WO2016170330A1 - Traitement d'une série d'images pour identifier au moins une partie d'un objet - Google Patents

Traitement d'une série d'images pour identifier au moins une partie d'un objet Download PDF

Info

Publication number
WO2016170330A1
WO2016170330A1 PCT/GB2016/051096 GB2016051096W WO2016170330A1 WO 2016170330 A1 WO2016170330 A1 WO 2016170330A1 GB 2016051096 W GB2016051096 W GB 2016051096W WO 2016170330 A1 WO2016170330 A1 WO 2016170330A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
region
images
identify
vehicle
Prior art date
Application number
PCT/GB2016/051096
Other languages
English (en)
Inventor
Paul Newman
Lina Maria PAZ
Pedro PINIES
Original Assignee
Oxford University Innovation Limited
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 Oxford University Innovation Limited filed Critical Oxford University Innovation Limited
Publication of WO2016170330A1 publication Critical patent/WO2016170330A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/174—Segmentation; Edge detection involving the use of two or more images
    • 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
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/64—Three-dimensional objects
    • 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
    • G06T2207/10016—Video; Image sequence
    • 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
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • 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
    • G06T2207/20156—Automatic seed setting
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30248—Vehicle exterior or interior
    • G06T2207/30252—Vehicle exterior; Vicinity of vehicle
    • G06T2207/30256—Lane; Road marking

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Image Analysis (AREA)
  • Traffic Control Systems (AREA)

Abstract

L'invention concerne un procédé et un système de traitement d'une série d'images pour identifier au moins une partie d'un objet d'intérêt dans les images, chaque image représentant au moins une partie d'un environnement. Le procédé consiste à obtenir une première image en deux dimensions (2D), dans laquelle au moins un point, ayant une propriété prédéterminée, est marqué comme formant au moins partie de l'objet d'intérêt ; à segmenter la première image 2D pour identifier la ou les régions correspondant audit ou auxdits points marqués en vue d'identifier la ou les parties de l'objet d'intérêt dans la première image 2D ; à obtenir une seconde image 2D de l'environnement ; à propager au moins une partie de la région de la première image 2D à la seconde image 2D à l'aide de données géométriques en trois dimensions (3D) ; et à segmenter la seconde image 2D pour identifier la ou les régions ayant la propriété prédéterminée dans la seconde image 2D, ce qui permet d'identifier la ou les parties de l'objet d'intérêt dans la seconde image 2D.
PCT/GB2016/051096 2015-04-24 2016-04-21 Traitement d'une série d'images pour identifier au moins une partie d'un objet WO2016170330A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
GB1507009.7 2015-04-24
GB1507009.7A GB2541153A (en) 2015-04-24 2015-04-24 Processing a series of images to identify at least a portion of an object

Publications (1)

Publication Number Publication Date
WO2016170330A1 true WO2016170330A1 (fr) 2016-10-27

Family

ID=53488610

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/GB2016/051096 WO2016170330A1 (fr) 2015-04-24 2016-04-21 Traitement d'une série d'images pour identifier au moins une partie d'un objet

Country Status (2)

Country Link
GB (1) GB2541153A (fr)
WO (1) WO2016170330A1 (fr)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106529604A (zh) * 2016-11-24 2017-03-22 苏州大学 一种自适应的图像标签鲁棒预测方法及系统
CN108957448A (zh) * 2018-06-06 2018-12-07 西安电子科技大学 一种基于广义全变差正则化的雷达关联成像方法
CN109117690A (zh) * 2017-06-23 2019-01-01 百度在线网络技术（北京）有限公司 可行驶区域检测方法、装置、设备及存储介质
US10254758B2 (en) 2017-01-18 2019-04-09 Ford Global Technologies, Llc Object tracking by unsupervised learning
CN110188687A (zh) * 2019-05-30 2019-08-30 爱驰汽车有限公司 汽车的地形识别方法、系统、设备及存储介质
US10449956B2 (en) 2017-01-18 2019-10-22 Ford Global Technologies, Llc Object tracking by unsupervised learning
CN111801711A (zh) * 2018-03-14 2020-10-20 法弗人工智能有限公司 图像标注
CN112347831A (zh) * 2019-08-09 2021-02-09 株式会社日立制作所 信息处理装置以及表识别方法
CN114531580A (zh) * 2020-11-23 2022-05-24 北京四维图新科技股份有限公司 图像处理方法及装置
US11977154B2 (en) 2016-10-28 2024-05-07 Ppg Industries Ohio, Inc. Coatings for increasing near-infrared detection distances

