CN109154973B - 执行卷积图像变换估算的方法和系统 - Google Patents

执行卷积图像变换估算的方法和系统 Download PDF

Info

Publication number
CN109154973B
CN109154973B CN201780030961.9A CN201780030961A CN109154973B CN 109154973 B CN109154973 B CN 109154973B CN 201780030961 A CN201780030961 A CN 201780030961A CN 109154973 B CN109154973 B CN 109154973B
Authority
CN
China
Prior art keywords
image
corner
subset
perturbation
homography
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN201780030961.9A
Other languages
English (en)
Chinese (zh)
Other versions
CN109154973A (zh
Inventor
D·德通
T·J·马利西维茨
A·拉比诺维奇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Magic Leap Inc
Original Assignee
Magic Leap Inc
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 Magic Leap Inc filed Critical Magic Leap Inc
Publication of CN109154973A publication Critical patent/CN109154973A/zh
Application granted granted Critical
Publication of CN109154973B publication Critical patent/CN109154973B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4046—Scaling of whole images or parts thereof, e.g. expanding or contracting using neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • G06N3/09—Supervised learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/14—Transformations for image registration, e.g. adjusting or mapping for alignment of images
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/403—Edge-driven scaling; Edge-based scaling
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/12—Edge-based segmentation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20084—Artificial neural networks [ANN]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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
    • G06T2207/20164—Salient point detection; Corner detection

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Artificial Intelligence (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Pure & Applied Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Multimedia (AREA)
  • Algebra (AREA)
  • Medical Informatics (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
CN201780030961.9A 2016-05-20 2017-05-19 执行卷积图像变换估算的方法和系统 Active CN109154973B (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US201662339799P 2016-05-20 2016-05-20
US62/339,799 2016-05-20
PCT/US2017/033661 WO2017201487A1 (en) 2016-05-20 2017-05-19 Method and system for performing convolutional image transformation estimation

Publications (2)

Publication Number Publication Date
CN109154973A CN109154973A (zh) 2019-01-04
CN109154973B true CN109154973B (zh) 2021-10-26

Family

ID=60326208

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201780030961.9A Active CN109154973B (zh) 2016-05-20 2017-05-19 执行卷积图像变换估算的方法和系统

Country Status (9)

Country Link
US (3) US10489708B2 (enExample)
EP (1) EP3459003B1 (enExample)
JP (3) JP6821707B2 (enExample)
KR (4) KR102347204B1 (enExample)
CN (1) CN109154973B (enExample)
AU (2) AU2017267983B2 (enExample)
CA (1) CA3021085A1 (enExample)
IL (2) IL262886B (enExample)
WO (1) WO2017201487A1 (enExample)

