TWI797571B - 用於自單一影像判定可遍歷空間之電腦實施方法及電腦可讀儲存媒體 - Google Patents

用於自單一影像判定可遍歷空間之電腦實施方法及電腦可讀儲存媒體 Download PDF

Info

Publication number
TWI797571B
TWI797571B TW110108388A TW110108388A TWI797571B TW I797571 B TWI797571 B TW I797571B TW 110108388 A TW110108388 A TW 110108388A TW 110108388 A TW110108388 A TW 110108388A TW I797571 B TWI797571 B TW I797571B
Authority
TW
Taiwan
Prior art keywords
traversable
image
depth map
space
visible
Prior art date
Application number
TW110108388A
Other languages
English (en)
Chinese (zh)
Other versions
TW202147179A (zh
Inventor
詹姆斯 華森
麥克 大衛 佛曼
亞倫 蒙茲怕
葛布雷歐 Ｊ 布羅斯托
Original Assignee
美商尼安蒂克公司
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 美商尼安蒂克公司 filed Critical 美商尼安蒂克公司
Publication of TW202147179A publication Critical patent/TW202147179A/zh
Application granted granted Critical
Publication of TWI797571B publication Critical patent/TWI797571B/zh

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
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating three-dimensional [3D] models or images for computer graphics
    • G06T19/006—Mixed reality
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
    • G05D1/0274—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means using mapping information stored in a memory device
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T17/00—Three-dimensional [3D] modelling for computer graphics
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T19/00—Manipulating three-dimensional [3D] models or images for computer graphics
    • G06T19/20—Editing of three-dimensional [3D] images, e.g. changing shapes or colours, aligning objects or positioning parts
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • 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
    • G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/10—Terrestrial scenes
    • 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
    • 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
    • G06T2219/00—Indexing scheme for manipulating 3D models or images for computer graphics
    • G06T2219/20—Indexing scheme for editing of 3D models
    • G06T2219/2004—Aligning objects, relative positioning of parts

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Computer Graphics (AREA)
  • Computer Hardware Design (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Informatics (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Architecture (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • Biophysics (AREA)
  • Computational Linguistics (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Geometry (AREA)
  • Processing Or Creating Images (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Control And Safety Of Cranes (AREA)
  • Valve Device For Special Equipments (AREA)
  • Shafts, Cranks, Connecting Bars, And Related Bearings (AREA)
  • Traffic Control Systems (AREA)
TW110108388A 2020-03-10 2021-03-09 用於自單一影像判定可遍歷空間之電腦實施方法及電腦可讀儲存媒體 TWI797571B (zh)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US202062987849P 2020-03-10 2020-03-10
US62/987,849 2020-03-10
US17/193,878 US11741675B2 (en) 2020-03-10 2021-03-05 Determining traversable space from single images
US17/193,878 2021-03-05

Publications (2)

Publication Number Publication Date
TW202147179A TW202147179A (zh) 2021-12-16
TWI797571B true TWI797571B (zh) 2023-04-01

Family

ID=77665508

Family Applications (1)

Application Number Title Priority Date Filing Date
TW110108388A TWI797571B (zh) 2020-03-10 2021-03-09 用於自單一影像判定可遍歷空間之電腦實施方法及電腦可讀儲存媒體

Country Status (9)

Country Link
US (2) US11741675B2 (https=)
EP (1) EP4118618B1 (https=)
JP (1) JP7763183B2 (https=)
KR (1) KR102540594B1 (https=)
CN (1) CN115485718A (https=)
AU (1) AU2021235397B2 (https=)
CA (1) CA3175003C (https=)
TW (1) TWI797571B (https=)
WO (1) WO2021181267A1 (https=)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102647336B1 (ko) * 2019-04-01 2024-03-14 구글 엘엘씨 동적 깊이 이미지를 캡처 및 편집하는 기술
FR3106659B1 (fr) * 2020-01-23 2023-07-28 Second Bridge Inc Carte numérique pour la navigation
US11741675B2 (en) * 2020-03-10 2023-08-29 Niantic, Inc. Determining traversable space from single images
US20230260240A1 (en) * 2021-03-11 2023-08-17 Quintar, Inc. Alignment of 3d graphics extending beyond frame in augmented reality system with remote presentation
US12310283B2 (en) * 2021-05-25 2025-05-27 Scythe Robotics, Inc. Method and apparatus for modeling an environment proximate an autonomous system
US20240414427A1 (en) * 2021-09-21 2024-12-12 Sony Group Corporation Information processing device, video processing method, and program
US11636658B1 (en) * 2022-05-04 2023-04-25 Google Llc Dynamic augmented reality overlay display
US20240394839A1 (en) * 2023-05-23 2024-11-28 Disney Enterprises, Inc. Artistically controllable stereo conversion
TWI907823B (zh) * 2023-07-31 2025-12-11 威盛電子股份有限公司 應用於基於深度學習之單目深度預測的模型訓練方法與模型訓練系統
TWI854919B (zh) * 2023-12-13 2024-09-01 中華電信股份有限公司 虛擬或現實場景之人工智慧內容生成系統、方法及其電腦可讀媒介
CN118334592B (zh) * 2024-06-13 2024-09-10 中铁四局集团有限公司 图像检测方法、存储介质和电子设备

