US 12,243,158 B2
Ensemble learning for cross-range 3D object detection in driver assist and autonomous driving systems
Saudin Botonjic, Gothenburg (SE); Sihao Ding, Sunnyvale, CA (US); Ying Li, Sunnyvale, CA (US); Cheng Zhang, Columbus, OH (US); and Oskar Karnblad, Västra Götaland (SE)
Assigned to Volvo Car Corporation, Sweden (SE)
Filed by Volvo Car Corporation, Gothenburg (SE)
Filed on Dec. 29, 2020, as Appl. No. 17/136,239.
Prior Publication US 2022/0207822 A1, Jun. 30, 2022
Int. Cl. G06T 17/00 (2006.01)
CPC G06T 17/00 (2013.01) [G06T 2207/10028 (2013.01); G06T 2207/20081 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A cross-range 3D object detection method, comprising:
generating a point cloud only utilizing data indicated from a single measurement of a single optical device of a vehicle;
dividing the point cloud into N sub-groups corresponding to N detection distance ranges from the vehicle and defined with respect to the optical device, wherein N is an integer of three or more;
sequentially training a same neural network for 3D object detection with the N sub-groups of the point cloud corresponding to the N detection distance ranges from the vehicle and defined with respect to the optical device to form N 3D object detection algorithm versions corresponding to the N detection distance ranges utilizing stochastic gradient descent to converge and escape from a local minima of each of the N 3D object detection algorithm versions in combination with a cycling procedure in which a learning rate is abruptly raised and then quickly lowered to follow a cosine function and utilizing online ground truth boxes augmentation in which object boxes and inside points from one scene are copied to the same locations in another scene; and
combining the N 3D object detection algorithm versions trained form the same neural network to form an ensemble 3D object detection algorithm utilizing Snapshot Ensembling such that inference is applied to the N sub-groups of the point cloud by performing non-maximum suppression on predictions of all of the N 3D object detection algorithm versions.