US 12,136,271 B2
Long-range object detection, localization, tracking and classification for autonomous vehicles
Ruichi Yu, Mountain View, CA (US); Kang Li, Sammamish, WA (US); Tao Han, Sunnyvale, CA (US); Robert Cosgriff, San Francisco, CA (US); and Henrik Kretzschmar, Mountain View, CA (US)
Assigned to Waymo LLC, Mountain View, CA (US)
Filed by WAYMO LLC, Mountain View, CA (US)
Filed on May 13, 2021, as Appl. No. 17/319,194.
Prior Publication US 2022/0366175 A1, Nov. 17, 2022
Int. Cl. G06V 20/58 (2022.01); G01S 13/931 (2020.01); G01S 17/931 (2020.01); G05D 1/00 (2006.01); G06F 18/22 (2023.01)
CPC G06V 20/58 (2022.01) [G01S 13/931 (2013.01); G01S 17/931 (2020.01); G05D 1/0088 (2013.01); G05D 1/0251 (2013.01); G06F 18/22 (2023.01)] 21 Claims
OG exemplary drawing
 
1. A method of controlling a vehicle, the method comprising:
capturing, by one or more processors, using a camera, a first camera image including a first object;
capturing, by the one or more processors, using the camera, a second camera image including a second object;
identifying, by the one or more processors, a first bounding box for the first object in the first camera image and a distance to the first object from the vehicle;
identifying, by the one or more processors, a second bounding box for the second object in the second camera image and a distance to the second object from the vehicle;
determining, by the one or more processors, whether the first object is the second object using a first model to compute visual similarity for the first bounding box and the second bounding box, a second model to compare a three-dimensional location based on the distance to the first object and a three-dimensional location based on the distance to the second object, and a third model to compare results from the first model and the second model, wherein the first, second, and third models are different models; and
controlling, by the one or more processors, the vehicle in an autonomous driving mode based on a result of the third model.