In recent years, because cameras have become inexpensive and ever more prevalent, there has been increasing interest in video-based modeling of shape and motion. This has many potential applications in areas such as medicine, surveillance, entertainment, and athletic training. However, it is an inherently difficult task because the image-data is often incomplete, noisy, and ambiguous.
Amazingly, our brains are able to make sense of this data apparently effortlessly. Our ultimate goal is therefore to emulate this ability to detect objects and interpret images.
More specifically, one important focus of our research is the recovery of deformable and articulated 3D motion from single video sequences. We are also active in the areas of multi-camera surveillance, augmented reality, and medical image processing. Furthermore, we provide undergraduate and graduate teaching and transfer technology to both established and start up companies.