WO2012146253A1 - Estimation de pose et classification d'objets à partir de nuages de points en 3d - Google Patents

Estimation de pose et classification d'objets à partir de nuages de points en 3d Download PDF

Info

Publication number
WO2012146253A1
WO2012146253A1 PCT/DK2012/050136 DK2012050136W WO2012146253A1 WO 2012146253 A1 WO2012146253 A1 WO 2012146253A1 DK 2012050136 W DK2012050136 W DK 2012050136W WO 2012146253 A1 WO2012146253 A1 WO 2012146253A1
Authority
WO
WIPO (PCT)
Prior art keywords
virtual
real
points
point
camera
Prior art date
Application number
PCT/DK2012/050136
Other languages
English (en)
Inventor
Bent MØLLER
Ivar Balslev
René Dencker ERIKSEN
Original Assignee
Scape Technologies A/S
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 Scape Technologies A/S filed Critical Scape Technologies A/S
Publication of WO2012146253A1 publication Critical patent/WO2012146253A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • G06T2207/30108—Industrial image inspection
    • G06T2207/30164—Workpiece; Machine component

Abstract

La présente invention permet la détermination de la pose, c.-à-d. la position et l'orientation, d'objets utilisant des informations acquises d'analyseurs 3D. Le nœud d'information élémentaire est un point 3D détecté et un vecteur de direction associé, appelé point orienté. Le vecteur associé est soit la normale dans le point ou - en cas de points d'arête 3D - la tangente. Pendant l'apprentissage, les poses d'un capteur virtuel associé à un objet virtuel sont utilisées. Les descripteurs numériques des points orientés résultants sont mémorisés dans une base de données. Pendant la reconnaissance, les points orientés sont déduits des données acquises par un capteur physique observant une scène d'objets aux poses inconnues. Une paire de points orientés, un de l'apprentissage et un de la reconnaissance, est incluse dans un algorithme qui produit un point paramètre dans un espace à 4 dimensions. Un espace d'agrégat correspond à un objet observé par le capteur.
PCT/DK2012/050136 2011-04-29 2012-04-25 Estimation de pose et classification d'objets à partir de nuages de points en 3d WO2012146253A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
EP11164299 2011-04-29
EP11164299.7 2011-04-29

Publications (1)

Publication Number Publication Date
WO2012146253A1 true WO2012146253A1 (fr) 2012-11-01

Family

ID=44513442

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/DK2012/050136 WO2012146253A1 (fr) 2011-04-29 2012-04-25 Estimation de pose et classification d'objets à partir de nuages de points en 3d

Country Status (1)

Country Link
WO (1) WO2012146253A1 (fr)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014202567A (ja) * 2013-04-03 2014-10-27 キヤノン株式会社 位置姿勢計測装置、位置姿勢計測装置の制御方法、およびプログラム
WO2017150878A1 (fr) * 2016-03-01 2017-09-08 Samsung Electronics Co., Ltd. Utilisation de repères multiples pour un classement d'objets à grains fins
US10192283B2 (en) 2014-12-22 2019-01-29 Cognex Corporation System and method for determining clutter in an acquired image
CN109410183A (zh) * 2018-10-08 2019-03-01 香港理工大学 基于点云数据的平面提取方法、系统、装置及存储介质
US10229347B2 (en) 2017-05-14 2019-03-12 International Business Machines Corporation Systems and methods for identifying a target object in an image
CN109816050A (zh) * 2019-02-23 2019-05-28 深圳市商汤科技有限公司 物体位姿估计方法及装置
US10452949B2 (en) 2015-11-12 2019-10-22 Cognex Corporation System and method for scoring clutter for use in 3D point cloud matching in a vision system
US10467756B2 (en) 2017-05-14 2019-11-05 International Business Machines Corporation Systems and methods for determining a camera pose of an image
CN110533726A (zh) * 2019-08-28 2019-12-03 哈尔滨工业大学 一种激光雷达场景三维姿态点法向量估计修正方法
US10579860B2 (en) 2016-06-06 2020-03-03 Samsung Electronics Co., Ltd. Learning model for salient facial region detection
CN111496289A (zh) * 2020-04-08 2020-08-07 清华大学 多功能集成化航空装配制孔系统及其使用方法
US11562505B2 (en) 2018-03-25 2023-01-24 Cognex Corporation System and method for representing and displaying color accuracy in pattern matching by a vision system

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070127816A1 (en) 2003-08-15 2007-06-07 Ivar Balslev Computer-vision system for classification and spatial localization of bounded 3d-objects

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20070127816A1 (en) 2003-08-15 2007-06-07 Ivar Balslev Computer-vision system for classification and spatial localization of bounded 3d-objects

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
DIPANKAR DAS ET AL: "Object Detection and Localization in Clutter Range Images Using Edge Features", 30 November 2009, ADVANCES IN VISUAL COMPUTING, SPRINGER BERLIN HEIDELBERG, BERLIN, HEIDELBERG, PAGE(S) 172 - 183, ISBN: 978-3-642-10519-7, XP019135085 *
SAMUELE SALTI ET AL: "On the Use of Implicit Shape Models for Recognition of Object Categories in 3D Data", 8 November 2010, COMPUTER VISION Â ACCV 2010, SPRINGER BERLIN HEIDELBERG, BERLIN, HEIDELBERG, PAGE(S) 653 - 666, ISBN: 978-3-642-19317-0, XP019160529 *

