US 12,223,749 B2
Object recognition method with increased representativeness
Ion Berechet, Vincennes (FR); Gérard Berginc, Elancourt (FR); and Stefan Berechet, Vincennes (FR)
Assigned to THALES, Courbevoie (FR); and SISPIA, Vincennes (FR)
Appl. No. 17/767,907
Filed by THALES, Courbevoie (FR); and SISPIA, Vincennes (FR)
PCT Filed Oct. 8, 2020, PCT No. PCT/EP2020/078197
§ 371(c)(1), (2) Date Apr. 10, 2022,
PCT Pub. No. WO2021/069536, PCT Pub. Date Apr. 15, 2021.
Claims priority of application No. 1911224 (FR), filed on Oct. 10, 2019.
Prior Publication US 2023/0222820 A1, Jul. 13, 2023
Int. Cl. G06V 20/64 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01)
CPC G06V 20/647 (2022.01) [G06V 10/774 (2022.01); G06V 10/82 (2022.01); G06V 2201/07 (2022.01)] 7 Claims
OG exemplary drawing
 
1. A method for recognizing an object of interest in a degraded 2D digital image of said object, comprising the following steps: detecting, beforehand, the object of interest in a 2D digital image and assigning it a label; reconstructing a 3D volume of said object thus labeled from a plurality of available 2D digital images of said object of interest; storing, in a database, a record relating to said object thus reconstructed in 3D form and labeled; for each record thus stored, generating a new plurality of 2D digital images according to a plurality of viewing modes from the thus reconstructed 3D volume of each object, the viewing modes comprising exposure modes with different levels of occlusion and/or of added noise; training a neural network on a learning set composed of an expanded set of 2D digital images thus generated and corresponding with the label of the object of interest to be recognized; from a degraded 2D digital image of said object of interest to be recognized, using the neural network thus trained to deliver as output the label of the object and a confidence index linked to the recognition of the object of interest.