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107403154B (zh) * 2017-07-20 2020-10-16 四川大学 一种基于动态视觉传感器的步态识别方法
EP3506160B1 (fr) * 2017-12-28 2022-06-01 Dassault Systèmes Segmentation sémantique de plans de sol 2d à l'aide d'un classificateur au niveau du pixel
CN111612806B (zh) * 2020-01-10 2023-07-28 江西理工大学 一种建筑物立面窗户提取方法及装置

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008152607A1 (fr) * 2007-06-15 2008-12-18 Koninklijke Philips Electronics N.V. Procede, appareil, systeme et programme informatique de propagation d'informations relatives a la profondeur
EP2538242A1 (fr) * 2011-06-24 2012-12-26 Softkinetic Software Amélioration de la qualité de mesure de profondeur
US20130129224A1 (en) * 2011-11-21 2013-05-23 Microsoft Corporation Combined depth filtering and super resolution
EP2858034A1 (fr) * 2013-10-02 2015-04-08 Thomson Licensing Procédé et appareil de génération de cartes de profondeur constante dans le temps

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9684972B2 (en) * 2012-02-03 2017-06-20 Koninklijke Philips N.V. Imaging apparatus for imaging an object
DE102012215825A1 (de) * 2012-09-06 2014-03-06 Siemens Aktiengesellschaft Bestimmung eines flächigen Untersuchungsbereiches

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2008152607A1 (fr) * 2007-06-15 2008-12-18 Koninklijke Philips Electronics N.V. Procede, appareil, systeme et programme informatique de propagation d'informations relatives a la profondeur
EP2538242A1 (fr) * 2011-06-24 2012-12-26 Softkinetic Software Amélioration de la qualité de mesure de profondeur
US20130129224A1 (en) * 2011-11-21 2013-05-23 Microsoft Corporation Combined depth filtering and super resolution
EP2858034A1 (fr) * 2013-10-02 2015-04-08 Thomson Licensing Procédé et appareil de génération de cartes de profondeur constante dans le temps

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
JOSÉ M ÁLVAREZ ALVAREZ ET AL: "Road Detection Based on Illuminant Invariance", IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, IEEE, PISCATAWAY, NJ, USA, vol. 12, no. 1, 1 March 2011 (2011-03-01), pages 184 - 193, XP011348832, ISSN: 1524-9050, DOI: 10.1109/TITS.2010.2076349 *
LINA MARIA PAZ ET AL: "A variational approach to online road and path segmentation with monocular vision", 2015 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), 26 May 2015 (2015-05-26), pages 1633 - 1639, XP055284722, DOI: 10.1109/ICRA.2015.7139407 *
SIBEL YENIKAYA ET AL: "Keeping the vehicle on the road", ACM COMPUTING SURVEYS., vol. 46, no. 1, 1 October 2013 (2013-10-01), US, pages 1 - 43, XP055285141, ISSN: 0360-0300, DOI: 10.1145/2522968.2522970 *
WANG YAN ET AL: "Label Propagation from ImageNet to 3D Point Clouds", IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION. PROCEEDINGS, IEEE COMPUTER SOCIETY, US, 23 June 2013 (2013-06-23), pages 3135 - 3142, XP032493269, ISSN: 1063-6919, [retrieved on 20131002], DOI: 10.1109/CVPR.2013.403 *
XIAO JIANXIONG ET AL: "SUN3D: A Database of Big Spaces Reconstructed Using SfM and Object Labels", 2013 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION, IEEE, 1 December 2013 (2013-12-01), pages 1625 - 1632, XP032572629, ISSN: 1550-5499, [retrieved on 20140228], DOI: 10.1109/ICCV.2013.458 *

