Markerless Motion Capture
Prof. Rama Chellappa
|Dr. Rama Chellappa
Markerless motion capture is the activity of analyzing and expressing human motion in mathematical terms. Prof. Rama Chellappa and his fellow researchers model the human body as a set of super-quadrics, or three-dimensional objects, that are connected in an articulated structure, and propose algorithms to estimate the parameters of the model from video sequences. This model marks an advancement from previous human motion capture methods, which use passive markers that are attached to different body parts of the subject and are therefore intrusive in nature.
This technology has important applications in biomechanics, computer animation, and human-computer interaction. Specifically, the researchers' software can be used in homeland security initiatives, sports instruction, such as improving one's golf swing, motion picture animation and simulation, and patient rehabilitation.
The researchers' ultimate objective is to build a completely automated markerless motion capture system. This technology is currently licensed in the field of sports. A U.S. patent application is pending.
Prof. Chellappa and ECE Ph.D. graduate Aravind Sundaresan won the University of Maryland Invention of the Year Award in the Information Science category for their "Markerless Motion Capture" invention. The award was presented at the University's 20th annual Invention of the Year Awards, sponsored by the Office of Technology Commercialization.
For more information, please visit:
return to spotlight on research