Title: Real-Time Hand-Tracking with a Color Glove

Authors: Wang, RY & Popovic, J.

Link to Article: http://portal.acm.org/citation.cfm?id=1531326.1531369

(I know not everyone will be able to view the full article using the link, see other links below)

Abstract: Articulated hand-tracking systems have been widely used in virtual reality but are rarely deployed in consumer applications due to their price and complexity. In this paper, we propose an easy-to-use and inexpensive system that facilitates 3-D articulated user-input using the hands. Our approach uses a single camera to track a hand wearing an ordinary cloth glove that is imprinted with a custom pattern. The pattern is designed to simplify the pose estimation problem, allowing us to employ a nearest-neighbor approach to track hands at interactive rates. We describe several proof-of-concept applications enabled by our system that we hope will provide a foundation for new interactions in modeling, animation control and augmented reality.

Link to MIT news: http://web.mit.edu/newsoffice/2010/gesture-computing-0520.html

Link to website with videos: http://people.csail.mit.edu/rywang/hand/

For those of you interested in inexpensive ways to track the hand for rehabilitation purposes, look no further! The glove that these researchers have developed has tremendous potential for the rehab field. While the Wii and EyeToy are great at tracking larger body parts, there are few ways to track the hand as a controller for video/computer games. Especially in occupational therapy, clients with motor and sensory dysfunctions in the hand can play games with their own hand as the controller. The other neat thing about this glove is that the person can interact with either virtual or real-life objects. Keep your eyes and ears open for futher developments with this awesome glove!

Title: Effects of virtual reality training on gait biomechanics of individuals post-stroke

Authors: Mirelman A, Patritti BL, Bonato P, & Deutsch JE

PubMed link: http://www.ncbi.nlm.nih.gov/pubmed/20189810

PubMed ID: 20189810

Abstract: Objective: To evaluate gait biomechanics after training with a virtual reality (VR) system and to elucidate underlying mechanisms that contributed to the observed functional improvement in gait speed and distance. Design: A single blind randomized control study. Setting: Gait analysis laboratory in a rehabilitation hospital and the community. Participants: Fifteen men and three women with hemiparesis caused by stroke. Interventions: Subjects trained on a six-degree of freedom force-feedback robot interfaced with a VR simulation. Subjects were randomized to either a VR group (n = 9) or non-VR group (NVR, n = 9). Training was performed three times a week for 4 weeks for approximately 1 h each visit. Main outcome measures: Kinematic and kinetic gait parameters. Results: Subjects in the VR group demonstrated a significantly larger increase in ankle power generation at push-off as a result of training (p = 0.036). The VR group had greater change in ankle ROM posttraining (19.5%) as compared to the NVR group (3.3%). Significant differences were found in knee ROM on the affected side during stance and swing, with greater change in the VR group. No significant changes were observed in kinematics or kinetics of the hip post-training. Conclusions: These findings are encouraging because they support the potential for recovery of force and
power of the lower extremity for individuals with chronic hemiparesis. It is likely that the effects of training included improved motor control at the ankle, which enabled the cascade of changes that produced the functional improvements seen after training.

This article was interesting to me for two reasons. First, this research adds to the body of literature supporting the motivating characteristics of VR interfaces. In this study, both groups used the same device; however only one group used the device while playing a game with a VR interface. This group showed significant increases in gait biomechanics at the ankle. The second reason I found this article interesting was the device they used for ankle strength training. This robotic ankle is currently being tested in our lab for ankle strenghtening with children with cerebral palsy. I'm excited to see what population this device and the VR interface can help next.