US 12,269,500 B2
Alignment validation in vehicle-based sensors
Michael Baltaxe, Kfar Saba (IL); Dan Levi, Ganei Tikvah (IL); Noa Garnett, Herzeliya (IL); Doron Portnoy, Kfar Yona (IL); Amit Batikoff, Petch tikwa (IL); Shahar Ben Ezra, Hod Hasharon (IL); and Tal Furman, Tel Aviv (IL)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM Global Technology Operations LLC, Detroit, MI (US)
Filed on Nov. 1, 2021, as Appl. No. 17/516,348.
Prior Publication US 2023/0134125 A1, May 4, 2023
Int. Cl. B60W 60/00 (2020.01); G06F 18/214 (2023.01); G06V 20/58 (2022.01)
CPC B60W 60/001 (2020.02) [G06F 18/214 (2023.01); G06V 20/58 (2022.01); B60W 2420/403 (2013.01); B60W 2420/408 (2024.01); B60W 2555/00 (2020.02)] 20 Claims
OG exemplary drawing
 
1. A system in a vehicle comprising:
an image sensor configured to obtain images in an image sensor coordinate system;
a depth sensor configured to obtain point clouds in a depth sensor coordinate system; and
processing circuitry configured to implement a neural network to determine a validation state of a transformation matrix configured to transform the point clouds in the depth sensor coordinate system to transformed point clouds in the image sensor coordinate system, the transformation matrix including rotation parameters and translation parameters, and wherein the processing circuitry is configured to train the neural network based on image data from an aligned image sensor that is aligned with an aligned depth sensor and based on transformed point cloud data that is obtained from the aligned depth sensor and transformed, using an aligned transformation matrix, to a coordinate system of the aligned image sensor.