Patent · US Active

Vehicle image generation

US11042758B2 · kind B2 · utility

2Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 2, 2019
Grant dateJun 22, 2021
Priority date
Expiry dateSep 24, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/30252
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A computer, including a processor and a memory, the memory including instructions to be executed by the processor to generate a synthetic image and corresponding ground truth and generate a plurality of domain adapted synthetic images by processing the synthetic image with a variational auto encoder-generative adversarial network (VAE-GAN), wherein the VAE-GAN is trained to adapt the synthetic image from a first domain to a second domain. The instructions can include further instructions to train a deep neural network (DNN) based on the domain adapted synthetic images and the corresponding ground truth and process images with the trained deep neural network to determine objects.

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