Stereo vision system for human motion analysis in a rehabilitation context

ABSTRACT

The present demographic trends point to an increase in aged population and chronic diseases which symptoms can be alleviated through rehabilitation. The applicability of passive 3D reconstruction for motion tracking in a rehabilitation context was explored using a stereo camera. The camera was used to acquire depth and color information from which the 3D position of predefined joints was recovered based on: kinematic relationships, anthropometrically feasible lengths and temporal consistency. Finally, a set of quantitative measures were extracted to evaluate the performed rehabilitation exercises. Validation study using data provided by a marker based as ground-truth revealed that our proposal achieved errors within the range of state-of-the-art active markerless systems and visual evaluations done by physical therapists. The obtained results are promising and demonstrate that the developed methodology allows the analysis of human motion for a rehabilitation purpose.

KEYWORDS:

• Rehabilitation
• stereo vision
• human motion tracking
• biomedical engineering

Acknowledgments

The first author would like to thank LABIOMEP for the availability in providing the location for the acquisition of the marker based software used in the collected dataset.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Notes on contributors

Teresa Azevedo Terroso

Teresa Azevedo TerrosoPh.D. in Computer Engineering, master in Biomedical Engineering and graduated in Electrical and Computer Engineering by FEUP (Faculdade de Engenharia da Universidade do Porto). Worked at Infineon Technologies, Portugal, and at CERN - Center Europeénne pour la Recherche Nucléaire, Geneva, Switzerland as Informatics Engineer and at ProjectBox, Portugal, in the Computer Vision department.She has been a college professor since 2008. She is currently an adjunct professor at ESMAD - Escola Superior de Media Artes e Design, IPP - Instituto Politécnico do Porto, Portugal. She is a researcher at INESC - TEC (Institute of Systems and Computer Engineering - Technology and Science) since 2004. Her research interests include Image/Video Processing and Computer Vision. Has several national and international journal, conference papers and a book published in the field of Computer Vision.

Luis Corte-Real

Luis Corte-Real was born in Vila do Conde, Portugal, in 1958. He received a degree in Electrical Engineering from the Faculdade de Engenharia, Universidade do Porto, Portugal, in 1981, the M.Sc. degree in Electrical and Computers Engineering in 1986 from Instituto Superior Técnico, Universidade Técnica de Lisboa, Lisbon, Portugal and the Ph.D. degree from the Faculdade de Engenharia, Universidade do Porto, in 1994.In 1984 he joined Universidade do Porto as a lecturer of telecommunications. He is currently an associate professor at the Departamento de Engenharia Eletrotécnica e de Computadores da Faculdade de Engenharia da Universidade do Porto. He is a researcher at the Institute for Systems and Computer Engineering, Technology and Science – INESC TEC since 1985. His research interests include image/video processing and coding.

Pedro Carvalho

Pedro Carvalho received the degree in electrical and computer engineering in 2001, the M.Sc. degree network and communication services in 2004 and the Ph.D. degree in electrical and computers engineering in 2012, from the Faculty of Engineering, University of Porto, Portugal. He joined INESC TEC in 2001 and is currently a senior researcher at the Center of Telecommunications and Multimedia. He has been an invited adjunct professor at the School of Engineering of the Polytechnic Institute of Porto, Porto, Portugal since 2014. His research interests include image/video processing and computer vision.