US 12,405,152 B2
Weight determination of an animal based on 3D imaging
Jan Lassen, Randers (DK); and Søren Borchersen, Horsens (DK)
Assigned to Viking Genetics FMBA, Randers (DK)
Appl. No. 17/617,445
Filed by Viking Genetics FMBA, Randers (DK)
PCT Filed Jun. 26, 2020, PCT No. PCT/EP2020/068095
§ 371(c)(1), (2) Date Dec. 8, 2021,
PCT Pub. No. WO2020/260631, PCT Pub. Date Dec. 30, 2020.
Claims priority of application No. 19182740 (EP), filed on Jun. 26, 2019.
Prior Publication US 2022/0221325 A1, Jul. 14, 2022
Int. Cl. G01G 17/08 (2006.01); A01K 29/00 (2006.01); G06V 10/44 (2022.01); G06V 40/10 (2022.01)
CPC G01G 17/08 (2013.01) [A01K 29/00 (2013.01); G06V 10/44 (2022.01); G06V 40/10 (2022.01)] 21 Claims
OG exemplary drawing
 
1. A computer implemented method for automatically determining a weight of a bovine subject with a known breed, the method comprising:
acquiring at least one 3D image of a back of the bovine subject from an optical device disposed in an aisle via a data connection with the optical device, wherein the optical device is positioned to capture the back of the bovine subject as the bovine subject passes through the aisle;
extracting data in the form of a discrete number of contour points from the at least one 3D image relating to a topology of the back of the bovine subject, the contour points extracted relative to a line of local maxima along the back of the bovine subject; and
calculating the weight of the bovine subject by directly correlating the contour points against a reference model comprising information relating to the topology of the back versus the weight for the breed of the bovine subject, the reference model further comprising non- volumetric topological characteristics specific to the breed of the bovine subject, the non- volumetric topological characteristics being associated with breed-specific weight patterns that account for localized shape variations and structural differences across bovine breeds.