Invention Grant
- Patent Title: Learning a similarity measure for vision-based localization on a high definition (HD) map
-
Application No.: US15479635Application Date: 2017-04-05
-
Publication No.: US10296828B2Publication Date: 2019-05-21
- Inventor: Anirudh Viswanathan
- Applicant: HERE GLOBAL B.V.
- Applicant Address: NL Eindhoven
- Assignee: HERE GLOBAL B.V.
- Current Assignee: HERE GLOBAL B.V.
- Current Assignee Address: NL Eindhoven
- Agency: Alston & Bird LLP
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06N3/08 ; G05D1/02 ; B60R1/00 ; G06K9/62 ; H04N7/18

Abstract:
A captured image and corresponding observed pose data are captured or received. The captured image is captured by an image capturing device onboard a vehicle. The observed pose data is determined by a location sensor onboard the vehicle. The observed pose data indicates the pose of the vehicle when the image was captured. A map projection is generated based on map data and the observed pose data. The captured image and the map projection are analyzed by a pose metric network. The pose metric network determines a pose metric based on the analysis of the captured image and the map projection. The pose metric describes how similar the captured image is to the map projection.
Public/Granted literature
- US20180293466A1 LEARNING A SIMILARITY MEASURE FOR VISION-BASED LOCALIZATION ON A HIGH DEFINITION (HD) MAP Public/Granted day:2018-10-11
Information query