US 11,954,844 B2
Fatigue crack detection in civil infrastructure
Xiangxiong Kong, Barrigada, GU (US); and Jian Li, Lawrence, KS (US)
Assigned to UNIVERSITY OF KANSAS, Lawrence, KS (US)
Appl. No. 17/265,902
Filed by University of Kansas, Lawrence, KS (US)
PCT Filed Aug. 20, 2019, PCT No. PCT/US2019/047272
§ 371(c)(1), (2) Date Feb. 4, 2021,
PCT Pub. No. WO2020/041319, PCT Pub. Date Feb. 27, 2020.
Claims priority of provisional application 62/720,339, filed on Aug. 21, 2018.
Prior Publication US 2021/0166366 A1, Jun. 3, 2021
Int. Cl. G06T 7/00 (2017.01); G06T 5/00 (2006.01); G06T 7/33 (2017.01)
CPC G06T 7/001 (2013.01) [G06T 5/002 (2013.01); G06T 7/337 (2017.01); G06T 2207/30136 (2013.01); G06T 2207/30184 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for fatigue crack detection, comprising:
capturing a first image of a structure at a first time;
capturing a second image of the structure at a second time;
performing a feature-based image registration through a rigid-body transformation to align features of the second image with the first image;
performing an intensity-based image registration through a non-rigid transformation to further align features of the second image with the first image;
determining a registration error map based on a comparison of the first image and the second image; and
performing edge-aware noise reduction on the registration error map.