C
Charles Claudius Marais
Researcher at Microsoft
Publications - 11
Citations - 432
Charles Claudius Marais is an academic researcher from Microsoft. The author has contributed to research in topics: Gesture & Video game. The author has an hindex of 9, co-authored 11 publications receiving 427 citations.
Papers
More filters
Patent
Validation analysis of human target
Jon D. Pulsipher,Parham Mohadjer P,Nazeeh Amin Eldirghami Na,Shao Liu S,Patrick Orville Cook Po,James Chadon Foster Jc,Ronald Omega Forbes Jr Rof,Szymon P Stachniak Sp,Tommer Leyvand,Joseph Bertolami J,Michael Taylor Janney Mt,Kien Toan Huynh Kt,Charles Claudius Marais,Spencer Dean Perreault Sd,Robert John Fitzgerald Rj,Wayne Richard Bisson Wr,Craig Carroll Peeper Cc +16 more
TL;DR: In this article, a searchable repository of recorded and synthesized depth clips and associated ground truth tracking data is provided for testing a target recognition, analysis, and tracking system and a report generator outputs an analysis of the tracking data relative to the ground truth in the at least subset.
Patent
Environment and/or Target Segmentation
TL;DR: In this article, a depth image of a scene may be observed or captured by a capture device and one or more pixels of the depth image may be analyzed to determine whether the pixels associated with the scene environment are associated with a human target.
Patent
Visual target tracking using model fitting and exemplar
Alex Aben-Athar Kipman,Mark J. Finocchio,Ryan Michael Geiss,Johnny Chung Lee,Charles Claudius Marais,Zsolt Mathe +5 more
TL;DR: In this paper, an exemplar pose or a model-fitting pose is selected to represent the target based on the differences between the observed depth image and the synthesized depth image.
Patent
Machine learning gesture detection
TL;DR: In this article, a gesture detection module is trained via machine learning to identify one or more features of a virtual skeleton and indicate if the feature(s) collectively indicate a particular gesture.
Patent
Systems And Methods For Processing An Image For Target Tracking
TL;DR: In this paper, a depth image of a scene may be received, observed, or captured by a device, and the image may then be processed and a refined image may be rendered based on the processed image.