Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020089285 - AUTOMATED GENERATION OF TRAINING IMAGES

Publication Number WO/2020/089285
Publication Date 07.05.2020
International Application No. PCT/EP2019/079629
International Filing Date 30.10.2019
IPC
G06K 9/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G06K 9/62 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
CPC
G06K 9/0063
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
00624Recognising scenes, i.e. recognition of a whole field of perception; recognising scene-specific objects
0063Recognising patterns in remote scenes, e.g. aerial images, vegetation versus urban areas
G06K 9/6256
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
Applicants
  • AIRBUS DEFENSE AND SPACE GMBH [DE]/[DE]
Inventors
  • MOHRDIECK, Camilla
  • WIEDMANN, Michael
  • ZIMMERMANN, Reiner
Agents
  • FRENKEL, Matthias
Priority Data
18203504.830.10.2018EP
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) AUTOMATED GENERATION OF TRAINING IMAGES
(FR) GÉNÉRATION AUTOMATISÉE D'IMAGES D'APPRENTISSAGE
Abstract
(EN)
A method for providing training images is provided. The method comprises receiving information about objects. The information is at least valid at a specific recording time. The method comprises receiving an image of an area. The area is imaged at the specific recording time. The method comprises estimating respective positions of the objects at the specific recording time based on the information. The method comprises selecting estimated positions of respective objects from the estimated respective positions which fulfill a predefined selection criterion. The method comprises generating training images by separating the imaged area into a first plurality of image tiles and a second plurality of image tiles. Each of the first plurality of image tiles differs from each of the second plurality of image tiles. Each of the first plurality of image tiles images (depicts) a respective one or several of the selected positions. The method comprises providing the training images. Further, a training image product and a device for providing training images are provided.
(FR)
L'invention porte sur un procédé de fourniture d'images d'apprentissage. Le procédé consiste à recevoir des informations concernant des objets. Les informations sont au moins valides à un moment d'enregistrement spécifique. Le procédé consiste à recevoir une image d'une zone. La zone est imagée au moment d'enregistrement spécifique. Le procédé consiste à estimer des positions respectives des objets au moment d'enregistrement spécifique sur la base des informations. Le procédé consiste à sélectionner des positions estimées d'objets respectifs à partir des positions respectives estimées qui remplissent un critère de sélection prédéfini. Le procédé consiste à générer des images d'apprentissage en séparant la zone imagée en une première pluralité de pavés d'image et en une seconde pluralité de pavés d'image. Chacun de la première pluralité de pavés d'image diffère de chacun de la seconde pluralité de pavés d'image. Chacun de la première pluralité de pavés d'image (représente) une ou plusieurs parmi les positions sélectionnées. Le procédé consiste à fournir les images d'apprentissage. En outre, l'invention concerne un produit d'image d'apprentissage et un dispositif destiné à fournir des images d'apprentissage.
Also published as
Latest bibliographic data on file with the International Bureau