US 11,922,651 B2
Systems and methods for utilizing a deep learning model to determine vehicle viewpoint estimations
Simone Magistri, San Casciano in Val di Pesa (IT); Francesco Sambo, Florence (IT); Douglas Coimbra De Andrade, Florence (IT); Fabio Schoen, Florence (IT); Matteo Simoncini, Pistoia (IT); Luca Bravi, Scandicci (IT); Stefano Caprasecca, Florence (IT); Luca Kubin, Collecchio (IT); and Leonardo Taccari, Florence (IT)
Assigned to Verizon Connect Development Limited, Dublin (IE)
Filed by Verizon Connect Development Limited, Dublin (IE)
Filed on Dec. 2, 2022, as Appl. No. 18/061,124.
Application 18/061,124 is a continuation of application No. 17/001,166, filed on Aug. 24, 2020, granted, now 11,532,096.
Claims priority of application No. 102020000011875 (IT), filed on May 21, 2020.
Prior Publication US 2023/0102113 A1, Mar. 30, 2023
Int. Cl. G06T 7/70 (2017.01); G06N 3/08 (2023.01); G06V 20/56 (2022.01)
CPC G06T 7/70 (2017.01) [G06N 3/08 (2013.01); G06V 20/56 (2022.01); G06T 2207/20076 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30252 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
extracting, by a device, a first image from a second image based on a location of an object within the first image;
grouping, by the device, a series of probabilities associated with the first image into a first quantity of groups;
determining, by the device, a coarse-grained viewpoint estimate associated with the object based on grouping the series of probabilities into the first quantity of groups;
determining, by the device, a fine-grained viewpoint estimate associated with the object based on grouping the series of probabilities into a second quantity of groups,
wherein the second quantity of groups is greater than the first quantity of groups;
determining, by the device, an object viewpoint associated with the object based on at least one of the coarse-grained viewpoint estimate or the fine-grained viewpoint estimate; and
performing, by the device, one or more actions based on the object viewpoint.