A New, Integrated Method of Human or Animal Body Modeling with Applications for Animation and Tracking

Stanford Reference:

06-193

Abstract

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.

Innovators & Portfolio

• Dragomir Anguelov   
• Daphne Koller   
• Praveen Srinivasan   
• Sebastian Thrun   more technologies from Sebastian Thrun »

Patent Status

• Published Application: 20080180448
• Issued : 8,139,067 (USA)

Date Released

Licensing Contact

02-139   The Stanford/NASA Vision Chip 02-215   Population Clustering for Analyzing Flow Cytometry and Other Large Data Sets 03-359   Voice to Text and Sketch - V2TS more technologies »