US 12,073,545 B2
Method for large area inspection
Richard A. Effler, Hazelwood, MO (US)
Assigned to The Boeing Company, Chicago, IL (US)
Filed by The Boeing Company, Chicago, IL (US)
Filed on Oct. 22, 2021, as Appl. No. 17/508,253.
Prior Publication US 2023/0131977 A1, Apr. 27, 2023
Int. Cl. G06T 7/00 (2017.01); B64C 39/02 (2023.01); G06F 18/213 (2023.01); G06T 3/40 (2024.01); G06T 5/90 (2024.01); G06T 7/11 (2017.01); G06T 7/80 (2017.01); G06V 10/141 (2022.01); G06V 10/75 (2022.01); G06V 20/10 (2022.01); B64U 10/13 (2023.01); B64U 101/30 (2023.01)
CPC G06T 7/0002 (2013.01) [B64C 39/024 (2013.01); G06F 18/213 (2023.01); G06T 3/40 (2013.01); G06T 5/90 (2024.01); G06T 7/11 (2017.01); G06T 7/80 (2017.01); G06V 10/141 (2022.01); G06V 10/751 (2022.01); G06V 20/10 (2022.01); B64U 10/13 (2023.01); B64U 2101/30 (2023.01); G06T 2207/10032 (2013.01); G06T 2207/20021 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30248 (2013.01)] 26 Claims
OG exemplary drawing
 
1. A computing device comprising:
a memory configured to store computer-readable program code; and
processing circuitry configured to access the memory, and to execute the computer-readable program code to cause the computing device to:
obtain a digital image of a target area of a vehicle, wherein the target area is illuminated by ambient light and a spotlight having a predominant color that is selected based on a type of inconsistency expected to be detected;
generate an enhanced contrast feature map based on a feature map of the digital image, wherein the enhanced contrast feature map comprises:
a plurality of feature map sub-sections with each sub-section being associated with a different color channel; and
scaled-up pixel values generated from selected pixel values in the feature map, wherein a weighting coefficient used to scale-up the selected pixel values is different for each color channel; and
detect an inconsistency in the target area based on the scaled-up pixel values in the enhanced contrast feature map.