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11977154B2 (en) 2016-10-28 2024-05-07 Ppg Industries Ohio, Inc. Coatings for increasing near-infrared detection distances
CN106529604B (zh) * 2016-11-24 2019-09-27 苏州大学 一种自适应的图像标签鲁棒预测方法及系统
CN106529604A (zh) * 2016-11-24 2017-03-22 苏州大学 一种自适应的图像标签鲁棒预测方法及系统
US10449956B2 (en) 2017-01-18 2019-10-22 Ford Global Technologies, Llc Object tracking by unsupervised learning
US10254758B2 (en) 2017-01-18 2019-04-09 Ford Global Technologies, Llc Object tracking by unsupervised learning
CN109117690A (zh) * 2017-06-23 2019-01-01 百度在线网络技术（北京）有限公司 可行驶区域检测方法、装置、设备及存储介质
CN111801711A (zh) * 2018-03-14 2020-10-20 法弗人工智能有限公司 图像标注
CN108957448B (zh) * 2018-06-06 2022-10-28 西安电子科技大学 一种基于广义全变差正则化的雷达关联成像方法
CN108957448A (zh) * 2018-06-06 2018-12-07 西安电子科技大学 一种基于广义全变差正则化的雷达关联成像方法
CN110188687A (zh) * 2019-05-30 2019-08-30 爱驰汽车有限公司 汽车的地形识别方法、系统、设备及存储介质
CN110188687B (zh) * 2019-05-30 2021-08-20 爱驰汽车有限公司 汽车的地形识别方法、系统、设备及存储介质
CN112347831A (zh) * 2019-08-09 2021-02-09 株式会社日立制作所 信息处理装置以及表识别方法
CN114531580A (zh) * 2020-11-23 2022-05-24 北京四维图新科技股份有限公司 图像处理方法及装置
CN114531580B (zh) * 2020-11-23 2023-11-21 北京四维图新科技股份有限公司 图像处理方法及装置

Also Published As

Publication number Publication date
GB201507009D0 (en) 2015-06-10
GB2541153A (en) 2017-02-15

Similar Documents

Publication Publication Date Title
WO2016170330A1 (fr) Traitement d'une série d'images pour identifier au moins une partie d'un objet
Menze et al. Object scene flow
US20220319024A1 (en) Image annotation
Yang et al. Recovering 3d planes from a single image via convolutional neural networks
US10546387B2 (en) Pose determination with semantic segmentation
Zhou et al. Efficient road detection and tracking for unmanned aerial vehicle
US9990736B2 (en) Robust anytime tracking combining 3D shape, color, and motion with annealed dynamic histograms
Ranft et al. The role of machine vision for intelligent vehicles
JP6095018B2 (ja) 移動オブジェクトの検出及び追跡
US9864927B2 (en) Method of detecting structural parts of a scene
US11049270B2 (en) Method and apparatus for calculating depth map based on reliability
EP3516582A1 (fr) Détermination d'itinéraire autonome
Bruls et al. Mark yourself: Road marking segmentation via weakly-supervised annotations from multimodal data
Pascoe et al. Robust direct visual localisation using normalised information distance.
EP3710985A1 (fr) Détection de parties statiques d'une scène
Peng et al. Globally-optimal event camera motion estimation
Suleymanov et al. Inferring road boundaries through and despite traffic
Dimitrievski et al. Semantically aware multilateral filter for depth upsampling in automotive lidar point clouds
Paz et al. A variational approach to online road and path segmentation with monocular vision
Xu et al. Direct visual-inertial odometry with semi-dense mapping
Liu et al. Accurate real-time visual SLAM combining building models and GPS for mobile robot
Seo et al. An efficient detection of vanishing points using inverted coordinates image space
Sommer et al. Sf2se3: Clustering scene flow into se (3)-motions via proposal and selection
Wong et al. Monocular localization within sparse voxel maps
Li et al. Ground target tracking and trajectory prediction by UAV using a single camera and 3D road geometry recovery

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: 16718867

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 16718867

Country of ref document: EP

Kind code of ref document: A1