WO2019042728A3 - Reconnaissance d'usagers de la route sur une voie de circulation - Google Patents

Reconnaissance d'usagers de la route sur une voie de circulation Download PDF

Info

Publication number
WO2019042728A3
WO2019042728A3 PCT/EP2018/071494 EP2018071494W WO2019042728A3 WO 2019042728 A3 WO2019042728 A3 WO 2019042728A3 EP 2018071494 W EP2018071494 W EP 2018071494W WO 2019042728 A3 WO2019042728 A3 WO 2019042728A3
Authority
WO
WIPO (PCT)
Prior art keywords
road users
traffic route
detection
object detection
suggested regions
Prior art date
Application number
PCT/EP2018/071494
Other languages
German (de)
English (en)
Other versions
WO2019042728A2 (fr
Inventor
Sikandar Amin
Fabio Galasso
Herbert Kaestle
Original Assignee
Osram Gmbh
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Osram Gmbh filed Critical Osram Gmbh
Publication of WO2019042728A2 publication Critical patent/WO2019042728A2/fr
Publication of WO2019042728A3 publication Critical patent/WO2019042728A3/fr

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
    • G08G1/0116—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from roadside infrastructure, e.g. beacons
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
    • G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/04—Detecting movement of traffic to be counted or controlled using optical or ultrasonic detectors
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/07—Controlling traffic signals
    • G08G1/08—Controlling traffic signals according to detected number or speed of vehicles

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Evolutionary Computation (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Traffic Control Systems (AREA)

Abstract

L'invention concerne un procédé (10) de reconnaissance d'usagers de la route (12) sur une voie de circulation (14) dans une image. Le procédé comprend : - générer (42) une pluralité de propositions de zone (18) pour des objets possibles, enregistrés dans l'image (16), par application d'un générateur de propositions de zone ; - fournir la détection d'objet (72) pour toutes les propositions de zone (18) afin de détecter la voie de circulation (14) et/ou les usagers de la route (12) par classification avec prise en compte d'un niveau de confiance prédéfini ; - délivrer des données de détection, qui sont reçues par la détection d'objet ; et - fournir un filtrage (48) pour les propositions de zone (18) avant l'étape consistant à fournir une détection d'objet, le filtrage étant effectué sur la base de données de filtrage respectives, estimé sur la base d'une pertinence des propositions de zone (18) concernant les usagers de la route (12) et/ou la voie de circulation (14).
PCT/EP2018/071494 2017-08-29 2018-08-08 Reconnaissance d'usagers de la route sur une voie de circulation WO2019042728A2 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102017215079.3 2017-08-29
DE102017215079.3A DE102017215079A1 (de) 2017-08-29 2017-08-29 Erfassen von Verkehrsteilnehmern auf einem Verkehrsweg

Publications (2)

Publication Number Publication Date
WO2019042728A2 WO2019042728A2 (fr) 2019-03-07
WO2019042728A3 true WO2019042728A3 (fr) 2019-04-25

Family

ID=63259495

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2018/071494 WO2019042728A2 (fr) 2017-08-29 2018-08-08 Reconnaissance d'usagers de la route sur une voie de circulation

Country Status (2)

Country Link
DE (1) DE102017215079A1 (fr)
WO (1) WO2019042728A2 (fr)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102019007057B4 (de) 2019-10-10 2022-06-30 CGF Counsel Group Frankfurt AG AUßENBEREICHSVORRICHTUNG MIT ELEKTRONISCHER KOMPONENTE
DE102019007058A1 (de) 2019-10-10 2021-04-15 CGF Counsel Group Frankfurt AG Vorrichtung innerhalb eines masts und verfahren
CN113139427A (zh) * 2021-03-12 2021-07-20 浙江智慧视频安防创新中心有限公司 基于深度学习的蒸汽管网智能监控方法、系统及设备
DE102021117613A1 (de) 2021-07-08 2023-01-12 Valeo Schalter Und Sensoren Gmbh Verfahren zum betreiben eines parkassistenzsystems, computerprogrammprodukt und parkassistenzsystem
CN113807270A (zh) 2021-09-22 2021-12-17 北京百度网讯科技有限公司 道路拥堵检测方法、装置及电子设备
CN117710795B (zh) * 2024-02-06 2024-06-07 成都同步新创科技股份有限公司 一种基于深度学习的机房线路安全性检测方法及系统

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104658279A (zh) * 2015-02-17 2015-05-27 公安部交通管理科学研究所 基于视频通行状态监测的实时优化信号控制方法及系统

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102473307B (zh) * 2010-03-15 2015-05-27 松下电器产业株式会社 用于轨迹估计的方法和装置以及用于分割的方法
US9947077B2 (en) * 2013-12-31 2018-04-17 Thomson Licensing Video object tracking in traffic monitoring
JP6604019B2 (ja) * 2015-04-14 2019-11-13 ソニー株式会社 画像処理装置、画像処理方法、および画像処理システム

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104658279A (zh) * 2015-02-17 2015-05-27 公安部交通管理科学研究所 基于视频通行状态监测的实时优化信号控制方法及系统

Non-Patent Citations (9)

