US 12,423,768 B2
Generating three-dimensional graphical data based on two-dimensional monocular camera sensor data
Kunal Saluja, Santa Cruz, CA (US); Rachit Aggarwal, Santa Cruz, CA (US); Ugur Oezdemir, Santa Cruz, CA (US); Duane Needham, Santa Cruz, CA (US); and Tyler Niday, Santa Cruz, CA (US)
Assigned to Bonsai Robotics Inc., San Jose, CA (US)
Filed by Bonsai Robotics Inc., Santa Cruz, CA (US)
Filed on Feb. 10, 2023, as Appl. No. 18/108,064.
Prior Publication US 2024/0273665 A1, Aug. 15, 2024
Int. Cl. G06T 1/00 (2006.01); A01D 46/00 (2006.01); G06T 15/00 (2011.01)
CPC G06T 1/0014 (2013.01) [A01D 46/00 (2013.01); G06T 15/005 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method comprising:
capturing, as an autonomous harvesting machine operates in an orchard, image data of trees in a tree row, wherein:
the image data is captured with a monocular camera and comprising a series of monocular images; and
the image data comprises a two-dimensional representation of the trees in the tree row;
inputting the image data in a graphic generation model, the graphic generation model configured to:
determine positions of each tree in the tree row in three dimensions using the series of monocular images; and
generate output data comprising a three-dimensional graphic, the three-dimensional graphic comprising a representation of each tree in the tree row at their determined positions; and
modifying an operation of the autonomous harvesting machine operating in the tree row based on the output data comprising the three-dimensional graphic.