Body posture estimation in an embedded system Raspberry Pi using computer vision techniques

Authors

DOI:

https://doi.org/10.35290/ro.v2n1.2021.380

Keywords:

binarization, images, numpy, OpenCV, Raspberry Pi

Abstract

Systems that are used for motion capture or known as gait analysis generally employ dedicated devices that are sold on the market at high prices. In recent years, companies focused on manufacturing and implementing gait laboratories have focused their efforts on creating measurement and reporting devices that are portable and take up a minimum of space; however, technological innovations proposed by companies dedicated to the field of biomedicine turn out to be closed and with compatibility limitations. That is to say, in cases where the expansion of the laboratory is required, it is necessary to acquire equipment of the same brand, which implies high costs. In view of this problem, the use of Raspberry Pi embedded systems is proposed, which, through artificial vision techniques and libraries, establish a running analysis with precision and higher performance as it is an open source system. Likewise, through artificial vision techniques, a binary image can be captured and processed. The use of OpenCV libraries to locate markers and delimit a region of interest consolidate a compact and portable system to capture body movement in real time, and in unrestricted spaces.

Downloads

Download data is not yet available.

References

Arenas-Ortiz, L., & Cantú-Gómez, Ó. (2013). Factores de riesgo de trastornos músculo-esqueléticos crónicos laborales. Medicina Interna de México, 370-379.

Coloma Coloma, M. A. (2019). Trastornos musculoesqueléticos de posible origen laboral asociado a posturas forzadas en el personal operativo de limpieza del Ministerio de Agricultura y Ganadería del Ecuador–Quito. Facultad de Ciencias del Trabajo y Comportamiento Humano, 1(1), 1-6.

Comisión Nacional de Seguridad y Salud en el Trabajo. (2008). Enfermedades Profesionales de los Agricultores. Grupo de Trabajo "Sector Agrario", 1(1), 1-36.

D.A. Bravo M, C. R. (2016). Comparación de dos Sistemas de Captura de Movimiento por medio de las Trayectorias Articulares de Marcha. Revista Mexicana de Ingeniería Biomédica, 37(2), 149-160.

Faisal, A. I., Majumder, S., Mondal, T., Cowan, D., Naseh, S., & Deen, M. J. (2019). Monitoring methods of human body joints: State-of-the-art and research challenges. Sensors, 19(11), 2629. https://doi.org/10.3390/s19112629

Guerrero Aguirre, A., & Ramos Giraldo, P. J. (2014). Sistema embebido de bajo costo para visión artificial. Scientia et Technica Año XIX, 163-173.

Luttmann, A., Jager, M., Griefahn, B., & Caffer, G. (2004). Prevención de Trastornos muscoloesqueleticos en el lugar de trabajo. Berlín: Serie protección de salud de los trabajadores.

Organización Mundial de la Salud. (9 de Agosto de 2019). Trastornos musculoesqueléticos. Recuperado el 22 de Junio de 2020, de https://www.who.int/es/news-room/fact-sheets/detail/musculoskeletal-conditions

Pérez, M., Cavanzo Nisso, G. A., & Villavisán Buitrago, F. (2018). Sistema embebido de detección de movimiento mediante visión artificial. Visión Eléctróncia, 97-101. https://doi.org/10.14483/22484728.15087

Raju J.B.V.P., Reddy Y.C., G P.R. (2020) Smart Posture Detection and Correction System Using Skeletal Points Extraction. In: Satapathy S.C., Raju K.S., Shyamala K., Krishna D.R., Favorskaya M.N. (eds) Advances in Decision Sciences, Image Processing, Security and Computer Vision. Learning and Analytics in Intelligent Systems, vol 3. Springer, Cham. https://doi.org/10.1007/978-3-030-24322-7_23

Sandoval, S. (2017). Trastornos musculoesqueléticos de origen laboral en el cuello y las extremidades superiores de los fisioterapeutas en Cataluña. Cataluña: Universitat de Lleida.

Shilpashree, K. S., Lokesha, H., & Shivkumar, H. (2015). Implementation of image processing on Raspberry Pi. International Journal of Advanced Research in Computer and Communication Engineering, 4(5), 199-202. https://doi.org/10.17148/IJARCCE.2015.4545

Vergara, T. A., & Dixon, C. S. G. (2005). Sistema de reconocimiento de posturas del cuerpo humano. Pontificia Universidad Javeriana., 1 (1), 1-6.

Published

2021-02-10

How to Cite

Vargas Guevara, C. L. ., Guevara Aulestia, D. O. ., Ciaccia , M. A. ., & San Antonio, T. . (2021). Body posture estimation in an embedded system Raspberry Pi using computer vision techniques. ODIGOS JOURNAL, 2(1), 9–20. https://doi.org/10.35290/ro.v2n1.2021.380