MX2017014963A - Deteccion y clasificacion de semaforos mediante el uso de vision informatica y aprendizaje profundo. - Google Patents

Deteccion y clasificacion de semaforos mediante el uso de vision informatica y aprendizaje profundo.

Info

Publication number
MX2017014963A
MX2017014963A MX2017014963A MX2017014963A MX2017014963A MX 2017014963 A MX2017014963 A MX 2017014963A MX 2017014963 A MX2017014963 A MX 2017014963A MX 2017014963 A MX2017014963 A MX 2017014963A MX 2017014963 A MX2017014963 A MX 2017014963A
Authority
MX
Mexico
Prior art keywords
traffic
frame
classification
deep learning
light detection
Prior art date
Application number
MX2017014963A
Other languages
English (en)
Inventor
Nariyambut Murali Vidya
J Goh Madeline
Zhang Yi
Moosaei Maryam
Original Assignee
Ford Global Tech Llc
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 Ford Global Tech Llc filed Critical Ford Global Tech Llc
Publication of MX2017014963A publication Critical patent/MX2017014963A/es

Links

Classifications

    • 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
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • G06V20/584—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of vehicle lights or traffic lights
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T5/00—Image enhancement or restoration
    • G06T5/90—Dynamic range modification of images or parts thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/09—Arrangements for giving variable traffic instructions
    • G08G1/095—Traffic lights
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20024—Filtering details
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20132—Image cropping

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)

Abstract

Se describe un método para detectar y clasificar uno o más semáforos. El método puede incluir convertir un cuadro RGB en un cuadro HSV. El cuadro HSV puede filtrarse en al menos un valor de umbral para obtener al menos un cuadro de saturación. Se puede extraer al menos un contorno de al menos un cuadro de saturación. Por consiguiente, se puede recortar una primera parte del RGB con el fin de abarcar un área que incluye el al menos un contorno. La primera parte puede clasificarse entonces por una red neural artificial para determinar si la primera parte corresponde a una clase de no semáforo, una clase de semáforo en rojo, una clase de semáforo verde, una clase de semáforo en amarillo o similares.
MX2017014963A 2016-11-23 2017-11-22 Deteccion y clasificacion de semaforos mediante el uso de vision informatica y aprendizaje profundo. MX2017014963A (es)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US15/360,883 US10185881B2 (en) 2016-11-23 2016-11-23 Traffic-light detection and classification using computer vision and deep learning

Publications (1)

Publication Number Publication Date
MX2017014963A true MX2017014963A (es) 2018-10-04

Family

ID=60805820

Family Applications (1)

Application Number Title Priority Date Filing Date
MX2017014963A MX2017014963A (es) 2016-11-23 2017-11-22 Deteccion y clasificacion de semaforos mediante el uso de vision informatica y aprendizaje profundo.

Country Status (6)

Country Link
US (3) US10185881B2 (es)
CN (1) CN108090411B (es)
DE (1) DE102017127489A1 (es)
GB (1) GB2559005A (es)
MX (1) MX2017014963A (es)
RU (1) RU2017135215A (es)

