A computational method for physical rehabilitation assessment

Abstract

The 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.