* Cited by examiner, † Cited by third party
Title
"Medical image computing and computer-assisted intervention - MICCAI 2015 : 18th international conference, Munich, Germany, October 5-9, 2015; proceedings", vol. 8691, 1 January 2014, SPRINGER INTERNATIONAL PUBLISHING, Cham, ISBN: 978-3-642-38081-5, ISSN: 0302-9743, article XINGYU ZENG ET AL: "Deep Learning of Scene-Specific Classifier for Pedestrian Detection", pages: 472 - 487, XP055424079, 032548, DOI: 10.1007/978-3-319-10578-9_31 *
ALA MHALLA ET AL: "SMC faster R-CNN: Toward a scene-specialized multi-object detector", COMPUTER VISION AND IMAGE UNDERSTANDING., vol. 164, 30 June 2017 (2017-06-30), US, pages 3 - 15, XP055521016, ISSN: 1077-3142, DOI: 10.1016/j.cviu.2017.06.008 *
ANDREAS GEIGER ET AL: "Joint 3D Estimation of Objects and Scene Layout", 1 January 2011 (2011-01-01), XP055520458, Retrieved from the Internet <URL:http://www.cs.utoronto.ca/~urtasun/publications/geiger_et_al_nips11.pdf> [retrieved on 20181031] *
CHEN XIAOZHI ET AL: "Monocular 3D Object Detection for Autonomous Driving", 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), IEEE, 27 June 2016 (2016-06-27), pages 2147 - 2156, XP033021394, DOI: 10.1109/CVPR.2016.236 *
JIFENG DAI ET AL: "R-FCN: Object Detection via Region-based Fully Convolutional Networks", IADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS, 21 June 2016 (2016-06-21), XP055486238, Retrieved from the Internet <URL:https://arxiv.org/pdf/1605.06409.pdf> [retrieved on 20180620] *
LI-WU TSAI ET AL: "Multi-Lane Detection and Road Traffic Congestion Classification for Intelligent Transportation System", ENERGY PROCEDIA, 1 January 2011 (2011-01-01), pages 3174 - 3182, XP055553257, Retrieved from the Internet <URL:https://pdfs.semanticscholar.org/8f30/70c51793f30ea7b6afd1ab1a8c193b9fc7fd.pdf> DOI: 10.1016/j.egypro.2011.11.460 *
MAYANK BANSAL ET AL: "A real-time pedestrian detection system based on structure and appearance classification", 2010 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION : ICRA 2010 ; ANCHORAGE, ALASKA, USA, 3 - 8 MAY 2010, IEEE, PISCATAWAY, NJ, USA, 3 May 2010 (2010-05-03), pages 903 - 909, XP031743776, ISBN: 978-1-4244-5038-1 *
SCOTT PENDLETON ET AL: "Perception, Planning, Control, and Coordination for Autonomous Vehicles", MACHINES, vol. 5, no. 1, 17 February 2017 (2017-02-17), pages 6, XP055553408, DOI: 10.3390/machines5010006 *
WANG XIAOGANG ET AL: "Scene-Specific Pedestrian Detection for Static Video Surveillance", IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, IEEE COMPUTER SOCIETY, USA, vol. 36, no. 2, 1 February 2014 (2014-02-01), pages 361 - 374, XP011534231, ISSN: 0162-8828, [retrieved on 20131218], DOI: 10.1109/TPAMI.2013.124 *

Also Published As

Publication number Publication date
DE102017215079A1 (de) 2019-02-28
WO2019042728A2 (fr) 2019-03-07

Similar Documents

Publication Publication Date Title
WO2019042728A3 (fr) Reconnaissance d&#39;usagers de la route sur une voie de circulation
MX2017000688A (es) Deteccion de peatones con mapas de prominencia.
WO2018132607A3 (fr) Navigation basée sur une activité de véhicule
EP3506169A3 (fr) Système d&#39;assistance au conducteur et procédé de détection d&#39;objet et de notification
WO2013188807A3 (fr) Procédés et systèmes de traitement de signaux
WO2018080932A8 (fr) Système et procédé de détection d&#39;obstacle
WO2015041872A8 (fr) Procédé et appareil destinés à fournir sélectivement des informations concernant des objets dans une image capturée
MX2018004708A (es) Metodo y dispositivo de deteccion de linea del espacio de estacionamiento.
WO2016042325A3 (fr) Détection d&#39;un signal de brouillage gnss
MX2018001483A (es) Sistemas y metodos para detectar tornados.
MX2020014325A (es) Sistemas y métodos para determinar un evento malicioso potencial.
MX354764B (es) Dispositivo de deteccion de semaforo y metodo de deteccion de semaforo.
IL226747B (en) A system and method for studying malware detection
WO2016050347A3 (fr) Dispositif d&#39;identification audio, procédé d&#39;identification audio et système d&#39;identification audio
EP3203417A3 (fr) Procédé pour détecter des textes inclus dans une image et appareil l&#39;utilisant
MX2018001229A (es) Metodo de control de desplazamiento y aparato de control de desplazamiento.
WO2013003778A3 (fr) Procédé et appareil pour déterminer et utiliser une valeur de biens numériques
GB2551288A (en) Detecting the location of a mobile device based on semantic indicators
WO2022098511A3 (fr) Architecture de détection de changement de carte dans des véhicules autonomes
WO2014006386A3 (fr) Procédé et système d&#39;identification d&#39;un document de sécurité
JP2009070344A (ja) 画像認識装置、画像認識方法および電子制御装置
WO2016077784A3 (fr) Système de sonorisation (pa) compatible avec un dispositif de communication personnel sensible à la localisation
AU2018253963A1 (en) Detection system, detection device and method therefor
MX2017009709A (es) Metodo para clasificar la autoria de una pintura y un uso correspondiente.
MX2017012143A (es) Sistemas y metodos para la deteccion de puentes de metal.

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18756389

Country of ref document: EP

Kind code of ref document: A2

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18756389

Country of ref document: EP

Kind code of ref document: A2