Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020110802 - ON-VEHICLE OBJECT IDENTIFICATION SYSTEM, AUTOMOBILE, VEHICLE LAMP, CLASSIFIER LEARNING METHOD, AND ARITHMETIC OPERATION DEVICE

Publication Number WO/2020/110802
Publication Date 04.06.2020
International Application No. PCT/JP2019/045095
International Filing Date 18.11.2019
IPC
G01S 17/89 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
17Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
88Lidar systems, specially adapted for specific applications
89for mapping or imaging
G06T 7/00 2017.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
G06T 7/521 2017.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
50Depth or shape recovery
521from laser ranging, e.g. using interferometry; from the projection of structured light
G08G 1/16 2006.01
GPHYSICS
08SIGNALLING
GTRAFFIC CONTROL SYSTEMS
1Traffic control systems for road vehicles
16Anti-collision systems
CPC
G01S 17/89
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
17Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
88Lidar systems specially adapted for specific applications
89for mapping or imaging
G06K 9/00
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
G06K 9/62
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
G06T 7/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
G06T 7/521
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
50Depth or shape recovery
521from laser ranging, e.g. using interferometry; from the projection of structured light
G08G 1/16
GPHYSICS
08SIGNALLING
GTRAFFIC CONTROL SYSTEMS
1Traffic control systems for road vehicles
16Anti-collision systems
Applicants
  • 株式会社小糸製作所 KOITO MANUFACTURING CO.,LTD. [JP]/[JP]
Inventors
  • 永島 徹 NAGASHIMA Toru
Agents
  • 森下 賢樹 MORISHITA Sakaki
Priority Data
2018-22576230.11.2018JP
Publication Language Japanese (JA)
Filing Language Japanese (JA)
Designated States
Title
(EN) ON-VEHICLE OBJECT IDENTIFICATION SYSTEM, AUTOMOBILE, VEHICLE LAMP, CLASSIFIER LEARNING METHOD, AND ARITHMETIC OPERATION DEVICE
(FR) SYSTÈME D'IDENTIFICATION D'OBJET EMBARQUÉ, AUTOMOBILE, LAMPE DE VÉHICULE, PROCÉDÉ D'APPRENTISSAGE DE CLASSIFICATEUR ET DISPOSITIF D'OPÉRATION ARITHMÉTIQUE
(JA) 車載用物体識別システム、自動車、車両用灯具、分類器の学習方法、演算処理装置
Abstract
(EN)
An on-vehicle object identification system 10 is provided with; a ranging sensor 20; and an arithmetic operation device 40. The ranging sensor 20 horizontally scans one beam, and measures the distance to a point P on the surface of an object OBJ. The arithmetic operation device 40 includes a classifier 42 that can identify the type of the object OBJ on the basis of point collection data PCD corresponding to one scan line SL acquired by the ranging sensor 20. The classifier 42 is mounted on the basis of a learned model acquired through machine learning. The machine learning is carried out by using a plurality of point collection data corresponding to a plurality of scan lines acquired through measurement of a prescribed object by a LiDAR having the scan lines in the vertical direction.
(FR)
Système d'identification d'objet embarqué 10 pourvu d'un capteur de télémétrie 20 ; et d'un dispositif d'opération arithmétique 40. Le capteur de télémétrie 20 balaye horizontalement un faisceau, et mesure la distance jusqu'à un point P sur la surface d'un objet OBJ. Le dispositif d'opération arithmétique 40 comprend un classificateur 42 qui peut identifier le type de l'objet OBJ sur la base de données de collecte de points PCD correspondant à une ligne de balayage SL acquise par le capteur de télémétrie 20. Le classificateur 42 est monté sur la base d'un modèle appris acquis par apprentissage automatique. L'apprentissage automatique est réalisé à l'aide d'une pluralité de données de collecte de points correspondant à une pluralité de lignes de balayage acquises par la mesure d'un objet prescrit par un LiDAR ayant les lignes de balayage dans la direction verticale.
(JA)
車載用の物体識別システム10は、測距センサ20および演算処理装置40を備える。測距センサ20は、1本のビームを水平方向にスキャンし、物体OBJの表面上の点Pまでの距離を測定する。演算処理装置40は、測距センサ20により得られる1本のスキャンラインSLに対応する点群データPCDにもとづいて、物体OBJの種類を識別可能な分類器42を含む。分類器42は、機械学習により得られた学習済みモデルにもとづいて実装される。機械学習は、鉛直方向に複数のスキャンラインを有するLiDARによって所定の物体を測定して得られる、複数のスキャンラインに対応する複数の点群データを利用して行われる。
Latest bibliographic data on file with the International Bureau