KR102397268B1 - 시나리오 깊이와 카메라 움직임 예측 방법 및 장치, 기기, 매체와 프로그램 - Google Patents

시나리오 깊이와 카메라 움직임 예측 방법 및 장치, 기기, 매체와 프로그램 Download PDF

Info

Publication number
KR102397268B1
KR102397268B1 KR1020217036422A KR20217036422A KR102397268B1 KR 102397268 B1 KR102397268 B1 KR 102397268B1 KR 1020217036422 A KR1020217036422 A KR 1020217036422A KR 20217036422 A KR20217036422 A KR 20217036422A KR 102397268 B1 KR102397268 B1 KR 102397268B1
Authority
KR
South Korea
Prior art keywords
image frame
prediction
time
depth
sample
Prior art date
Application number
KR1020217036422A
Other languages
English (en)
Korean (ko)
Other versions
KR20210138788A (ko
Inventor
타오 한
잔펭 장
후이 쳉
Original Assignee
선전 센스타임 테크놀로지 컴퍼니 리미티드
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 선전 센스타임 테크놀로지 컴퍼니 리미티드 filed Critical 선전 센스타임 테크놀로지 컴퍼니 리미티드
Publication of KR20210138788A publication Critical patent/KR20210138788A/ko
Application granted granted Critical
Publication of KR102397268B1 publication Critical patent/KR102397268B1/ko

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/50—Depth or shape recovery
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00—Machine learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/207—Analysis of motion for motion estimation over a hierarchy of resolutions
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • 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
    • G06T2207/20—Special algorithmic details
    • G06T2207/20081—Training; Learning
    • 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
    • G06T2207/30244—Camera pose

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Medical Informatics (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Image Analysis (AREA)
  • Studio Devices (AREA)
  • Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
  • Auxiliary Devices For Music (AREA)
KR1020217036422A 2020-04-28 2021-02-08 시나리오 깊이와 카메라 움직임 예측 방법 및 장치, 기기, 매체와 프로그램 KR102397268B1 (ko)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
CN202010348872.2 2020-04-28
CN202010348872.2A CN111540000B (zh) 2020-04-28 2020-04-28 场景深度和相机运动预测方法及装置、电子设备和介质
PCT/CN2021/076038 WO2021218282A1 (zh) 2020-04-28 2021-02-08 场景深度和相机运动预测方法及装置、设备、介质和程序

Publications (2)

Publication Number Publication Date
KR20210138788A KR20210138788A (ko) 2021-11-19
KR102397268B1 true KR102397268B1 (ko) 2022-05-12

Family

ID=71977213

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020217036422A KR102397268B1 (ko) 2020-04-28 2021-02-08 시나리오 깊이와 카메라 움직임 예측 방법 및 장치, 기기, 매체와 프로그램

Country Status (5)

Country Link
JP (1) JP7178514B2 (ja)
KR (1) KR102397268B1 (ja)
CN (1) CN111540000B (ja)
TW (1) TWI767596B (ja)
WO (1) WO2021218282A1 (ja)

Families Citing this family (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111540000B (zh) * 2020-04-28 2021-11-05 深圳市商汤科技有限公司 场景深度和相机运动预测方法及装置、电子设备和介质
CN112492230B (zh) * 2020-11-26 2023-03-24 北京字跳网络技术有限公司 视频处理方法、装置、可读介质及电子设备
CN112232322A (zh) * 2020-12-14 2021-01-15 支付宝(杭州)信息技术有限公司 一种基于对象状态预测的图像生成方法及装置
CN112767481B (zh) * 2021-01-21 2022-08-16 山东大学 一种基于视觉边缘特征的高精度定位及建图方法
CN114339402A (zh) * 2021-12-31 2022-04-12 北京字节跳动网络技术有限公司 视频播放完成率预测方法、装置、介质及电子设备
KR102559936B1 (ko) * 2022-01-28 2023-07-27 포티투닷 주식회사 단안 카메라를 이용하여 깊이 정보를 추정하는 방법 및 장치
WO2023155043A1 (zh) * 2022-02-15 2023-08-24 中国科学院深圳先进技术研究院 一种基于历史信息的场景深度推理方法、装置及电子设备
CN114998403A (zh) * 2022-06-13 2022-09-02 北京百度网讯科技有限公司 深度预测方法、装置、电子设备、介质
TWI823491B (zh) * 2022-07-22 2023-11-21 鴻海精密工業股份有限公司 深度估計模型的優化方法、裝置、電子設備及存儲介質

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2019099684A1 (en) * 2017-11-15 2019-05-23 Google Llc Unsupervised learning of image depth and ego-motion prediction neural networks
JP2019530926A (ja) * 2016-09-15 2019-10-24 グーグル エルエルシー イメージ深度予測ニューラルネットワーク
US20200089977A1 (en) 2018-09-17 2020-03-19 Honda Motor Co., Ltd. Driver behavior recognition and prediction

