US 12,175,595 B2
System and method for optimizing a bounding box using an iterative closest point algorithm
Jacopo Serafin, Los Altos, CA (US)
Assigned to Toyota Research Institute, Inc., Los Altos, CA (US); and Toyota Jidosha Kabushiki Kaisha, Aichi-ken (JP)
Filed by Toyota Research Institute, Inc., Los Altos, CA (US)
Filed on Apr. 29, 2022, as Appl. No. 17/733,150.
Prior Publication US 2023/0351679 A1, Nov. 2, 2023
Int. Cl. G06T 17/00 (2006.01); G01S 17/89 (2020.01); G06T 7/73 (2017.01)
CPC G06T 17/00 (2013.01) [G01S 17/89 (2013.01); G06T 7/73 (2017.01); G06T 2207/10028 (2013.01); G06T 2210/12 (2013.01)] 17 Claims
OG exemplary drawing
 
7. A method for optimizing a bounding box that was generated based on a point cloud using an iterative closest point algorithm (ICP), the method comprising iteratively performing, until a predetermined condition is satisfied, the steps of:
matching points of the point cloud to sides of the bounding box to create matched sets, wherein the matched sets include a point of the point cloud and a side of the bounding box; and
finding a best transformation to apply to the bounding box that jointly minimizes distances between the point of the point cloud and the side of the bounding box for the matched sets.