Vehicle localization systems and methods
AssigneeFord Global Technologies, LLC
InventorsSarah Houts, Praveen Narayanan, Punarjay Chakravarty, Gaurav Pandey, Graham Mills, Tyler Reid
Life of this patent
Estimating the term…
Abstract
Example localization systems and methods are described. In one implementation, a method receives a camera image from a vehicle camera and cleans the camera image using a VAE-GAN (variational autoencoder combined with a generative adversarial network) algorithm. The method further receives a vector map related to an area proximate the vehicle and generates a synthetic image based on the vector map. The method then localizes the vehicle based on the cleaned camera image and the synthetic image.
Claims20
A method comprising:
- receiving, by a localization component, a camera image from a vehicle camera;
- cleaning, by the localization component, the camera image using a VAE-GAN (variational autoencoder combined with a generative adversarial network) algorithm to generate a cleaned camera image;
- receiving a vector map related to an area proximate the vehicle;
- generating a synthetic image based on the vector map;
- and
- localizing, by the localization component, the vehicle based on the cleaned camera image and the synthetic image.
A method for localization, the method comprising:
- receiving, by a localization component, a camera image from a camera associated with a vehicle;
- cleaning, by the localization component, the camera image using a VAE-GAN (variational autoencoder combined with a generative adversarial network) algorithm to generate a cleaned camera image;
- communicating the cleaned image to a NMI (Normalized Mutual Information) correlation system;
- receiving a vector map related to an area proximate the vehicle;
- generating a synthetic image based on the vector map;
- correlating, by the NMI correlation system, the cleaned image and the synthetic image;
- and
- localizing the vehicle based on the correlation of the cleaned camera image and the synthetic image.
A localization system comprising:
- a processor;
- and
- a memory device coupled to the processor, the memory device configured to store instructions for execution on the processor, the instructions causing the processor to:
- receive a camera image from a vehicle camera;
- clean the camera image using a VAE-GAN (variational autoencoder combined with a generative adversarial network) algorithm to generate a cleaned camera image;
- receive a vector map related to an area proximate the vehicle;
- generate a synthetic image based on the vector map;
- and
- localize the vehicle based on the cleaned camera image and the synthetic image.
Dependencies are inferred from the claim text.