Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021030414 - AUTOMATIC HIGH BEAM CONTROL FOR AUTONOMOUS MACHINE APPLICATIONS

Publication Number WO/2021/030414
Publication Date 18.02.2021
International Application No. PCT/US2020/045888
International Filing Date 12.08.2020
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
G06K 9/20 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
20Image acquisition
G06K 9/40 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
40Noise filtering
G06N 3/02 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
G06T 7/10 2017.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
10Segmentation; Edge detection
CPC
B60Q 1/076
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
QARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
1Arrangements or adaptations of optical signalling or lighting devices
02the devices being primarily intended to illuminate the way ahead or to illuminate other areas of way or environments
04the devices being headlights
06adjustable, e.g. remotely controlled from inside vehicle
076by electrical means ; including means to transmit the movements, e.g. shafts or joints
B60Q 1/143
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
QARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
1Arrangements or adaptations of optical signalling or lighting devices
02the devices being primarily intended to illuminate the way ahead or to illuminate other areas of way or environments
04the devices being headlights
14having dimming means
1415Dimming circuits
1423Automatic dimming circuits, i.e. switching between high beam and low beam due to change of ambient light or light level in road traffic
143combined with another condition, e.g. using vehicle recognition from camera images or activation of wipers
B60Q 2300/056
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
QARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
2300Indexing codes for automatically adjustable headlamps or automatically dimmable headlamps
05Special features for controlling or switching of the light beam
056Special anti-blinding beams, e.g. a standard beam is chopped or moved in order not to blind
B60Q 2300/41
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
QARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
2300Indexing codes for automatically adjustable headlamps or automatically dimmable headlamps
40Indexing codes relating to other road users or special conditions
41preceding vehicle
B60Q 2300/42
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
QARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
2300Indexing codes for automatically adjustable headlamps or automatically dimmable headlamps
40Indexing codes relating to other road users or special conditions
42oncoming vehicle
B60Q 2300/45
BPERFORMING OPERATIONS; TRANSPORTING
60VEHICLES IN GENERAL
QARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
2300Indexing codes for automatically adjustable headlamps or automatically dimmable headlamps
40Indexing codes relating to other road users or special conditions
45Special conditions, e.g. pedestrians, road signs or potential dangers
Applicants
  • NVIDIA CORPORATION [US]/[US]
Inventors
  • LI, Jincheng
  • PARK, Minwoo
Agents
  • ALCANTARA, Jaclyn S.
  • BACON, Kirk D.
  • SCHNAYER, Jeffrey R.
Priority Data
16/991,24212.08.2020US
62/885,77412.08.2019US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) AUTOMATIC HIGH BEAM CONTROL FOR AUTONOMOUS MACHINE APPLICATIONS
(FR) COMMANDE AUTOMATIQUE DE FAISCEAU ÉLEVÉ POUR DES APPLICATIONS DE MACHINE AUTONOME
Abstract
(EN)
In various examples, high beam control for vehicles may be automated using a deep neural network (DNN) that processes sensor data received from vehicle sensors. The DNN may process the sensor data to output pixel-level semantic segmentation masks in order to differentiate actionable objects (e.g., vehicles with front or back lights lit, bicyclists, or pedestrians) from other objects (e.g., parked vehicles). Resulting segmentation masks output by the DNN(s), when combined with one or more post processing steps, may be used to generate masks for automated high beam on/off activation and/or dimming or shading – thereby providing additional illumination of an environment for the driver while controlling downstream effects of high beam glare for active vehicles.
(FR)
Dans divers exemples, une commande de faisceau élevée pour des véhicules peut être automatisée à l'aide d'un réseau neuronal profond (DNN) qui traite des données de capteur reçues en provenance de capteurs de véhicule. Le DNN peut traiter les données de capteur pour délivrer en sortie des masques de segmentation sémantique de niveau de pixel afin de différencier des objets exploitables (par exemple, des véhicules ayant des feux avant ou arrière allumés, des cyclistes ou des piétons) à partir d'autres objets (par exemple, des véhicules en stationnement). Des masques de segmentation résultants fournis par le ou les DNN, lorsqu'ils sont combinés à une ou plusieurs étapes de post-traitement, peuvent être utilisés pour générer des masques pour une activation/désactivation et/ou gradation ou ombrage automatisé(e) de faisceau élevé, ce qui permet d'obtenir un éclairage supplémentaire d'un environnement pour le conducteur tout en commandant les effets en aval d'éblouissement de faisceau élevé pour des véhicules actifs.
Latest bibliographic data on file with the International Bureau