Families Citing this family (28)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2017267983B2 (en) 2016-05-20 2022-03-31 Magic Leap, Inc. Method and system for performing convolutional image transformation estimation
US10304191B1 (en) 2016-10-11 2019-05-28 Zoox, Inc. Three dimensional bounding box estimation from two dimensional images
IL266595B (en) 2016-11-16 2022-08-01 Magic Leap Inc Thermal management systems for wearable components
US11347054B2 (en) 2017-02-16 2022-05-31 Magic Leap, Inc. Systems and methods for augmented reality
US10783394B2 (en) * 2017-06-20 2020-09-22 Nvidia Corporation Equivariant landmark transformation for landmark localization
JP7091209B2 (ja) * 2018-01-29 2022-06-27 パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカ 情報処理方法及び情報処理システム
US11875251B2 (en) * 2018-05-03 2024-01-16 Samsung Electronics Co., Ltd. Neural network method and apparatus
US11202000B2 (en) * 2018-06-18 2021-12-14 Sony Interactive Entertainment Inc. Learning apparatus, image generation apparatus, learning method, image generation method, and program
EP3850581A4 (en) * 2018-09-15 2022-05-11 Qualcomm Incorporated SYSTEMS AND METHODS FOR VSLAM SCALE ESTIMATION USING AN OPTICAL FLOW SENSOR ON A ROBOT
CN109670532B (zh) * 2018-11-23 2022-12-09 腾讯医疗健康(深圳)有限公司 生物体器官组织图像的异常识别方法、装置及系统
US11995854B2 (en) * 2018-12-19 2024-05-28 Nvidia Corporation Mesh reconstruction using data-driven priors
CN110827375B (zh) * 2019-10-31 2023-05-30 湖北大学 一种基于微光图像的红外图像真彩着色方法及系统
CN111027421A (zh) * 2019-11-26 2020-04-17 西安宏规电子科技有限公司 一种基于图的直推式半监督行人再识别方法
EP4073690B1 (en) * 2019-12-12 2025-10-29 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Target detection method, terminal device, and medium
KR102343363B1 (ko) * 2020-03-06 2021-12-24 경북대학교 산학협력단 2차원 손뼈 투영 이미지로부터 회전된 2차원 손뼈 투영 이미지 생성 방법, 이를 수행하기 위한 기록 매체 및 장치
US11830160B2 (en) * 2020-05-05 2023-11-28 Nvidia Corporation Object detection using planar homography and self-supervised scene structure understanding
KR20230026398A (ko) 2020-06-12 2023-02-24 유니버시티 오브 워싱턴 근안 디스플레이들에서의 눈 추적
CN112016612A (zh) * 2020-08-26 2020-12-01 四川阿泰因机器人智能装备有限公司 一种基于单目深度估计的多传感器融合slam方法
US11899095B2 (en) * 2020-09-17 2024-02-13 Texas Instruments Incorporated Doppler processing in frequency-modulated continuous wave radar systems using dither
US12198395B2 (en) 2021-01-19 2025-01-14 Objectvideo Labs, Llc Object localization in video
WO2022236647A1 (en) * 2021-05-11 2022-11-17 Huawei Technologies Co., Ltd. Methods, devices, and computer readable media for training a keypoint estimation network using cgan-based data augmentation
CN113361542B (zh) * 2021-06-02 2022-08-30 合肥工业大学 一种基于深度学习的局部特征提取方法
KR20230030996A (ko) 2021-08-26 2023-03-07 현대자동차주식회사 객체 추적 장치 및 방법
US11688169B1 (en) * 2022-08-29 2023-06-27 Bnsf Railway Company Drone based automated yard check
US12212899B2 (en) * 2022-09-07 2025-01-28 Texas Instruments Incorporated System and method for projector geometric correction
CN116310339B (zh) * 2023-03-23 2025-08-12 长沙理工大学 基于矩阵分解增强全局特征的遥感图像分割方法
CN119556017B (zh) * 2024-10-08 2025-10-10 扬州市双宝电力设备有限公司 一种基于电致发光效应的复合绝缘子电场畸变检测方法
CN120869320A (zh) * 2025-09-22 2025-10-31 好特许(杭州)品牌管理有限公司 一种基于大模型的重量识别方法、设备及介质

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102156995A (zh) * 2011-04-21 2011-08-17 北京理工大学 一种运动相机下的视频运动前景分割方法

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050089213A1 (en) * 2003-10-23 2005-04-28 Geng Z. J. Method and apparatus for three-dimensional modeling via an image mosaic system
US9064161B1 (en) * 2007-06-08 2015-06-23 Datalogic ADC, Inc. System and method for detecting generic items in image sequence
JP5600954B2 (ja) * 2010-02-10 2014-10-08 セイコーエプソン株式会社 検査システム、その方法及びプログラム
US20120092329A1 (en) 2010-10-13 2012-04-19 Qualcomm Incorporated Text-based 3d augmented reality
US8903128B2 (en) 2011-02-16 2014-12-02 Siemens Aktiengesellschaft Object recognition for security screening and long range video surveillance
US10027952B2 (en) * 2011-08-04 2018-07-17 Trx Systems, Inc. Mapping and tracking system with features in three-dimensional space
US8965057B2 (en) * 2012-03-02 2015-02-24 Qualcomm Incorporated Scene structure-based self-pose estimation
US8818133B2 (en) * 2012-07-11 2014-08-26 Raytheon Company Point cloud construction with unposed camera
KR20150103723A (ko) * 2013-01-03 2015-09-11 메타 컴퍼니 가상 또는 증강매개된 비전을 위한 엑스트라미시브 공간 이미징 디지털 아이 글래스
KR102028952B1 (ko) * 2013-02-21 2019-10-08 삼성전자주식회사 휴대 단말에 의해 촬영된 이미지들을 합성하는 방법, 기계로 읽을 수 있는 저장 매체 및 휴대 단말
JP6448767B2 (ja) * 2014-04-24 2019-01-09 ナント・ホールデイングス・アイ・ピー・エル・エル・シー 画像物体認識におけるロバスト特徴特定
JP2016015037A (ja) * 2014-07-02 2016-01-28 キヤノン株式会社 情報処理装置及びその制御方法、並びに、ビデオカメラ
US9530235B2 (en) * 2014-11-18 2016-12-27 Google Inc. Aligning panoramic imagery and aerial imagery
CN106485192B (zh) * 2015-09-02 2019-12-06 富士通株式会社 用于图像识别的神经网络的训练方法和装置
US20170337682A1 (en) * 2016-05-18 2017-11-23 Siemens Healthcare Gmbh Method and System for Image Registration Using an Intelligent Artificial Agent
AU2017267983B2 (en) 2016-05-20 2022-03-31 Magic Leap, Inc. Method and system for performing convolutional image transformation estimation
EP4350647B1 (en) * 2016-06-03 2025-11-12 Magic Leap, Inc. Augmented reality identity verification
US10477178B2 (en) * 2016-06-30 2019-11-12 Massachusetts Institute Of Technology High-speed and tunable scene reconstruction systems and methods using stereo imagery
US10467768B2 (en) * 2017-04-07 2019-11-05 Intel Corporation Optical flow estimation using 4-dimensional cost volume processing
US10783394B2 (en) * 2017-06-20 2020-09-22 Nvidia Corporation Equivariant landmark transformation for landmark localization

