Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020141549 - OBJECT CLASSIFICATION USING MACHINE LEARNING

Publication Number WO/2020/141549
Publication Date 09.07.2020
International Application No. PCT/IN2019/050969
International Filing Date 31.12.2019
IPC
G01S 13/89 2006.01
GPHYSICS
01MEASURING; TESTING
SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
13Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
88Radar or analogous systems, specially adapted for specific applications
89for mapping or imaging
G01S 13/93 2020.01
GPHYSICS
01MEASURING; TESTING
SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
13Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
88Radar or analogous systems, specially adapted for specific applications
93for anti-collision purposes
CPC
G01S 13/931
GPHYSICS
01MEASURING; TESTING
SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
13Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
88Radar or analogous systems specially adapted for specific applications
93for anti-collision purposes
931of land vehicles
G01S 7/417
GPHYSICS
01MEASURING; TESTING
SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
7Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
02of systems according to group G01S13/00
41using analysis of echo signal for target characterisation; Target signature; Target cross-section
417involving the use of neural networks
G06N 20/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
Applicants
  • ATAI LABS PVT LTD. [IN]/[IN]
Inventors
  • KHAIRMODE, Vijay Shankar
  • DEVARA, VamsiKrishna
  • BALASUBRAMANIAN, Aanandh Suttamalli
  • BOMMENA, Vidya Manoher
  • GUDE, Gangadhar
  • ARUMILLI, Kishor Bulli
Agents
  • LAKSHMIKUMARAN, Malathi
  • PHILLIPS, Prashant
  • RAE, Konpal
  • PANDEYA, Jaya
  • SRINIVASAN, T.
Priority Data
20184105010231.12.2018IN
20184105010631.12.2018IN
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) OBJECT CLASSIFICATION USING MACHINE LEARNING
(FR) CLASSIFICATION D'OBJETS PAR APPRENTISSAGE AUTOMATIQUE
Abstract
(EN)
Techniques of machine learning of a radar are disclosed, where the radar has a plurality of antennas that are arranged on an antenna array. In an example, a method of machine learning includes obtaining a real training sample from a first real target in field of view of the radar, where the real training sample includes a plurality of first real data signals, where each of the first real data signals are obtained from a corresponding antenna from amongst the plurality of antennas. The method further includes deriving a synthetic training sample by manipulating the plurality of first real data signals to simulate a rotation of the first real target about a pre-determined axis of the antenna array.
(FR)
L'invention concerne des techniques d'apprentissage automatique pour un radar comprenant une pluralité d'antennes agencées sur un réseau d'antennes. Dans un exemple, l'invention concerne un procédé d'apprentissage automatique consistant à obtenir un échantillon d'apprentissage réel à partir d'une première cible réelle dans le champ de vision du radar, l'échantillon d'apprentissage réel comprenant une pluralité de premiers signaux de données réelles, chacun des premiers signaux étant obtenu à partir d'une antenne correspondante parmi la pluralité d'antennes. Le procédé selon l'invention consiste également à obtenir un échantillon d'apprentissage synthétique par manipulation de la pluralité de premiers signaux de données réelles afin de simuler une rotation de la première cible réelle autour d'un axe prédéterminé du réseau d'antennes.
Latest bibliographic data on file with the International Bureau