US 12,420,935 B2
Aircraft ice detection
Michael Christian Büddefeld, Hessen (DE); Miriam Cornel, Bavaria (DE); Stuart Cocks, Fareham (GB); Millie Irene Sterling, Wiesbaden (DE); and Andres Munoz Hernandez, Bayern (DE)
Assigned to The Boeing Company, Arlington, VA (US)
Filed by THE BOEING COMPANY, Chicago, IL (US)
Filed on Nov. 30, 2022, as Appl. No. 18/060,370.
Prior Publication US 2024/0174366 A1, May 30, 2024
Int. Cl. G06K 9/48 (2006.01); B64D 11/00 (2006.01); B64D 15/20 (2006.01); B64D 45/00 (2006.01); B64D 47/08 (2006.01); G06V 10/56 (2022.01); G06V 10/60 (2022.01); G06V 10/764 (2022.01); G06V 20/56 (2022.01)
CPC B64D 15/20 (2013.01) [B64D 11/0015 (2013.01); B64D 45/00 (2013.01); B64D 47/08 (2013.01); G06V 10/56 (2022.01); G06V 10/60 (2022.01); G06V 10/764 (2022.01); G06V 20/56 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining a first series of images captured by one or more cameras onboard an aircraft;
determining a frame rate based on weather conditions associated with the aircraft, wherein determining the frame rate comprises:
determining the frame rate corresponds to a first frame rate when the weather conditions represent a high risk of ice formation; and
determining the frame rate corresponds to a second frame rate when the weather conditions represent a lower risk of ice formation than the high risk of ice formation, wherein the first frame rate is greater than the second frame rate;
performing data reduction operations on the first series of images based on the frame rate to generate a second series of images;
generating feature data based on the second series of images, wherein the feature data is indicative of changes over time of pixel data of the second series of images, wherein the feature data includes data identifying a location of adjacent pixels that change in illumination between a first image of the second series of images and a second image of the second series of images;
generating, based on the feature data, input data for a trained classifier; and
determining, using the trained classifier, whether ice is present on one or more surfaces of the aircraft.