US 12,442,925 B2
Determining weights of points of a point cloud based on geometric features
Derik Schroeter, Fremont, CA (US)
Assigned to NVIDIA CORPORATION, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Nov. 21, 2022, as Appl. No. 18/057,582.
Application 18/057,582 is a continuation in part of application No. 16/910,742, filed on Jun. 24, 2020, granted, now 11,514,682.
Claims priority of provisional application 62/866,504, filed on Jun. 25, 2019.
Claims priority of provisional application 62/865,855, filed on Jun. 24, 2019.
Prior Publication US 2023/0121226 A1, Apr. 20, 2023
Int. Cl. G01S 17/89 (2020.01); G01S 17/931 (2020.01)
CPC G01S 17/89 (2013.01) [G01S 17/931 (2020.01)] 19 Claims
OG exemplary drawing
 
1. A method, comprising:
identifying a cluster of points of a first point cloud;
determining a percentage of points of the cluster of points that are identified as corresponding to respective points of a second point cloud;
determining that the cluster of points corresponds to a dynamic object based at least on the percentage;
based at least on the cluster of points corresponding to the dynamic object, removing the cluster of points from the first point cloud to generate an updated first point cloud; and
determining a location of an autonomous or semi-autonomous machine based at least on the updated first point cloud, wherein the autonomous or semi-autonomous machine performs one or more navigation or control operations for maneuvering based at least on the location of the autonomous or semi-autonomous machine.