Publications

Wei Xu and Jane Mulligan. Performance evaluation of color correction approaches for automatic multiview image and video stitching. In Intl. Conf on Computer Vision and Pattern Recognition (CVPR10), San Francisco, CA, 2010.

Wei Xu, Jaeheon Jeong, and Jane Mulligan. Augmenting exercise systems with virtual exercise environment. In 5th International Symposium on Visual Computing (ISVC09), Las Vegas, NV, Nov. 2009.

Wei Xu and Jane Mulligan. Feature matching under region-based constraints for robust epipolar geometry estimation. In 5th International Symposium on Visual Computing (ISVC09), Las Vegas, NV, Nov. 2009. [pdf]

Wei Xu and Jane Mulligan, Robust relative pose estimation with integrated cheirality constraint, In Proc. 19th Intl. Conf on Pattern. Recognition , Dec. 2008.

Technical Report CU-CS-1013-06. Wei Xu, John Penners, Jane Mulligan, "Recording Real Worlds for Playback in a Virtual Exercise Environment". (pdf)


 

Virtual Exercise Environments

People

Jane Mulligan
Wei Xu
Jaeheon Jeong

Wei Xu and Jaeheon Jeong at RESNA 07

Abstract

RecTech is a NIDRR Rehabilitation Engineering Research Center for Recreational Technologies and Exercise Physiology (RecTech) based at the University of Illinois at Chicago.

In the IA Lab we work on the development project:
D1: Use of Virtual Exercise Environments for People with Disabilities

Virtual Reality technology can create compelling augmentations for cardiovascular exercise equipment such as treadmills, stationary bikes, or arm ergometers, which can engage users and increase enjoyment and participation in regular exercise programs. The overall goal of this project is to create more motivational, visually-stimulating virtual exercise environments (VEEs) that will promote greater adherence to exercise among people with disabilities. Currently the prototype VEE consists of a recording system to capture video as well as distance and incline data about real trails, and a playback system which "displays" both video and terrain data in the form of video speed and machine resistance.

The VEE trail capture system requires methods for acquiring both multiple video streams and physical measurements of tilt and distance. We have completed our revision of the system developing a new rig using 3 HD camcorders and a handheld GPS unit. The new system blends 3 1920x1080 views into a 140 deg. horizontal field of view panorama (below) for display on one or more large format screens.

UC Boulder Campus

Large Format VEE display at RecTech SoS, Oct 2010, Arlignton, VA

See our latest YouTUBE video

Under construction VEE Repository

 
 
Home | People | Projects | Publications | Contact