公开(公告)号：US11921210B2

公开(公告)日：2024-03-05

申请号：US17959406

申请日：2022-10-04

Applicant: Aurora Operations, Inc.

Inventor： Stephen C. Crouch ,  Brant Kaylor ,  Randy R. Reibel

IPC: G01S17/42 ,  G01S7/48 ,  G01S17/89 ,  G06F18/22 ,  G06F18/2413 ,  G06F18/2431 ,  G06V10/40 ,  G06V10/74 ,  G06V10/75 ,  G06V10/764 ,  G06V20/64

CPC classification number: G01S17/42 ,  G01S7/4802 ,  G01S7/4808 ,  G01S17/89 ,  G06F18/22 ,  G06F18/24147 ,  G06F18/2431 ,  G06V10/40 ,  G06V10/7515 ,  G06V10/761 ,  G06V10/764 ,  G06V20/64

Abstract: A method for classifying an object in a point cloud includes computing first and second classification statistics for one or more points in the point cloud. Closest matches are determined between the first and second classification statistics and a respective one of a set of first and second classification statistics corresponding to a set of N classes of a respective first and second classifier, to estimate the object is in a respective first and second class. If the first class does not correspond to the second class, a closest fit is performed between the point cloud and model point clouds for only the first and second classes of a third classifier. The object is assigned to the first or second class, based on the closest fit within near real time of receiving the 3D point cloud. A device is operated based on the assigned object class.