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102156995A (zh) * 2011-04-21 2011-08-17 北京理工大学 一种运动相机下的视频运动前景分割方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Equivalence and efficiency of image alignment algorithms;Simon Baker,Iain Matthews;《IEEE》;20030415;全文 *

Also Published As

Publication number Publication date
IL295245B1 (en) 2023-04-01
KR20220125380A (ko) 2022-09-14
JP2020107356A (ja) 2020-07-09
EP3459003B1 (en) 2021-01-13
JP6821707B2 (ja) 2021-01-27
IL262886A (en) 2018-12-31
US20200097819A1 (en) 2020-03-26
KR20220003171A (ko) 2022-01-07
KR20190010582A (ko) 2019-01-30
US11593654B2 (en) 2023-02-28
JP7005669B2 (ja) 2022-01-21
IL295245A (en) 2022-10-01
KR102218603B1 (ko) 2021-02-19
KR102347204B1 (ko) 2022-01-03
JP2022040209A (ja) 2022-03-10
EP3459003A4 (en) 2019-05-08
JP2019517071A (ja) 2019-06-20
US20170337470A1 (en) 2017-11-23
US10489708B2 (en) 2019-11-26
EP3459003A1 (en) 2019-03-27
IL295245B2 (en) 2023-08-01
CN109154973A (zh) 2019-01-04
JP7241210B2 (ja) 2023-03-16
AU2017267983B2 (en) 2022-03-31
KR102506459B1 (ko) 2023-03-03
CA3021085A1 (en) 2017-11-23
KR102442018B1 (ko) 2022-09-07
IL262886B (en) 2022-09-01
WO2017201487A1 (en) 2017-11-23
KR20210019609A (ko) 2021-02-22
AU2022204613A1 (en) 2022-07-21
AU2017267983A1 (en) 2018-11-08
US11062209B2 (en) 2021-07-13
US20210365785A1 (en) 2021-11-25

Similar Documents

Publication Publication Date Title
CN109154973B (zh) 执行卷积图像变换估算的方法和系统
US10885659B2 (en) Object pose estimating method and apparatus
US12118668B2 (en) Scene representation using image processing
EP3295426B1 (en) Edge-aware bilateral image processing
US9715761B2 (en) Real-time 3D computer vision processing engine for object recognition, reconstruction, and analysis
US20250022153A1 (en) Multi-view stereo with learnable cost metric for 3d reconstruction
Lange et al. WLD: A Wavelet and Learning based Line Descriptor for Line Feature Matching.
CN112991254A (zh) 视差估计系统、方法、电子设备及计算机可读存储介质
US11734855B2 (en) Rotation equivariant orientation estimation for omnidirectional localization
CN109784353A (zh) 一种无向图匹配的方法、设备和存储介质
JP2018010359A (ja) 情報処理装置、情報処理方法、およびプログラム
CN116957999A (zh) 深度图优化方法、装置、设备及存储介质
JP2005339535A (ja) 相違度の計算
US20250209784A1 (en) Leveraging synthetic images to improve visual localization in case of extreme domain shifts
CN119963585A (zh) 一种角点特征检测方法、设备及存储介质

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant