WO2022239689A1 - 学習方法、学習装置、及び、プログラム - Google Patents

学習方法、学習装置、及び、プログラム Download PDF

Info

Publication number
WO2022239689A1
WO2022239689A1 PCT/JP2022/019477 JP2022019477W WO2022239689A1 WO 2022239689 A1 WO2022239689 A1 WO 2022239689A1 JP 2022019477 W JP2022019477 W JP 2022019477W WO 2022239689 A1 WO2022239689 A1 WO 2022239689A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
data
learning
distance
distance image
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.)
Ceased
Application number
PCT/JP2022/019477
Other languages
English (en)
French (fr)
Japanese (ja)
Inventor
育規 石井
正真 遠間
達也 小山
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.)
Panasonic Intellectual Property Corp of America
Original Assignee
Panasonic Intellectual Property Corp of America
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 Panasonic Intellectual Property Corp of America filed Critical Panasonic Intellectual Property Corp of America
Priority to JP2023520984A priority Critical patent/JPWO2022239689A1/ja
Priority to EP22807391.2A priority patent/EP4339886B1/en
Publication of WO2022239689A1 publication Critical patent/WO2022239689A1/ja
Priority to US18/383,616 priority patent/US20240054325A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • 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
    • G06N3/0455—Auto-encoder networks; Encoder-decoder 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
    • G06N3/088—Non-supervised learning, e.g. competitive learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G06T7/55—Depth or shape recovery from multiple images
    • 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
    • G06V10/56—Extraction of image or video features relating to colour
    • 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
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/64—Three-dimensional [3D] objects
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10028—Range image; Depth image; 3D point clouds
    • 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]

Definitions

  • the parameter update method is not particularly limited, but examples include the gradient descent method.
  • the error may be an L2 error or the like, but is not particularly limited.
  • the encoder network model extracts the feature representation of the input RGB image data.
  • the encoder network model is, for example, a CNN (Convolution Neural Networks) model configured with a plurality of convolution layers, but is not limited to this.
  • the encoder network model may be configured with ResNet (Residual Network), may be configured with MobileNet, or may be configured with Transformer.
  • the learning device 100 estimates distance data using the embedded image generated in step S06 as input data for teacher data (S07). More specifically, learning device 100 inputs embedded images to machine learning model 133 to infer distance data.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Molecular Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Databases & Information Systems (AREA)
  • Medical Informatics (AREA)
  • Image Analysis (AREA)
PCT/JP2022/019477 2021-05-13 2022-05-02 学習方法、学習装置、及び、プログラム Ceased WO2022239689A1 (ja)

Priority Applications (3)

Application Number Priority Date Filing Date Title
JP2023520984A JPWO2022239689A1 (https=) 2021-05-13 2022-05-02
EP22807391.2A EP4339886B1 (en) 2021-05-13 2022-05-02 Training method, training device, and program
US18/383,616 US20240054325A1 (en) 2021-05-13 2023-10-25 Training method and training device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US202163188013P 2021-05-13 2021-05-13
US63/188,013 2021-05-13

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/383,616 Continuation US20240054325A1 (en) 2021-05-13 2023-10-25 Training method and training device

Publications (1)

Publication Number Publication Date
WO2022239689A1 true WO2022239689A1 (ja) 2022-11-17

Family

ID=84028304

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2022/019477 Ceased WO2022239689A1 (ja) 2021-05-13 2022-05-02 学習方法、学習装置、及び、プログラム

Country Status (4)

Country Link
US (1) US20240054325A1 (https=)
EP (1) EP4339886B1 (https=)
JP (1) JPWO2022239689A1 (https=)
WO (1) WO2022239689A1 (https=)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025192499A1 (ja) * 2024-03-14 2025-09-18 富士フイルム株式会社 モデルの学習方法及びプログラム、モデルの学習装置

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US12444166B2 (en) * 2022-05-27 2025-10-14 Raytheon Company Object classification based on spatially discriminated parts