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10185881B2 (en) * 2016-11-23 2019-01-22 Ford Global Technologies, Llc Traffic-light detection and classification using computer vision and deep learning
JP6834425B2 (ja) * 2016-12-02 2021-02-24 スズキ株式会社 運転支援装置
US10650257B2 (en) * 2017-02-09 2020-05-12 SMR Patents S.à.r.l. Method and device for identifying the signaling state of at least one signaling device
US10614326B2 (en) * 2017-03-06 2020-04-07 Honda Motor Co., Ltd. System and method for vehicle control based on object and color detection
US11069234B1 (en) 2018-02-09 2021-07-20 Applied Information, Inc. Systems, methods, and devices for communication between traffic controller systems and mobile transmitters and receivers
CN108830199B (zh) 2018-05-31 2021-04-16 京东方科技集团股份有限公司 识别交通灯信号的方法、装置、可读介质及电子设备
US11205345B1 (en) 2018-10-02 2021-12-21 Applied Information, Inc. Systems, methods, devices, and apparatuses for intelligent traffic signaling
CN109508635B (zh) * 2018-10-08 2022-01-07 海南师范大学 一种基于TensorFlow结合多层CNN网络的交通灯识别方法
US11056005B2 (en) 2018-10-24 2021-07-06 Waymo Llc Traffic light detection and lane state recognition for autonomous vehicles
JP7172441B2 (ja) * 2018-10-25 2022-11-16 トヨタ自動車株式会社 進行可能方向検出装置及び進行可能方向検出方法
US10467487B1 (en) * 2018-12-11 2019-11-05 Chongqing Jinkang New Energy Automobile Co., Ltd. Fusion-based traffic light recognition for autonomous driving
CN111723614A (zh) * 2019-03-20 2020-09-29 北京四维图新科技股份有限公司 交通信号灯识别方法及装置
DE102019207580A1 (de) 2019-05-23 2020-11-26 Volkswagen Aktiengesellschaft Verfahren zum Betreiben eines tiefen Neuronalen Netzes
US10944912B2 (en) 2019-06-04 2021-03-09 Ford Global Technologies, Llc Systems and methods for reducing flicker artifacts in imaged light sources
CN110633635A (zh) * 2019-08-08 2019-12-31 北京联合大学 一种基于roi的交通标志牌实时检测方法及系统
DE102019129029A1 (de) * 2019-10-28 2021-04-29 Bayerische Motoren Werke Aktiengesellschaft System und verfahren zur objektdetektion
US11210571B2 (en) 2020-03-13 2021-12-28 Argo AI, LLC Using rasterization to identify traffic signal devices
CN111723690B (zh) * 2020-06-03 2023-10-20 北京全路通信信号研究设计院集团有限公司 一种电路设备状态监测方法和系统
US11900689B1 (en) * 2020-06-04 2024-02-13 Aurora Operations, Inc. Traffic light identification and/or classification for use in controlling an autonomous vehicle
US11704912B2 (en) * 2020-06-16 2023-07-18 Ford Global Technologies, Llc Label-free performance evaluator for traffic light classifier system
EP4286809A4 (en) 2021-03-03 2024-01-10 Mitsubishi Electric Corporation SIGNAL PROCESSING DEVICE, CONTROL CIRCUIT, STORAGE MEDIUM AND SIGNAL PROCESSING METHOD

Family Cites Families (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4380838B2 (ja) * 1999-04-08 2009-12-09 アジア航測株式会社 ビデオ画像の道路標識自動認識方法及び道路標識自動認識装置並びに道路標識自動認識プログラム
JP3621065B2 (ja) * 2000-12-25 2005-02-16 松下電器産業株式会社 画像検出装置、プログラムおよび記録媒体
US7724962B2 (en) 2006-07-07 2010-05-25 Siemens Corporation Context adaptive approach in vehicle detection under various visibility conditions
US8358806B2 (en) * 2007-08-02 2013-01-22 Siemens Corporation Fast crowd segmentation using shape indexing
CN101408942B (zh) * 2008-04-17 2011-01-12 浙江师范大学 一种复杂背景下的车牌定位方法
CN103020623B (zh) * 2011-09-23 2016-04-06 株式会社理光 交通标志检测方法和交通标志检测设备
CN102542260A (zh) 2011-12-30 2012-07-04 中南大学 一种面向无人驾驶车的道路交通标志识别方法
US9530056B2 (en) 2012-06-15 2016-12-27 Bhaskar Saha Day night classification of images using thresholding on HSV histogram
CN103489324B (zh) * 2013-09-22 2015-09-09 北京联合大学 一种基于无人驾驶的实时动态红绿灯检测识别方法
CN104778833B (zh) 2014-01-10 2018-05-08 北京信路威科技股份有限公司 识别交通信号灯的方法
CN103955705B (zh) * 2014-04-29 2017-11-28 银江股份有限公司 基于视频分析的交通信号灯定位、识别与分类方法
US20150339589A1 (en) * 2014-05-21 2015-11-26 Brain Corporation Apparatus and methods for training robots utilizing gaze-based saliency maps
CN104021378B (zh) * 2014-06-07 2017-06-30 北京联合大学 基于时空关联与先验知识的交通信号灯实时识别方法
CN105404856B (zh) * 2015-11-02 2018-08-24 长安大学 一种公交车辆座位占用状态检测方法
CN106101632A (zh) * 2016-06-29 2016-11-09 韦醒妃 基于视觉特征的图像处理装置
US10185881B2 (en) * 2016-11-23 2019-01-22 Ford Global Technologies, Llc Traffic-light detection and classification using computer vision and deep learning
CN106909937B (zh) 2017-02-09 2020-05-19 北京汽车集团有限公司 交通信号灯识别方法、车辆控制方法、装置及车辆

