US 12,259,229 B1
Long range depth estimation sensor
Sergey M. Nikitin, Cambridge, MA (US); Sara Jean Woo, Andover, MA (US); and Jing Ma, Salt Lake City, UT (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on May 16, 2022, as Appl. No. 17/745,648.
Int. Cl. G01B 11/22 (2006.01); B25J 9/16 (2006.01); G01B 11/25 (2006.01)
CPC G01B 11/22 (2013.01) [B25J 9/1687 (2013.01); B25J 9/1697 (2013.01); G01B 11/2518 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A system, comprising:
a transport device comprising a volume for holding one or more items;
a frame providing a mounting location above the transport device;
a multi-base imaging camera disposed in the mounting location, such that the volume of the transport device is within a field-of-view of the multi-base imaging camera, wherein the multi-base imaging camera comprises:
a first imaging sensor;
a second imaging sensor separated from the first imaging sensor by a first baseline; and
a third imaging sensor separated from the first imaging sensor by a second baseline greater than the first baseline; and
a computing system configured to:
capture, via the first imaging sensor, a first image of the volume of the transport device;
capture, via the second imaging sensor, a second image of the volume of the transport device;
capture, via the third imaging sensor, a third image of the volume of the transport device;
generate a first point cloud based on the first image and the second image, the first point cloud comprising first depth information for distances within a first range of distances from the multi-base imaging camera;
generate a second point cloud based on the first image and the third image, the second point cloud comprising second depth information for distances within a second range of distances from the multi-base imaging camera; and
generate third depth information, based on the first point cloud and the second point cloud, the third depth information comprising at least the first depth information and the second depth information.