US 12,450,918 B2
Automatic lane marking extraction and classification from lidar scans
Dhananjai Sharma, Singapore (SG); Venice Erin Baylon Liong, Singapore (SG); Sergi Adipraja Widjaja, Singapore (SG); and Edouard Francois Marc Capellier, Singapore (SG)
Assigned to Motional AD LLC, Boston, MA (US)
Filed by Motional AD LLC, Boston, MA (US)
Filed on Aug. 31, 2022, as Appl. No. 17/823,916.
Claims priority of provisional application 63/365,698, filed on Jun. 1, 2022.
Prior Publication US 2024/0096109 A1, Mar. 21, 2024
Int. Cl. G06V 20/56 (2022.01); G01S 17/89 (2020.01); G06T 7/10 (2017.01); G06V 10/82 (2022.01)
CPC G06V 20/588 (2022.01) [G01S 17/89 (2013.01); G06T 7/10 (2017.01); G06V 10/82 (2022.01); G06T 2207/10028 (2013.01)] 13 Claims
OG exemplary drawing
 
1. A computer-implemented method implemented by at least one processor, the computer-implemented method comprising:
receiving, by the at least one processor, an image representing data from a liDAR scan of a vehicle environment;
convoluting, by the at least one processor, the image to generate a first feature map;
converting, by the at least one processor, the first feature map into a first feature vector;
applying, by the at least one processor, one or more additional convolutions to the first feature map to generate a second feature map;
converting, by the at least one processor, the second feature map into a second feature vector;
passing, by the at least one processor, an input representing at least the first feature vector and the second feature vector through a neural network to produce a scene feature vector;
generating, by the at least one processor, an output map based on at least the scene feature vector and the second feature map, wherein the output map includes a plurality of pixels and indicates a likelihood of each pixel corresponding to a road element; and
generating one or more polylines from the output map, each of the one or more polylines identifying a road element in the vehicle environment, wherein generating the one or more polylines comprises:
converting one or more adjacent pixels in the output map with a classification value satisfying a threshold into an undirected graph; and
identifying a longest path within the undirected graph as a polyline of the one or more polylines.