US 11,972,015 B2
Personally identifiable information removal based on private area logic
David Michael Herman, West Bloomfield, MI (US); Gregg William Byrne, Dearborn, MI (US); and Akshay Vaidya, Canton, MI (US)
Assigned to Ford Global Technologies, LLC, Dearborn, MI (US)
Filed by FORD GLOBAL TECHNOLOGIES, LLC, Dearborn, MI (US)
Filed on Jun. 1, 2021, as Appl. No. 17/335,920.
Prior Publication US 2022/0382903 A1, Dec. 1, 2022
Int. Cl. G06F 21/62 (2013.01); G06K 9/72 (2006.01); G06T 15/20 (2011.01); G06V 30/262 (2022.01); G06N 5/04 (2023.01)
CPC G06F 21/6245 (2013.01) [G06T 15/205 (2013.01); G06V 30/274 (2022.01); G06N 5/04 (2013.01)] 14 Claims
OG exemplary drawing
 
1. A system for removal of personally identifiable information (PH), comprising:
sensors configured to capture sensor data; and
one or more controllers programmed to
perform object detection on the sensor data to create a sematic labeling of objects in the sensor data,
identify a current location of the system,
create a three-dimensional (3D) depth mapping based on the sensor data,
perform a data fusion to fuse the 3D depth mapping, the object detection, and high definition (HD) maps of the current location,
utilize a model receiving the data fusion as input to classify regions of the sensor data with a public or private labeling according to the sematic labeling, the 3D depth mapping, the HD maps, and a PH filter corresponding to a jurisdiction of the current location of the system, and
utilize the sensor data in accordance with the public or private labeling.