HMM and DTW for evaluation of therapeutical gestures using kinect
This addresses the challenge of evaluating therapeutic gestures for patients and therapists, but it is incremental as it applies existing methods (HMM and DTW) to a new domain with Kinect data.
The paper tackled the problem of automatically recognizing movement quality in physical therapy by detecting deviations from correct forms using Hidden Markov Models (HMM) and compared it to Dynamic Time Warping (DTW). The result showed that HMM-based systems are much more likely to detect deviations effectively.
Automatic recognition of the quality of movement in human beings is a challenging task, given the difficulty both in defining the constraints that make a movement correct, and the difficulty in using noisy data to determine if these constraints were satisfied. This paper presents a method for the detection of deviations from the correct form in movements from physical therapy routines based on Hidden Markov Models, which is compared to Dynamic Time Warping. The activities studied include upper an lower limbs movements, the data used comes from a Kinect sensor. Correct repetitions of the activities of interest were recorded, as well as deviations from these correct forms. The ability of the proposed approach to detect these deviations was studied. Results show that a system based on HMM is much more likely to determine if a certain movement has deviated from the specification.