US 11,940,537 B2
Real-time virtual LiDAR sensor
Wei Zeng, Oakland Township, MI (US); Huabing Zhu, Troy, MI (US); Shuqing Zeng, Sterling Heights, MI (US); and Jordan B. Chipka, Commerce Township, MI (US)
Assigned to GM GLOBAL TECHNOLOGY OPERATIONS LLC, Detroit, MI (US)
Filed by GM Global Technology Operations LLC, Detroit, MI (US)
Filed on Dec. 8, 2021, as Appl. No. 17/545,194.
Prior Publication US 2023/0176218 A1, Jun. 8, 2023
Int. Cl. G01S 17/89 (2020.01); G01B 11/22 (2006.01); G01S 17/931 (2020.01); G06T 7/11 (2017.01); G06T 7/521 (2017.01); G06T 7/55 (2017.01); H04N 23/90 (2023.01)
CPC G01S 17/89 (2013.01) [G01B 11/22 (2013.01); G01S 17/931 (2020.01); G06T 7/11 (2017.01); G06T 7/521 (2017.01); G06T 7/55 (2017.01); H04N 23/90 (2023.01); G06T 2207/10024 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/30252 (2013.01)] 9 Claims
OG exemplary drawing
 
1. A virtual LiDAR sensor system for a motor vehicle, the system comprising:
a first camera or a first camera system that captures depth of field information of an image;
a second camera that captures RGB information of the image; and
a third camera that generates semantic segmentation information of the image;
a geometry point cloud that receives depth of field information from the first camera; and
a physics module that receives information from the geometry point cloud module, the second camera and the third camera, the physics module including a laser beam propagation sub-module, a backscattering attenuation sub-module, a digital reflector sub-module and a color-reflectivity table sub-module,
wherein the physics module generates a depth and intensity point cloud of the image from the depth of field information, the RGB information and the semantic segmentation information.