US 12,380,599 B2
Characterizing and improving of image processing
Daniel Milan Lütgehetmann, Lausanne (CH); Dimitri Zaganidis, Granges (CH); Nicolas Alain Berger, Fribourg (CH); and Felix Schürmann, Grens (CH)
Assigned to INAIT SA, Lausanne (CH)
Filed by INAIT SA, Lausanne (CH)
Filed on Nov. 10, 2021, as Appl. No. 17/454,347.
Claims priority of application No. 20210100602 (GR), filed on Sep. 13, 2021.
Prior Publication US 2023/0085384 A1, Mar. 16, 2023
Int. Cl. G06K 9/00 (2022.01); G06T 7/73 (2017.01); H04N 23/60 (2023.01)
CPC G06T 7/75 (2017.01) [G06T 7/74 (2017.01); H04N 23/64 (2023.01); G06T 2207/30244 (2013.01)] 8 Claims
OG exemplary drawing
 
1. A method for characterizing correctness of image processing, the method comprising:
receiving images of an instance of an object, wherein the images were acquired at different relative poses;
identifying positions of corresponding landmarks on at least a first portion of the instance of the object in each of the received images;
receiving information characterizing a difference in position or a difference in orientation of at least one of
the instance of the object and
one or more imaging devices when the images were acquired,
wherein receiving the information characterizing the difference in position or the difference in orientation comprises
identifying either a second, different object or a second, different portion of the instance of the object in the images of the instance of the object, and
determining the difference in position or the difference in orientation based on the second object or the second portion of the instance of the object, wherein the at least the first portion of the instance of the object used for identifying corresponding landmarks is excluded from the determination of the difference in position or the difference in orientation;
transferring the positions of landmarks identified in a first of the images based on the difference in position or the difference in orientation to obtain transferred landmarks on the first portion of the object;
comparing the positions of the transferred landmarks with the positions of the corresponding of the landmarks identified in a second of the received images; and
characterizing, based on the comparison of the positions of the transferred landmarks with the positions of the corresponding of the landmarks on at least the first portion of the instance of the object, a correctness of the identification of the positions of the landmarks in at least one of the received images.