Invention Grant
- Patent Title: Vehicle image generation
-
Application No.: US16460066Application Date: 2019-07-02
-
Publication No.: US11042758B2Publication Date: 2021-06-22
- Inventor: Nikita Jaipuria , Gautham Sholingar , Vidya Nariyambut Murali , Rohan Bhasin , Akhil Perincherry
- Applicant: Ford Global Technologies, LLC
- Applicant Address: US MI Dearborn
- Assignee: Ford Global Technologies, LLC
- Current Assignee: Ford Global Technologies, LLC
- Current Assignee Address: US MI Dearborn
- Agency: Bejin Bieneman PLC
- Agent Frank A. MacKenzie
- Main IPC: G06K9/62
- IPC: G06K9/62 ; G06K9/00 ; G06N3/08 ; G06T15/06 ; G06T7/70

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.
Public/Granted literature
- US20210004608A1 VEHICLE IMAGE GENERATION Public/Granted day:2021-01-07
Information query