Learning a similarity measure for vision-based localization on a high definition (hd) map
AssigneeHERE Global B.V.
InventorAnirudh Viswanathan
Life of this patent
Estimating the term…
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.
Claims21
A routing and navigation system comprising:
- an image capturing device configured to capture a captured image;
- a location sensor configured to determine observed pose data that indicates the pose of the routing and navigation system when the captured image was captured;
- memory storing map data;
- and
- at least one processor configured to:
- generate a map projection based on the map data and the observed pose data;
- execute a pose metric network to:
- analyze the captured image and the map projection;
- and
- determine, based on the analysis of the captured image and the map projection, a pose metric, wherein the pose metric describes how similar the captured image is to the map projection;
- and
- determine one or more operational parameters based on the pose metric, the one or more operational parameters configured to control at least one aspect of the operation of the routing and navigation system.
A method comprising:
- capturing or receiving a captured image and corresponding observed pose data, wherein (a) the captured image is captured by an image capturing device onboard a vehicle, (b) the observed pose data is determined by a location sensor onboard the vehicle, and (c) the observed pose data indicates the pose of the vehicle when the captured image was captured;
- generating, via at least one processor, a map projection based on map data and the observed pose data;
- analyzing the captured image and the map projection using a pose metric network;
- determining, by the pose metric network and based on the analysis of the captured image and the map projection, a pose metric, wherein the pose metric describes how similar the captured image is to the map projection.
An apparatus comprising at least one processor, at least one memory storing computer program code, and a pose error network, the at least one memory and the computer program code configured to, with the processor, cause the apparatus to at least:
- capture or receive a captured image and corresponding observed pose data, wherein (a) the captured image is captured by an image capturing device onboard a vehicle, (b) the observed pose data is determined by a location sensor onboard the vehicle, and (c) the observed pose data indicates the pose of the vehicle when the image was captured;
- generate a map projection based on map data and the observed pose data;
- analyze the captured image and the map projection using a pose metric network;
- determine, by the pose metric network and based on the analysis of the captured image and the map projection, a pose metric, wherein the pose metric describes how similar the captured image is to the map projection.
A computer program product comprising at least one non-transitory computer-readable storage medium having computer-executable program code instructions stored therein, the computer-executable program code instructions comprising program code instructions configured to:
- capture or receive a captured image and corresponding observed pose data, wherein (a) the captured image is captured by an image capturing device onboard a vehicle, (b) the observed pose data is determined by a location sensor onboard the vehicle, and (c) the observed pose data indicates the pose of the vehicle when the image was captured;
- generate a map projection based on map data and the observed pose data;
- analyze the captured image and the map projection using a pose metric network;
- determine, by the pose metric network and based on the analysis of the captured image and the map projection, a pose metric, wherein the pose metric describes how similar the captured image is to the map projection.
Dependencies are inferred from the claim text.