Also Published As

Publication number Publication date
US10402667B2 (en) 2019-09-03
GB2559005A (en) 2018-07-25
US20190005340A1 (en) 2019-01-03
US20180144203A1 (en) 2018-05-24
US20190340450A1 (en) 2019-11-07
GB201718962D0 (en) 2018-01-03
CN108090411A (zh) 2018-05-29
DE102017127489A1 (de) 2018-05-24
US10614327B2 (en) 2020-04-07
CN108090411B (zh) 2023-06-02
US10185881B2 (en) 2019-01-22
RU2017135215A (ru) 2019-04-05

Similar Documents

Publication Publication Date Title
MX2017014963A (es) Deteccion y clasificacion de semaforos mediante el uso de vision informatica y aprendizaje profundo.
MX2017004705A (es) Deteccion de lluvia basada en vision con aprendizaje profundo.
ZA202106289B (en) Intelligent recognition and alert methods and systems
SG11201908245QA (en) Vehicle insurance image processing method, apparatus, server, and system
MX2019005352A (es) Metodo, aparato y dispositivo electronico para deteccion de la vitalidad facial.
PH12020550588A1 (en) Target detection method and apparatus, training method, electronic device and medium
EP3203417A3 (en) Method for detecting texts included in an image and apparatus using the same
MX2018000835A (es) Deteccion de vehiculos en condiciones de iluminacion baja.
WO2018189589A3 (en) Document classification using machine learning
MX2017000688A (es) Deteccion de peatones con mapas de prominencia.
GB2549875A (en) Automated content classification/filtering
US20180060660A1 (en) Blindman navigation method and blindman navigation apparatus
EP2851808A3 (en) Hybrid natural language processor
MX2017015387A (es) Metodo de identificion de señal de intrusion de perimetro de fibra optica, dispositivo de identificacion y sistema de alarma de intrusion de perimetro de fibra optica.
WO2010151029A3 (ko) 얼굴의 돌출부 인식 방법 및 장치
US8965068B2 (en) Apparatus and method for discriminating disguised face
WO2015018517A8 (en) Adaptive pattern recognition for psychosis risk modelling
CN104573719A (zh) 基于图像智能分析的山火检测方法
MX365472B (es) Sistema para la identificacion y cuantificacion de huevos de helmintos en muestras ambientales.
CN102682304A (zh) 一种融合多特征的行人检测方法及装置
WO2015024257A8 (en) Unstructured road boundary detection
WO2020076644A3 (en) Methods for automated detection of cervical pre-cancers with a low-cost, point-of-care, pocket colposcope
IN2014MU03302A (es)
WO2019042728A3 (de) Erfassen von verkehrsteilnehmern auf einem verkehrsweg
ATE528730T1 (de) Verfahren zur erkennung von objekten