Patent · US Active

Application of convolutional neural networks to object meshes

US10643382B2 · kind B2 · utility

0Cited by

0References

20Claims

0Family size

Assignee

Intel Corporation · US

Inventors

Shahar Fleishman · Hod HaSharon, IL
Mark Kliger · Beer Sheva, IL

Key dates

Filing date	Apr 4, 2017
Grant date	May 5, 2020
Priority date	—
Expiry date	Aug 23, 2037

Classification

Technology area (CPC G)Physics
CPC primaryG06T17/205
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Convolutional Neural Networks are applied to object meshes to allow three-dimensional objects to be analyzed. In one example, a method includes performing convolutions on a mesh, wherein the mesh represents a three-dimensional object of an image, the mesh having a plurality of vertices and a plurality of edges between the vertices, performing pooling on the convolutions of an edge of a mesh, and applying fully connected and loss layers to the pooled convolutions to provide metadata about the three-dimensional object.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.