US 11,755,688 B2
Apparatus and method for generating training data for a machine learning system
Bradley Quinton, Vancouver (CA); Trent McClements, Burnaby (CA); Michael Lee, North Vancouver (CA); and Scott Chin, Vancouver (CA)
Assigned to Singulos Research Inc., Burnaby (CA)
Filed by Singulos Research Inc., Burnaby (CA)
Filed on Dec. 21, 2021, as Appl. No. 17/557,515.
Claims priority of provisional application 63/167,800, filed on Mar. 30, 2021.
Prior Publication US 2022/0318568 A1, Oct. 6, 2022
Int. Cl. G06N 3/00 (2023.01); G06F 18/214 (2023.01); G06T 19/00 (2011.01); G06N 3/088 (2023.01); G06F 18/24 (2023.01); G06N 3/045 (2023.01)
CPC G06F 18/2148 (2023.01) [G06F 18/24 (2023.01); G06N 3/045 (2023.01); G06N 3/088 (2013.01); G06T 19/00 (2013.01)] 9 Claims
OG exemplary drawing
 
1. A method for training a machine learning engine configured to determine whether an object in a two dimensional (2D) image is in-scope or out-of-scope relative to the one or more 3D objects, the method comprising:
receiving a 3D model of each of the one or more 3D objects;
for each 3D model:
receiving a set of specifications and thresholds for the 3D model;
augmenting the specifications of the 3D model to generate a plurality of augmented 3D models; and
generating auxiliary training data based on the plurality of augmented 3D models; and
utilizing the auxiliary training data to train the machine learning engine,
wherein generating auxiliary training data based on the plurality of augmented 3D models comprises, for each augmented 3D model:
determining whether the specifications of the augmented 3D model are within the thresholds;
classifying any augmented 3D model that are determined not within the thresholds as out-of-scope; and
classifying any augmented 3D models are determined to be within the thresholds as in-scope.