Patent · US Active

Training methods for deep networks

US11113526B2 · kind B2 · utility

0Cited by
3References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 13, 2019
Grant dateSep 7, 2021
Priority date
Expiry dateDec 2, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20104
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method for training a deep neural network of a robotic device is described. The method includes constructing a 3D model using images captured via a 3D camera of the robotic device in a training environment. The method also includes generating pairs of 3D images from the 3D model by artificially adjusting parameters of the training environment to form manipulated images using the deep neural network. The method further includes processing the pairs of 3D images to form a reference image including embedded descriptors of common objects between the pairs of 3D images. The method also includes using the reference image from training of the neural network to determine correlations to identify detected objects in future images.

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