Accurate 2D to 3D overlay

The project will investigate image-based 3D reconstruction to infer the 3D geometry and structure of human body and scenes from multiple 2D images.
Effective solutions typically require multiple images, captured using accurately calibrated cameras. Stereo-based technique – Multiple View Geometry, for example, require matching features across images captured from slightly different viewing angles, and then use the triangulation principle to recover the 3D coordinates of the image pixels. Shape-from-silhouette, or shape by-space-carving, methods such as The Visual Hull Concept require accurately segmented 2D silhouettes. These methods, which have led to reasonable quality 3D reconstructions, require multiple images of the same object captured by well calibrated cameras
This research will benefit the partner organization by being useful to many applications such as robot navigation, object recognition and scene understanding, 3D modeling and animation, industrial control, and medical diagnosis.

Faculty Supervisor:

Svetlana Yanushkevich

Student:

Partner:

H3alth Technologies

Discipline:

Engineering

Sector:

Professional, scientific and technical services

University:

University of Calgary

Program: