US 12,283,119 B2
3D object detection
Vibhav Vineet, Cambridge (GB); and John Redford, Cambridge (GB)
Assigned to Five AI Limited, Cambridge (GB)
Appl. No. 17/775,944
Filed by Five AI Limited, Bristol (GB)
PCT Filed Nov. 11, 2020, PCT No. PCT/EP2020/081799
§ 371(c)(1), (2) Date May 11, 2022,
PCT Pub. No. WO2021/094398, PCT Pub. Date May 20, 2021.
Claims priority of application No. 1916371 (GB), filed on Nov. 11, 2019.
Prior Publication US 2022/0383648 A1, Dec. 1, 2022
Int. Cl. G06V 20/64 (2022.01); G06V 10/25 (2022.01); G06V 10/62 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G06V 20/58 (2022.01)
CPC G06V 20/647 (2022.01) [G06V 10/25 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01); G06V 20/58 (2022.01); G06V 20/64 (2022.01); G06V 10/62 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method of training a 3D structure detector to detect 3D structure in 3D structure representation, the method comprising the following steps:
receiving, at a trainable 3D structure detector, a set of training inputs, each training input comprising at least one 3D structure representation;
the 3D structure detector determining, for each training input, a set of predicted 3D objects for the at least one 3D structure representation of that training input; and
training the 3D structure detector to optimize a cost function, wherein the cost function penalizes deviation from an expected geometric relationship between the set of predicted 3D objects for the at least one 3D structure representation, determined for each training input.