Methods and systems for applying machine learning to volumetric capture of a body in a real-world scene

US11222474B2 · kind B2 · utility

Assignee

• Verizon Patent and Licensing Inc. · US

Inventors

• Daniel Kopeinigg · Palo Alto, US
• Andrew David Walkingshaw · Palo Alto, US
• Arthur van Hoff · Menlo Park, US
• Charles LePere · San Mateo, US
• Christopher Redmann · San Mateo, US
• Philip Lee · San Jose, US
• Solmaz Hajmohammadi · Palo Alto, US
• Sourabh Khire · San Mateo, US
• Simion Venshtain · Chicago, US

Key dates

• Filing date: Mar 26, 2020
• Grant date: Jan 11, 2022
• Expiry date: Mar 26, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G06V40/23
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

An illustrative volumetric capture system accesses a machine learning model associated with bodies of a particular body type, as well as a two-dimensional (2D) image captured by a capture device located at a real-world scene. The 2D image depicts a body of the particular body type that is present at the real-world scene. Using the machine learning model and based on the 2D image, the volumetric capture system identifies a 2D joint location, from a perspective of the capture device, of a particular joint of the body. The volumetric capture system also generates a three-dimensional (3D) reference model of the body that represents the particular joint of the body at a 3D joint location that is determined based on the 2D joint location identified using the machine learning model. Corresponding methods and systems are also disclosed.