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019125116A (ja) * 2018-01-15 2019-07-25 キヤノン株式会社 情報処理装置、情報処理方法、およびプログラム
JP2020154605A (ja) * 2019-03-19 2020-09-24 富士ゼロックス株式会社 画像処理装置及びプログラム

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11210802B2 (en) * 2019-09-24 2021-12-28 Toyota Research Institute, Inc. Systems and methods for conditioning training data to avoid learned aberrations

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019125116A (ja) * 2018-01-15 2019-07-25 キヤノン株式会社 情報処理装置、情報処理方法、およびプログラム
JP2020154605A (ja) * 2019-03-19 2020-09-24 富士ゼロックス株式会社 画像処理装置及びプログラム

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
JIN HAN LEE ET AL., FROM BIG TO SMALL: MULTI-SCALE LOCAL PLANAR GUIDANCE FOR MONOCULAR DEPTH ESTIMATION, Retrieved from the Internet <URL:https://doi.org/10.48550/arXiv.1907.10326>
See also references of EP4339886A4

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2025192499A1 (ja) * 2024-03-14 2025-09-18 富士フイルム株式会社 モデルの学習方法及びプログラム、モデルの学習装置

Also Published As

Publication number Publication date
EP4339886A1 (en) 2024-03-20
JPWO2022239689A1 (https=) 2022-11-17
EP4339886B1 (en) 2025-12-17
EP4339886A4 (en) 2024-11-13
US20240054325A1 (en) 2024-02-15

Similar Documents

Publication Publication Date Title
JP7585600B2 (ja) データ処理方法、装置、データ処理システム、電子機器及びコンピュータプログラム
CN113012293B (zh) 石刻模型构建方法、装置、设备及存储介质
US11315266B2 (en) Self-supervised depth estimation method and system
US9858670B2 (en) Information processing apparatus and method thereof
US9348950B2 (en) Perceptually guided capture and stylization of 3D human figures
US20130162643A1 (en) Physical Three-Dimensional Model Generation Apparatus
CN111480342B (zh) 编码装置、编码方法、解码装置、解码方法和存储介质
JP6798860B2 (ja) 境界線推定装置
CN113689578B (zh) 一种人体数据集生成方法及装置
KR102152436B1 (ko) 3차원 포인트 클라우드 기반의 동적 3차원 모델 생성을 위한 뼈대 정보 처리 시스템 및 방법
JP7103357B2 (ja) 情報処理装置、情報処理方法、及びプログラム
JP2018169690A (ja) 画像処理装置、画像処理方法及び画像処理プログラム
US11488354B2 (en) Information processing apparatus and information processing method
KR102152432B1 (ko) 동적 3차원 모델을 이용한 실사 콘텐츠 생성 시스템 및 방법
JP2018129007A (ja) 学習データ生成装置、学習装置、推定装置、学習データ生成方法及びコンピュータプログラム
WO2022239689A1 (ja) 学習方法、学習装置、及び、プログラム
CN113516755A (zh) 图像处理方法、图像处理装置、电子设备和存储介质
CN119919578B (zh) 一种高精度变电站三维自动建模方法
CN107206693A (zh) 处理用于储存的三维物体数据
JP2019016164A (ja) 学習データ生成装置、推定装置、推定方法及びコンピュータプログラム
JP2016509805A (ja) 画像ストリームの高フレームレート化
KR20210018114A (ko) 교차 도메인 메트릭 학습 시스템 및 방법
US12131423B2 (en) Analysis apparatus, communication system, non-transitory computer readable medium
JP2006285952A (ja) 画像処理方法、画像処理装置、プログラムおよび記録媒体
JP2023177855A (ja) 位置対応付けシステム、位置対応付け方法および位置対応付けプログラム

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: 22807391

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023520984

Country of ref document: JP

WWE Wipo information: entry into national phase

Ref document number: 2022807391

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2022807391

Country of ref document: EP

Effective date: 20231213

WWG Wipo information: grant in national office

Ref document number: 2022807391

Country of ref document: EP