A computational method for physical rehabilitation assessment

©2010 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.Presented at the 3rd IEEE RAS and EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob), 26-29 September 2010, Tokyo, Japan.DOI: 10.1109/BIOROB.2010.5626047The objective of this research effort is to advance the process of quantifying physical rehabilitation techniques by developing and validating the core technologies needed to integrate therapy instruction with human-robot interaction in order to improve upper-arm rehabilitation. The method presented uses computer vision techniques such as Motion History Imaging (MHI), edge detection, and Random Sample Consensus (RANSAC) to quantify movements through robot observation. The results are compared with ground truth data retrieved via the Trimble 5606 Robotic Total Station for the purpose of assessing the efficiency of this approach