US 11,875,496 B2
Dimension estimation using duplicate instance identification in a multiview and multiscale system
Abhilash Nvs, Bhubaneswar (IN); Ankit Sati, New Delhi (IN); Payanshi Jain, Jaipur (IN); Koundinya K. Nvss, Tirupati (IN); Rajat Katiyar, Lucknow (IN); Mohiuddin Khan, Bangalore (IN); Chirag Jain, Bangalore (IN); and Sreekanth Menon, Bangalore (IN)
Assigned to Genpact Luxembourg S.à r.l. II, Luxembourg (LU)
Filed by Genpact Luxembourg S.à r.l. II, Luxembourg (LU)
Filed on Aug. 25, 2021, as Appl. No. 17/412,045.
Prior Publication US 2023/0063002 A1, Mar. 2, 2023
Int. Cl. G06T 7/00 (2017.01); G06T 7/11 (2017.01); G06T 7/62 (2017.01); G06F 18/22 (2023.01)
CPC G06T 7/0002 (2013.01) [G06F 18/22 (2023.01); G06T 7/11 (2017.01); G06T 7/62 (2017.01); G06T 2207/20081 (2013.01); G06T 2207/20221 (2013.01); G06T 2207/30252 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for dimension estimation based on duplicate instance identification, the method comprising:
receiving a set of images of an object;
detecting, using a first machine learning system trained to perform image segmentation, from a first image in the set of images, a first image segmentation representing a damage of the object on the first image;
detecting, using the first machine learning system trained to perform image segmentation, from a second image in the set of images, a second image segmentation representing a damage of the object on the second image;
determining, using a second machine learning system trained to perform dimension estimation, a first dimension for the damage represented by the first image segmentation and a second dimension for the damage represented by the second image segmentation;
determining whether the first image segmentation and the second image segmentation represent a same damage of the object based on a similarity index between the first image segmentation and the second image segmentation; and
responsive to determining that the first image segmentation and the second image segmentation represent the same damage, intelligently combining the first dimension and the second dimension to obtain a final dimension for the damage of the object.