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106780543B (zh) * 2017-01-13 2019-06-28 深圳市唯特视科技有限公司 一种基于卷积神经网络的双框架估计深度和运动方法
EP3847619B1 (en) * 2018-09-05 2023-11-01 Google LLC Unsupervised depth prediction neural networks
CN109978851B (zh) * 2019-03-22 2021-01-15 北京航空航天大学 一种红外视频空中弱小运动目标检测跟踪方法
CN110060286B (zh) * 2019-04-25 2023-05-23 东北大学 一种单目深度估计方法
CN110136185B (zh) * 2019-05-23 2022-09-06 中国科学技术大学 一种单目深度估计方法及系统
CN110264526B (zh) * 2019-06-19 2023-04-07 华东师范大学 一种基于深度学习的场景深度和摄像机位置姿势求解方法
CN110310317A (zh) * 2019-06-28 2019-10-08 西北工业大学 一种基于深度学习的单目视觉场景深度估计的方法
CN110378250B (zh) * 2019-06-28 2021-04-09 深圳先进技术研究院 用于场景认知的神经网络的训练方法、装置及终端设备
CN110503680B (zh) * 2019-08-29 2023-08-18 大连海事大学 一种基于非监督的卷积神经网络单目场景深度估计方法
CN110942484B (zh) * 2019-11-26 2022-07-12 福州大学 基于遮挡感知和特征金字塔匹配的相机自运动估计方法
CN111028282A (zh) * 2019-11-29 2020-04-17 浙江省北大信息技术高等研究院 一种无监督位姿与深度计算方法及系统
CN111540000B (zh) * 2020-04-28 2021-11-05 深圳市商汤科技有限公司 场景深度和相机运动预测方法及装置、电子设备和介质

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2019530926A (ja) * 2016-09-15 2019-10-24 グーグル エルエルシー イメージ深度予測ニューラルネットワーク
WO2019099684A1 (en) * 2017-11-15 2019-05-23 Google Llc Unsupervised learning of image depth and ego-motion prediction neural networks
US20200089977A1 (en) 2018-09-17 2020-03-19 Honda Motor Co., Ltd. Driver behavior recognition and prediction

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Haokui Zhang 등, Exploiting temporal consistency for real-time video depth estimation, arXiv:1908.03706v1(2019.08.10.)
Rui Wang 등, Recurrent Neural Network for (Un-)supervised Learning of Monocular Video Visual Odometry and Depth, arXiv:1904.07087v1(2019.04.15.)

Also Published As

Publication number Publication date
KR20210138788A (ko) 2021-11-19
TW202141428A (zh) 2021-11-01
CN111540000B (zh) 2021-11-05
CN111540000A (zh) 2020-08-14
JP7178514B2 (ja) 2022-11-25
WO2021218282A1 (zh) 2021-11-04
CN113822918A (zh) 2021-12-21
TWI767596B (zh) 2022-06-11
JP2022528012A (ja) 2022-06-07

Similar Documents

Publication Publication Date Title
KR102397268B1 (ko) 시나리오 깊이와 카메라 움직임 예측 방법 및 장치, 기기, 매체와 프로그램
CN109829863B (zh) 图像处理方法及装置、电子设备和存储介质
CN110798630B (zh) 图像处理方法及装置、电子设备和存储介质
CN111401230B (zh) 姿态估计方法及装置、电子设备和存储介质
CN111783986A (zh) 网络训练方法及装置、姿态预测方法及装置
CN111104920B (zh) 视频处理方法及装置、电子设备和存储介质
KR20210090238A (ko) 비디오 처리 방법 및 장치, 전자 기기, 및 기억 매체
JP7316456B2 (ja) 点群マップ構築方法及びその装置、電子機器、記憶媒体並びにプログラム
KR20210024631A (ko) 이미지 처리 방법 및 장치, 전자 기기 및 저장 매체
KR20220123218A (ko) 타깃 포지셔닝 방법, 장치, 전자 기기, 저장 매체 및 프로그램
US20220383517A1 (en) Method and device for target tracking, and storage medium
CN113139471A (zh) 目标检测方法及装置、电子设备和存储介质
KR20220047802A (ko) 이미지 재구성 방법 및 장치, 전자 기기 및 저장 매체
CN111832338A (zh) 对象检测方法及装置、电子设备和存储介质
CN111784772B (zh) 基于域随机化的姿态估计模型训练方法及装置
CN112669338B (zh) 图像分割方法及装置、电子设备和存储介质
CN115035440A (zh) 时序动作提名的生成方法及装置、电子设备和存储介质
CN113822918B (zh) 场景深度和相机运动预测方法及装置、电子设备和介质
CN114842404A (zh) 时序动作提名的生成方法及装置、电子设备和存储介质
CN113506325A (zh) 图像处理方法及装置、电子设备和存储介质
CN113506324A (zh) 图像处理方法及装置、电子设备和存储介质
CN112800954A (zh) 文本检测方法及装置、电子设备和存储介质
CN112461245A (zh) 数据处理方法及装置、电子设备和存储介质
CN112967311B (zh) 三维线图构建方法及装置、电子设备和存储介质
CN113435390A (zh) 人群定位方法及装置、电子设备和存储介质

Legal Events

Date Code Title Description
A201 Request for examination
A302 Request for accelerated examination
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant