Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020114780 - METHOD FOR PREDICTING MULTIPLE FUTURES

Publication Number WO/2020/114780
Publication Date 11.06.2020
International Application No. PCT/EP2019/081984
International Filing Date 20.11.2019
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 9/46 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
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
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 9/00791
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
00791Recognising scenes perceived from the perspective of a land vehicle, e.g. recognising lanes, obstacles or traffic signs on road scenes
G06K 9/4619
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
36Image preprocessing, i.e. processing the image information without deciding about the identity of the image
46Extraction of features or characteristics of the image
4604Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes, intersections
4609by matching or filtering
4619Biologically-inspired filters, e.g. receptive fields
G06K 9/6271
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
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
627based on distances between the pattern to be recognised and training or reference patterns
6271based on distances to prototypes
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
Applicants
  • IMRA EUROPE S.A.S. [FR]/[FR]
Inventors
  • ABAD, Frédéric
  • TSISHKOU, Dzmitry
  • BENDAHAN, Rémy
  • MIOULET, Luc
Agents
  • VIGAND, Philippe
  • PAUTEX SCHNEIDER, Nicole
  • BALSTERS, Robert
  • POINDRON, Cyrille
  • STEPHANN, Valérie
  • ROUX, Stéphane
Priority Data
18306623.205.12.2018EP
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) METHOD FOR PREDICTING MULTIPLE FUTURES
(FR) PROCÉDÉ DE PRÉDICTION DE MULTIPLES FUTURS
Abstract
(EN)
A computer-implemented method comprising an operating phase comprising the steps of receiving one or several video frames from a plurality of modalities, so-called multi-modality video frames, of a vehicle's environment, corresponding to present and past timestamps; encoding into a latent representation, said multi-modality video frames by a spatial-temporal encoding convolutional neural network (E); combining into a composite representation (Z), said latent representation with encoded conditioning parameters corresponding to timestamps at the desired future time horizon; predicting multiple future multi-modality video frames corresponding to multiple future modes of a multi-modal future solution space associated with likelihood coefficients by a generative convolutional neural network (G) previously trained in a generative adversarial network training scheme.
(FR)
L'invention concerne un procédé mis en œuvre par ordinateur comprenant une phase de fonctionnement qui comprend les étapes suivantes : réception d'une ou plusieurs trames vidéo parmi une pluralité de modalités, appelées trames vidéo à modalités multiples, de l'environnement d'un véhicule, correspondant à des estampilles temporelles présentes et passées; codage en une représentation latente desdites trames vidéo à modalités multiples par un réseau neuronal convolutif de codage spatio-temporel (E); combinaison en une représentation composite (Z) de ladite représentation latente avec des paramètres de conditionnement codés correspondant aux estampilles temporelles à l'horizon temporel futur souhaité; prédiction de trames vidéo à modalités multiples futures multiples correspondant à de multiples modes futurs d'un espace de solution future multimodale associé à des coefficients de vraisemblance par un réseau neuronal convolutif génératif (G) préalablement entraîné dans un schéma d'entraînement de réseau contradictoire génératif.
Also published as
Latest bibliographic data on file with the International Bureau