Docket #: S06-193
A New, Integrated Method of Human or Animal Body Modeling with Applications for Animation and Tracking
Stanford researchers have patented a data-driven method for building a human shape model that spans variation in both subject shape and pose. The method is based on a representation that incorporates both articulated and non-rigid deformations.
Capabilities include partial-view completion and lifelike animation of marker motion-capture sequences. Specifically, this method is capable of constructing a high-quality animated surface model of a moving person, with realistic muscle deformation, using just a single static scan and a marker motion capture sequence of the person.
Related Markerless Motion Capture Technologies also available for license:
S05-433– US Patent 7,804,998
S07-254– US Patent 8,180,714
S08-122– US Patent 8,384,714
Figure
Figure description - Animation of a motion capture sequence taken for a subject, of whom we have a single body scan. The muscle deformations are synthesized automatically from the space of pose and body shape deformations.
Applications
- Animation and computer graphics
- Digital movies
- Interactive Gaming and video games industry
- Biomechanical and clinical applications
- Biofeedback and rehabilitation
- Design and engineering
- Ergonomics
- Digital simulation of human and animal interaction
- Education
- Art. Visual arts and any art using biological signals as an input or output.
- Robotics. Development of biomimetic robots
- Surveillance
Advantages
- Captures body deformations due to change in pose and body shape variation between different individuals
- Maintains proper deformation scaling
- Efficient shape-completion of different subjects in different poses
- Enables marker-less motion capture of different people and animals from any kind of 3D readings, including stereo cameras, or multiple camera feeds combined, using shape-from-silhouette techniques, or the input from any 3D range sensors
- Accurate - The shape-completion capability provides accurate subject-specific automatic segmentation
- Low cost - The integrated method saves production time and cost
Publications
- Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., & Davis, J. (2005, July). SCAPE: shape completion and animation of people. In ACM Transactions on Graphics (TOG) (Vol. 24, No. 3, pp. 408-416). ACM.
Patents
- Published Application: 20080180448
- Issued: 8,139,067 (USA)
Similar Technologies
-
Automatic Generation of Human Models for Motion Capture, Biomechanics and Animation S07-254Automatic Generation of Human Models for Motion Capture, Biomechanics and Animation
-
Mesh-based Performance Capture from Multi-view Video S08-122Mesh-based Performance Capture from Multi-view Video
-
A New Accurate Method of 3D Full Body Motion Capture for Animation S05-433A New Accurate Method of 3D Full Body Motion Capture for Animation