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8855408B2 (en) * 2011-11-30 2014-10-07 Samsung Electronics Co., Ltd. Method and apparatus for recovering depth information of image
CN107407567A (zh) * 2015-03-18 2017-11-28 微软技术许可有限责任公司 增强现实导航
CN110400322A (zh) * 2019-07-30 2019-11-01 江南大学 基于颜色和三维几何信息的水果点云分割方法
US20200054939A1 (en) * 2012-07-31 2020-02-20 Niantic, Inc. Placement of Virtual Elements in a Virtual World Associated with a Location-Based Parallel Reality Game

Family Cites Families (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8094928B2 (en) 2005-11-14 2012-01-10 Microsoft Corporation Stereo video for gaming
US20130063556A1 (en) * 2011-09-08 2013-03-14 Prism Skylabs, Inc. Extracting depth information from video from a single camera
US10977662B2 (en) * 2014-04-28 2021-04-13 RetailNext, Inc. Methods and systems for simulating agent behavior in a virtual environment
US9798943B2 (en) * 2014-06-09 2017-10-24 I.R.I.S. Optical character recognition method
US10602126B2 (en) 2016-06-10 2020-03-24 Lucid VR, Inc. Digital camera device for 3D imaging
KR20190062390A (ko) 2016-10-11 2019-06-05 모빌아이 비젼 테크놀로지스 엘티디. 검출된 배리어에 기반한 차량의 항법
KR101982298B1 (ko) 2016-11-24 2019-05-24 고려대학교 산학협력단 차량에서의 돌발적으로 출현한 이동 객체를 탐지하는 방법 및 장치
WO2018123641A1 (ja) 2016-12-27 2018-07-05 日立オートモティブシステムズ株式会社 走行可能領域検出装置及び走行支援システム
US10007269B1 (en) 2017-06-23 2018-06-26 Uber Technologies, Inc. Collision-avoidance system for autonomous-capable vehicle
US10929987B2 (en) * 2017-08-16 2021-02-23 Nvidia Corporation Learning rigidity of dynamic scenes for three-dimensional scene flow estimation
US10678257B2 (en) * 2017-09-28 2020-06-09 Nec Corporation Generating occlusion-aware bird eye view representations of complex road scenes
US11448508B2 (en) * 2017-10-13 2022-09-20 Kohl's, Inc. Systems and methods for autonomous generation of maps
WO2019222467A1 (en) 2018-05-17 2019-11-21 Niantic, Inc. Self-supervised training of a depth estimation system
KR102192899B1 (ko) 2018-08-16 2020-12-18 주식회사 날비컴퍼니 이미지에 보케 효과를 적용하는 방법 및 기록매체
CN109215080B (zh) 2018-09-25 2020-08-11 清华大学 基于深度学习迭代匹配的6d姿态估计网络训练方法及装置
US11017586B2 (en) * 2019-04-18 2021-05-25 Adobe Inc. 3D motion effect from a 2D image
EP4058983A4 (en) * 2019-11-12 2024-08-07 Geomagical Labs, Inc. METHOD AND SYSTEM FOR MODIFYING SCENE IMAGES
US11741675B2 (en) * 2020-03-10 2023-08-29 Niantic, Inc. Determining traversable space from single images

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8855408B2 (en) * 2011-11-30 2014-10-07 Samsung Electronics Co., Ltd. Method and apparatus for recovering depth information of image
US20200054939A1 (en) * 2012-07-31 2020-02-20 Niantic, Inc. Placement of Virtual Elements in a Virtual World Associated with a Location-Based Parallel Reality Game
CN107407567A (zh) * 2015-03-18 2017-11-28 微软技术许可有限责任公司 增强现实导航
CN110400322A (zh) * 2019-07-30 2019-11-01 江南大学 基于颜色和三维几何信息的水果点云分割方法

Also Published As

Publication number Publication date
JP2023517661A (ja) 2023-04-26
TW202147179A (zh) 2021-12-16
EP4118618B1 (en) 2025-05-07
EP4118618A4 (en) 2024-04-10
CN115485718A (zh) 2022-12-16
US11741675B2 (en) 2023-08-29
US20210287385A1 (en) 2021-09-16
AU2021235397B2 (en) 2023-08-31
US12573153B2 (en) 2026-03-10
KR20220143957A (ko) 2022-10-25
CA3175003C (en) 2023-08-01
CA3175003A1 (en) 2021-09-16
JP7763183B2 (ja) 2025-10-31
US20230360339A1 (en) 2023-11-09
KR102540594B1 (ko) 2023-06-08
WO2021181267A1 (en) 2021-09-16
AU2021235397A1 (en) 2022-11-03
EP4118618A1 (en) 2023-01-18

Similar Documents

Publication Publication Date Title
TWI797571B (zh) 用於自單一影像判定可遍歷空間之電腦實施方法及電腦可讀儲存媒體
CN112805748B (zh) 使用深度提示对深度估计模型的自我监督训练
TWI837557B (zh) 用於自監督多圖框單眼深度估計模型之電腦實施方法及非暫時性電腦可讀儲存媒體
US12159358B2 (en) High-speed real-time scene reconstruction from input image data
US12073601B2 (en) Determining visual overlap of images by using box embeddings