Patent · US Active

Human pose estimation using neural networks and kinematic structure

US11335023B2 · kind B2 · utility

0Cited by

1References

17Claims

0Family size

Assignee

Google LLC · US

Inventors

Sameh Khamis · Seattle, US
Christian Haene · Berkeley, US
Hossam Isack · Oakland, US
Cem Keskin · Seattle, US
Sofien Bouaziz · Los Gatos, US
Shahram Izadi · Cambridge, GB

Key dates

Filing date	May 22, 2020
Grant date	May 17, 2022
Priority date	—
Expiry date	May 22, 2040

Classification

Technology area (CPC G)Physics
CPC primaryG06T2207/30244
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

According to an aspect, a method for pose estimation using a convolutional neural network includes extracting features from an image, downsampling the features to a lower resolution, arranging the features into sets of features, where each set of features corresponds to a separate keypoint of a pose of a subject, updating, by at least one convolutional block, each set of features based on features of one or more neighboring keypoints using a kinematic structure, and predicting the pose of the subject using the updated sets of features.

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