaro D.
Perdomo, Oscar J.
Abstract (Spanish)
La estimación de la pose humana se define como el proceso de localizar las articulaciones de una persona o una multitud a partir de una imagen o un vídeo. Actualmente, esta estimación es muy utilizada para la evaluación de deportistas, trabajadores y el seguimiento de pacientes. en entornos clínicos. Sin embargo, la estimación de la pose humana no es una tarea fácil ya que requiere que los expertos realicen manualmente evaluar la posición de la persona mediante el uso de equipos especializados, como dispositivos de salud electrónica (relojes, pulseras, manijas), marcadores y cámaras de alto costo para monitorear un escenario limitado. El objetivo principal de este artículo es evaluar una Sistema de visión por computadora de bajo costo y sin marcadores para obtener la estimación automática de posturas y detección de caídas en video. calculando el ángulo articular de la persona con un alto nivel de adaptabilidad a cualquier espacio. El modelo propuesto es el primer paso en la construcción de una herramienta que permita monitorear y generar alertas para prevenir caídas en el hogar y entornos clínicos.
Abstract (English)
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.
Extent
9 páginas
URI: https://repositorio.escuelaing.edu.co/handle/001/3292
Collections

Collections

AA. Gibiome
References

Toshev, A. and Szegedy, C., “Deeppose: Human pose estimation via deep neural networks,” in [Proceedings of the IEEE conference on computer vision and pattern recognition], 1653–1660 (2014).

L´opez-Quintero, M. I., “Estimaci´on de la pose humana 2d en im´agenes est´ereo,” (2016).

Leitch, J., Stebbins, J., Paolini, G., and Zavatsky, A. B., “Identifying gait events without a force plate during running: A comparison of methods,” Gait & Posture 33(1), 130–132 (2011).

Davis, R. B., “Clinical gait analysis,” IEEE Engineering in Medicine and Biology Magazine 7(3), 35–40 (1988).

Li, X., Fan, Z., Liu, Y., Li, Y., and Dai, Q., “3d pose detection of closely interactive humans using multi-view cameras,” Sensors 19(12), 2831 (2019).

Wang, C., Wang, Y., and Yuille, A. L., “An approach to pose-based action recognition,” in [Proceedings of the IEEE conference on computer vision and pattern recognition], 915–922 (2013).

Hidalgo, G. et al., “Openpose: Real-time multi-person keypoint detection library for body, face, and hands estimation,” Retrieved April (2018).

Liu, J., Gu, Y., and Kamijo, S., “Customer pose estimation using orientational spatio-temporal network from surveillance camera,” Multimedia Systems 24, 1–19 (11 2017).

Buzzelli, M., Alb´e, A., and Ciocca, G., “A vision-based system for monitoring elderly people at home,” Applied Sciences 10(1), 374 (2020)

Sebestyen, G., Stoica, I., and Hangan, A., “Human activity recognition and monitoring for elderly people,” in [2016 IEEE 12th international conference on intelligent computer communication and processing (ICCP) ], 341–347, IEEE (2016).

Hall, A., Wilson, C. B., Stanmore, E., and Todd, C., “Implementing monitoring technologies in care homes for people with dementia: a qualitative exploration using normalization process theory,” International journal of nursing studies 72, 60–70 (2017).

Andriluka, M., Pishchulin, L., Gehler, P., and Schiele, B., “2d human pose estimation: New benchmark and state of the art analysis,” in [Proceedings of the IEEE Conference on computer Vision and Pattern Recognition], 3686–3693 (2014).

Cao, Z., Simon, T., Wei, S.-E., and Sheikh, Y., “Realtime multi-person 2d pose estimation using part affinity fields,” in [Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition], 7291–7299 (2017).