JP7499280B2 - 人物の単眼深度推定のための方法およびシステム - Google Patents

人物の単眼深度推定のための方法およびシステム Download PDF

Info

Publication number
JP7499280B2
JP7499280B2 JP2021574764A JP2021574764A JP7499280B2 JP 7499280 B2 JP7499280 B2 JP 7499280B2 JP 2021574764 A JP2021574764 A JP 2021574764A JP 2021574764 A JP2021574764 A JP 2021574764A JP 7499280 B2 JP7499280 B2 JP 7499280B2
Authority
JP
Japan
Prior art keywords
joint
depth
heatmap
convolutional
skeleton
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
JP2021574764A
Other languages
English (en)
Japanese (ja)
Other versions
JP2022536790A5 (cg-RX-API-DMAC7.html
JP2022536790A (ja
Inventor
コリン ブラウン，
ルイス ハーバー，
Original Assignee
ヒンジ ヘルス， インコーポレイテッド
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 ヒンジ ヘルス， インコーポレイテッド filed Critical ヒンジ ヘルス， インコーポレイテッド
Publication of JP2022536790A publication Critical patent/JP2022536790A/ja
Publication of JP2022536790A5 publication Critical patent/JP2022536790A5/ja
Application granted granted Critical
Publication of JP7499280B2 publication Critical patent/JP7499280B2/ja
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
    • 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 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • 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
    • 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
    • G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Biomedical Technology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)
JP2021574764A 2019-06-14 2020-03-27 人物の単眼深度推定のための方法およびシステム Active JP7499280B2 (ja)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CA3046612A CA3046612C (en) 2019-06-14 2019-06-14 Method and system for monocular depth estimation of persons
CA3,046,612 2019-06-14
PCT/IB2020/052936 WO2020250046A1 (en) 2019-06-14 2020-03-27 Method and system for monocular depth estimation of persons

Publications (3)

Publication Number Publication Date
JP2022536790A JP2022536790A (ja) 2022-08-18
JP2022536790A5 JP2022536790A5 (cg-RX-API-DMAC7.html) 2023-03-24
JP7499280B2 true JP7499280B2 (ja) 2024-06-13

Family

ID=73781888

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2021574764A Active JP7499280B2 (ja) 2019-06-14 2020-03-27 人物の単眼深度推定のための方法およびシステム

Country Status (6)

Country Link
US (4) US11354817B2 (cg-RX-API-DMAC7.html)
EP (1) EP3983997A4 (cg-RX-API-DMAC7.html)
JP (1) JP7499280B2 (cg-RX-API-DMAC7.html)
KR (1) KR20220024494A (cg-RX-API-DMAC7.html)
CA (2) CA3280234A1 (cg-RX-API-DMAC7.html)
WO (1) WO2020250046A1 (cg-RX-API-DMAC7.html)

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CA3280234A1 (en) 2019-06-14 2025-10-30 Hinge Health, Inc. Method and system for monocular depth estimation of persons
WO2021186222A1 (en) * 2020-03-20 2021-09-23 Wrnch Inc. Markerless motion capture of hands with multiple pose estimation engines
EP4009277A1 (en) * 2020-12-03 2022-06-08 Tata Consultancy Services Limited Methods and systems for generating end-to-end model to estimate 3-dimensional(3-d) pose of object
CN114036969B (zh) * 2021-03-16 2023-07-25 上海大学 一种多视角情况下的3d人体动作识别算法
US12100156B2 (en) 2021-04-12 2024-09-24 Snap Inc. Garment segmentation
WO2023022709A1 (en) * 2021-08-17 2023-02-23 Innopeak Technology, Inc. Real-time hand-held markerless human motion recording and avatar rendering in a mobile platform
KR102636549B1 (ko) * 2021-08-31 2024-02-14 광주과학기술원 노이즈 개선 네트워크 기반 보행 인식 장치 및 방법
US11670059B2 (en) 2021-09-01 2023-06-06 Snap Inc. Controlling interactive fashion based on body gestures
US11983826B2 (en) 2021-09-30 2024-05-14 Snap Inc. 3D upper garment tracking
US11636662B2 (en) 2021-09-30 2023-04-25 Snap Inc. Body normal network light and rendering control
US11651572B2 (en) 2021-10-11 2023-05-16 Snap Inc. Light and rendering of garments
CN114742698B (zh) * 2022-04-24 2025-05-30 天津大学 基于深度生成模型的威亚线擦除方法、设备及存储介质
US12394082B2 (en) * 2022-08-16 2025-08-19 Verizon Patent And Licensing Inc. Methods and systems for resolving 3D positions of multiple objects present within a 3D space
CN116205984A (zh) * 2022-08-26 2023-06-02 安徽工布智造工业科技有限公司 基于单目视觉的立方体视差校正设备的视差校正算法
CN116188555B (zh) * 2022-12-09 2025-12-12 合肥工业大学 一种基于深度网络与运动信息的单目室内深度估计算法
WO2024128124A1 (ja) * 2022-12-15 2024-06-20 日本電気株式会社 学習装置、推定装置、学習方法、推定方法ならびに記録媒体
US20240296582A1 (en) * 2023-03-01 2024-09-05 Purdue Research Foundation Pose relation transformer and refining occlusions for human pose estimation
CN117237311B (zh) * 2023-09-26 2026-04-03 国网浙江省电力有限公司杭州市富阳区供电公司 一种检测电表箱视窗破损的方法

