US 11,748,445 B1
Techniques for managing feature maps
Bruno M. Sommer, Sunnyvale, CA (US); and Alexandre da Veiga, San Francisco, CA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Apr. 29, 2020, as Appl. No. 16/861,692.
Claims priority of provisional application 62/841,135, filed on Apr. 30, 2019.
Int. Cl. G06V 20/00 (2022.01); G06F 18/213 (2023.01)
CPC G06F 18/213 (2023.01) [G06V 20/00 (2022.01)] 18 Claims
OG exemplary drawing
 
1. An electronic device, comprising:
one or more processors; and
memory storing one or more programs configured to be executed by the one or more processors, the one or more programs including instructions for:
receiving a first plurality of feature points corresponding to a location within a real world environment, wherein:
the first plurality of feature points includes a first set of feature points from a first series of one or more images captured by a first recording device and a second set of feature points from a second series of one or more images captured by a second recording device different from the first recording device, and
the first plurality of feature points includes data corresponding to one or more characteristics of the location, wherein the data corresponding to the one or more characteristics of the location includes a first time data corresponding to one or more times during which the first series of one or more images were captured and a second time data corresponding to one or more times during which the second series of one or more images were captured;
identifying, based on the data corresponding to the one or more characteristics of the location, a second plurality of feature points of a feature map, wherein the second plurality of feature points of the feature map at least partially correspond to the first plurality of feature points;
determining whether the second plurality of feature points are to be updated based on the first plurality of feature points, wherein determining whether the second plurality of feature points are to be updated based on the first plurality of feature points includes determining, based on the first time data and the second time data, whether the first plurality of feature points correspond to images that were captured more recently than images corresponding to the second plurality of feature points; and
in accordance with a determination that the second plurality of feature points should be updated based on the first plurality of feature points, updating the second plurality of feature points using the first plurality of feature points.