K
Kong-Man (German) Cheung
Researcher at Carnegie Mellon University
Publications - 7
Citations - 810
Kong-Man (German) Cheung is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Silhouette & Visual hull. The author has an hindex of 6, co-authored 7 publications receiving 786 citations. Previous affiliations of Kong-Man (German) Cheung include University of Hong Kong.
Papers
More filters
Proceedings ArticleDOI
Shape-from-silhouette of articulated objects and its use for human body kinematics estimation and motion capture
TL;DR: An iterative algorithm is proposed to solve this simultaneous assignment and alignment problem of the shape and motion of a rigidly moving object over time to apply to dynamic articulated objects.
Journal ArticleDOI
Shape-From-Silhouette Across Time Part II: Applications to Human Modeling and Markerless Motion Tracking
TL;DR: This paper builds a system to acquire human kinematic models consisting of precise shape, joint locations, and body part segmentation and shows how they can be used to track the motion of the person in new video sequences.
Journal ArticleDOI
Shape-From-Silhouette Across Time Part I: Theory and Algorithms
TL;DR: A theory of performing SFS across time: estimating the shape of a dynamic object (with unknown motion) by combining all of the silhouette images of the object over time is developed.
Visual hull construction, alignment and refinement for human kinematic modeling, motion tracking and rendering
TL;DR: This thesis proposes a fast testing/projection algorithm for voxel-based SFS algorithms and develops an algorithm to align Visual Hulls over time using stereo and an important property of the Shape-From-Silhouette principle.
Proceedings ArticleDOI
Blind deconvolution of system with unknown response excited by cyclostationary impulses
TL;DR: This method generalizes Bresler's (1989) idea of resolving overlapping echoes by partitioning the signals into portions which fit the mathematical formulation used by B Resler.