We present results of our work on a method for tracking a 3D skeletal model of the human
body based on markerless observations acquired by a single RGBD camera. The proposed approach
has a number of attractive properties, such as:
It tracks a skeletal model of the human body (torso, arms, legs) plus the fingers of hands
It tolerates differences in biometrics, clothing, distance of observation, illumination variations
It handles occlusions (e.g., body occluded by objects, partial body views)
It performs automatic initialization / re-initialization, automatic recovery from tracking failures
It provides information on limbs depending on confidence
It operates with a potentially moving camera
It performs in real time (20-30 fps) on a conventional processor (single CPU, no GPGPU).
D. Michel and A.A. Argyros, "Apparatuses, methods and systems for recovering a 3-dimensional skeletal model of the human body", United States Patent No 20160086350, Filed: 22/09/2015, Published: 24/03/2016.
D. Michel, A. Qammaz and A.A. Argyros, "Markerless 3D human pose estimation and tracking based on RGBD cameras: an experimental evaluation", In International Conference on Pervasive Technologies Related to Assistive Environments (PETRA 2017) (to appear), ACM, Rhodes, Greece, June 2017.
P. Panteleris and A.A. Argyros, "Monitoring and interpreting human motion to support clinical applications of a smart walker", In Workshop on Human Motion Analysis for Healthcare Applications (HMAHA 2016), IET, London, UK, May 2016
M. Foukarakis, I. Adami, D. Ioannidi, A. Leonidis, D. Michel, A. Qammaz, K. Papoutsakis, M. Antona and A.A. Argyros, "A robot-based application for physical exercise training", In International Conference on Information and Communication Technologies for Ageing Well and e-Health (ICT4AWE 2016), Scitepress, pp. 45-52, Rome, Italy, April 2016.
The electronic versions of the above publications can be downloaded from my publications page.