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018087933A1 (ja) 2016-11-14 2018-05-17 富士通株式会社 情報処理装置、情報処理方法、およびプログラム

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105787439B (zh) * 2016-02-04 2019-04-05 广州新节奏智能科技股份有限公司 一种基于卷积神经网络的深度图像人体关节定位方法
US10679046B1 (en) * 2016-11-29 2020-06-09 MAX-PLANCK-Gesellschaft zur Förderung der Wissenschaften e.V. Machine learning systems and methods of estimating body shape from images
EP3462373A1 (en) * 2017-10-02 2019-04-03 Promaton Holding B.V. Automated classification and taxonomy of 3d teeth data using deep learning methods
CN111565638B (zh) * 2018-01-08 2023-08-15 柯惠有限合伙公司 用于基于视频的非接触式潮气容积监测的系统和方法
US10929654B2 (en) * 2018-03-12 2021-02-23 Nvidia Corporation Three-dimensional (3D) pose estimation from a monocular camera
CN108549876A (zh) * 2018-04-20 2018-09-18 重庆邮电大学 基于目标检测和人体姿态估计的坐姿检测方法
US10922573B2 (en) * 2018-10-22 2021-02-16 Future Health Works Ltd. Computer based object detection within a video or image
US10937173B2 (en) * 2018-11-15 2021-03-02 Qualcomm Incorporated Predicting subject body poses and subject movement intent using probabilistic generative models
US10839543B2 (en) * 2019-02-26 2020-11-17 Baidu Usa Llc Systems and methods for depth estimation using convolutional spatial propagation networks
US11004230B2 (en) * 2019-03-22 2021-05-11 Microsoft Technology Licensing, Llc Predicting three-dimensional articulated and target object pose
CA3280234A1 (en) 2019-06-14 2025-10-30 Hinge Health, Inc. Method and system for monocular depth estimation of persons

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018087933A1 (ja) 2016-11-14 2018-05-17 富士通株式会社 情報処理装置、情報処理方法、およびプログラム

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Alin-Ionut Popa et al.，Deep Multitask Architecture for Integrated 2D and 3D Human Sensing，2017 IEEE Conference on Computer Vision and Pattern Recognition，2017年07月21日，pp. 4714-4723，https://ieeexplore.ieee.org/document/8099984
村岡 太郎 外，二次元動画像からの動作情報抽出，電子情報通信学会技術報告 Ｖｏｌ．１０１ Ｎｏ．７３７，2002年03月，pp. 97-104

Also Published As

Publication number Publication date
KR20220024494A (ko) 2022-03-03
US20220292714A1 (en) 2022-09-15
WO2020250046A1 (en) 2020-12-17
US20220108470A1 (en) 2022-04-07
CA3046612A1 (en) 2020-12-14
CA3280234A1 (en) 2025-10-30
EP3983997A1 (en) 2022-04-20
US11875529B2 (en) 2024-01-16
CA3046612C (en) 2025-12-09
US12373983B2 (en) 2025-07-29
US11354817B2 (en) 2022-06-07
JP2022536790A (ja) 2022-08-18
US20240087161A1 (en) 2024-03-14
EP3983997A4 (en) 2023-06-28
US20250336087A1 (en) 2025-10-30

Similar Documents

Publication Publication Date Title
JP7499280B2 (ja) 人物の単眼深度推定のための方法およびシステム
JP7178396B2 (ja) 入力映像に含まれた客体の３次元ポーズの推定のためのデータを生成する方法およびコンピュータシステム
CN117115256B (zh) 图像处理系统
US10217195B1 (en) Generation of semantic depth of field effect
JP7162750B2 (ja) 画像処理装置、画像処理方法、及び、プログラム
US11113571B2 (en) Target object position prediction and motion tracking
US11159717B2 (en) Systems and methods for real time screen display coordinate and shape detection
WO2020225562A1 (en) Processing captured images
US11200689B1 (en) Detailed 3D estimation from a single image
KR20210015695A (ko) 포즈 추정 방법, 포즈 추정 장치, 및 포즈 추정을 위한 트레이닝 방법
KR20220098895A (ko) 인체 포즈 추정 장치 및 방법
US20180189955A1 (en) Augumented reality (ar) method and system enhanced through efficient edge detection of image objects
JP2002216129A (ja) 顔領域検出装置およびその方法並びにコンピュータ読み取り可能な記録媒体
US20200118333A1 (en) Automated costume augmentation using shape estimation
CN114581987A (zh) 图像处理方法、装置、电子设备及存储介质
CN113538704A (zh) 一种基于光源位置绘制虚拟对象光影的方法及设备
Mukasa et al. 3d scene mesh from cnn depth predictions and sparse monocular slam
CN117529758A (zh) 用于使用神经网络识别图像和视频中的人类协同活动的方法、系统和介质
Yang et al. Sparse color-code net: Real-time RGB-based 6D object pose estimation on edge devices
Jian et al. Realistic face animation generation from videos
KR102808311B1 (ko) 영상 처리 방법 및 장치
Ciou et al. Indoor positioning using convolution neural network to regress camera pose
Ru et al. Action recognition based on binocular vision
Aigerim et al. Recognition of 3D object using Kinect
Purps et al. Reconstructing Facial Expressions

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20230315

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20230315

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20240130

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20240205

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20240419

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20240528

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20240603

R150 Certificate of patent or registration of utility model

Ref document number: 7499280

Country of ref document: JP

Free format text: JAPANESE INTERMEDIATE CODE: R150