US 12,444,057 B2
Systems and methods for improved three-dimensional data association using information from two-dimensional images
Gary Fay, Hermosa Beach, CA (US); and Krishna Prasad Varadarajan Srinivasan, Mountain View, CA (US)
Assigned to Rivian IP Holdings, LLC, Irvine, CA (US)
Filed by Rivian IP Holdings, LLC, Irvine, CA (US)
Filed on Dec. 31, 2021, as Appl. No. 17/567,016.
Prior Publication US 2023/0230257 A1, Jul. 20, 2023
Int. Cl. G06T 7/246 (2017.01); G06T 7/60 (2017.01); G06T 7/73 (2017.01); G06T 7/90 (2017.01); G06V 20/56 (2022.01); G06V 20/64 (2022.01)
CPC G06T 7/246 (2017.01) [G06T 7/60 (2013.01); G06T 7/73 (2017.01); G06T 7/90 (2017.01); G06V 20/56 (2022.01); G06V 20/64 (2022.01); G06T 2207/20084 (2013.01); G06T 2207/30252 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
tracking, by a processing circuitry associated with a vehicle, a tracked object in three-dimensional space, wherein the tracked object in the three-dimensional space is associated with a first two-dimensional image characteristic from a first two-dimensional image and a first three-dimensional bounding box for the tracked object in the first two-dimensional image;
receiving, by the processing circuitry, subsequent to receiving the first two-dimensional image, a second two-dimensional image from a sensor associated with the vehicle;
generating, by the processing circuitry, a second three-dimensional bounding box for an object in the second two-dimensional image;
determining, by the processing circuitry, a second two-dimensional image characteristic of the object in the second two-dimensional image; and
associating, by the processing circuitry, the second three-dimensional bounding box with the tracked object based on comparing the first three-dimensional bounding box to the second three-dimensional bounding box of the object and based on comparing the first two-dimensional image characteristic to the second two-dimensional image characteristic of the object.