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014202567A (ja) * 2013-04-03 2014-10-27 キヤノン株式会社 位置姿勢計測装置、位置姿勢計測装置の制御方法、およびプログラム
US10192283B2 (en) 2014-12-22 2019-01-29 Cognex Corporation System and method for determining clutter in an acquired image
US10452949B2 (en) 2015-11-12 2019-10-22 Cognex Corporation System and method for scoring clutter for use in 3D point cloud matching in a vision system
US10424072B2 (en) 2016-03-01 2019-09-24 Samsung Electronics Co., Ltd. Leveraging multi cues for fine-grained object classification
WO2017150878A1 (fr) * 2016-03-01 2017-09-08 Samsung Electronics Co., Ltd. Utilisation de repères multiples pour un classement d'objets à grains fins
US10579860B2 (en) 2016-06-06 2020-03-03 Samsung Electronics Co., Ltd. Learning model for salient facial region detection
US10229347B2 (en) 2017-05-14 2019-03-12 International Business Machines Corporation Systems and methods for identifying a target object in an image
US10395143B2 (en) 2017-05-14 2019-08-27 International Business Machines Corporation Systems and methods for identifying a target object in an image
US10467756B2 (en) 2017-05-14 2019-11-05 International Business Machines Corporation Systems and methods for determining a camera pose of an image
US11562505B2 (en) 2018-03-25 2023-01-24 Cognex Corporation System and method for representing and displaying color accuracy in pattern matching by a vision system
CN109410183A (zh) * 2018-10-08 2019-03-01 香港理工大学 基于点云数据的平面提取方法、系统、装置及存储介质
CN109410183B (zh) * 2018-10-08 2022-03-25 香港理工大学 基于点云数据的平面提取方法、系统、装置及存储介质
CN109816050A (zh) * 2019-02-23 2019-05-28 深圳市商汤科技有限公司 物体位姿估计方法及装置
CN110533726A (zh) * 2019-08-28 2019-12-03 哈尔滨工业大学 一种激光雷达场景三维姿态点法向量估计修正方法
CN110533726B (zh) * 2019-08-28 2021-05-04 哈尔滨工业大学 一种激光雷达场景三维姿态点法向量估计修正方法
CN111496289A (zh) * 2020-04-08 2020-08-07 清华大学 多功能集成化航空装配制孔系统及其使用方法
CN111496289B (zh) * 2020-04-08 2021-08-10 清华大学 多功能集成化航空装配制孔系统及其使用方法

Similar Documents

Publication Publication Date Title
WO2012146253A1 (fr) Estimation de pose et classification d'objets à partir de nuages de points en 3d
CN110992356B (zh) 目标对象检测方法、装置和计算机设备
US8908913B2 (en) Voting-based pose estimation for 3D sensors
Holz et al. Real-time plane segmentation using RGB-D cameras
Kang et al. Automatic targetless camera–lidar calibration by aligning edge with gaussian mixture model
JP6216508B2 (ja) ３ｄシーンにおける３ｄ物体の認識および姿勢決定のための方法
EP1986153B1 (fr) Procédé et système pour déterminer les poses d'objets à partir d'une gamme d'images
US8442304B2 (en) System and method for three-dimensional alignment of objects using machine vision
Kriegel et al. Combining object modeling and recognition for active scene exploration
US9576363B2 (en) Object picking system, object detecting device, object detecting method
JP6983828B2 (ja) ビジョンシステムにより画像特徴におけるエッジと法線を同時に考慮するためのシステム及び方法
JP6503153B2 (ja) ビジョンシステムにおいて３ｄアライメントアルゴリズムを自動選択するためのシステム及び方法
EP1658579A1 (fr) Systeme de vision artificielle destine a la classification et a la localisation spatiale d'objets tridimensionnels finis
Abbeloos et al. Point pair feature based object detection for random bin picking
JP6172432B2 (ja) 被写体識別装置、被写体識別方法および被写体識別プログラム
Zheng et al. Industrial part localization and grasping using a robotic arm guided by 2D monocular vision
JP2008217544A (ja) 物体検出方法、物体検出装置、及びそれを備えたロボット
US20210350165A1 (en) Methods and apparatus for generating point cloud histograms
JPH07103715A (ja) 視覚に基く三次元位置および姿勢の認識方法ならびに視覚に基く三次元位置および姿勢の認識装置
Moritani et al. Cylinder-based efficient and robust registration and model fitting of laser-scanned point clouds for as-built modeling of piping systems
Cociaş et al. Multiple-superquadrics based object surface estimation for grasping in service robotics
Akizuki et al. Stable position and pose estimation of industrial parts using evaluation of observability of 3D vector pairs
Hlubik et al. Advanced point cloud estimation based on multiple view geometry
Ali et al. Segmentation and pose estimation of planar metallic objects
Akizuki et al. Position and pose recognition of randomly stacked objects using highly observable 3D vector pairs

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: 12718052

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 12718052

Country of ref document: EP

Kind code of ref document: A1