US 11,989,893 B2
Methods and systems for camera to lidar alignment using road poles
Yousef Omar, Troy, MI (US); Wende Zhang, Birmingham, MI (US); and Hao Yu, Troy, MI (US)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed on Mar. 22, 2022, as Appl. No. 17/655,888.
Prior Publication US 2023/0306621 A1, Sep. 28, 2023
Int. Cl. G06T 7/37 (2017.01); B60R 1/22 (2022.01); G01S 17/87 (2020.01); G01S 17/89 (2020.01); G06F 18/2321 (2023.01); G06F 18/25 (2023.01); G06V 20/58 (2022.01)
CPC G06T 7/37 (2017.01) [B60R 1/22 (2022.01); G01S 17/87 (2013.01); G01S 17/89 (2013.01); G06F 18/2321 (2023.01); G06F 18/251 (2023.01); G06V 20/58 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/30252 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for generating alignment parameters for processing data associated with a vehicle, the method comprising:
receiving image data associated with an environment of the vehicle;
receiving lidar data associated with the environment of the vehicle;
processing, by a processor, the image data to determine data points associated with at least one road pole identified within image data;
processing, by the processor, the lidar data to determine data points associated with at least one road pole identified within the lidar data;
selectively storing the data points as a set of data point pairs in a data buffer;
iteratively processing, by the processor, the set of data point pairs with a plurality of perturbations to determine a plurality of transformation matrices, wherein the iteratively processing results in each of the plurality of transformation matrices having an associated score;
selecting, by the processor, an optimal transformation matrix with a threshold associated score from the plurality of transformation matrices;
generating, by the processor, alignment data based on the optimal transformation matrix; and
processing the data associated with the vehicle based on the alignment parameters.