KMDI Seminar – Semantics-enabled 3D Selection via Freehand Gestures

Semantics-enabled 3D Selection via Freehand Gestures

Guest speaker: Professor Huagen Wan, Zhejiang University

Abstract

Human-computer interfaces need more natural and intuitive communication between people and devices. In this talk, I will present Lasso3D, a complementary 3D object selection technique by matching the shape semantics of the object calculated in real time with the outline of the freehand gesture to facilitate accurate, natural and intuitive object selection. We conducted four experiments to compare the accuracy and time performance of Lasso3D with both standard and progressive refinement ray-casting. Results indicated that Lasso3D is effective, learnable and engaging in selecting 3D virtual objects with high accuracy. We also evaluated Lasso3D for object selection in realistic 3D environment, and the results showed that Lasso3D can be practically used in real world scenarios.

About the speaker

Huagen Wan is currently an associate professor with the State Key Lab of CAD&CG, Zhejiang University. He is also a vice director of the Virtual Reality Committee, China Society of Image and Graphics (CSIG). He got his bachelor, master and Ph.D. degrees in 1990, 1993, and 1999 respectively, all from the Department of Applied Mathematics, Zhejiang University. His research interests include human computer interaction, virtual reality continuum and their applications in industries. He has published more than 50 academic papers in peer-reviewed conferences and journals.