US 12,080,038 B2
System and method for augmented decision making by detecting occlusions
Manoj Sharma, Troy, MI (US); Jacob Alan Bond, Rochester Hills, MI (US); and Joseph F. Szczerba, Grand Blanc, 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. 14, 2022, as Appl. No. 18/066,008.
Prior Publication US 2024/0203084 A1, Jun. 20, 2024
Int. Cl. G06V 10/26 (2022.01); G06T 5/77 (2024.01); G06V 10/25 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/25 (2022.01) [G06T 5/77 (2024.01); G06V 10/26 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06T 2207/30256 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method for selectively augmenting information in a vehicle, the method comprising:
receiving a scene information from at least one sensor;
identifying a region of interest from the scene information;
analyzing the scene information to determine whether the region of interest is occluded by passing the scene information through a neural network;
identifying whether the region of interest contains a traffic light;
determining the traffic light state;
converting a red, green, or red light of the traffic light to an intensity image;
calculating contrast values of the of the intensity image;
determining whether the contrast values are less than a contrast threshold;
augmenting the traffic light state, using a display system, when the contrast is less than the contrast threshold; and
not augmenting the traffic light state, using the display system, when the contrast is greater than the contrast threshold.