Avatar-Guided Estimation of Human Shape and Motion

虚拟形象引导的人体形状和运动估计

基本信息

  • 批准号:
    0208965
  • 负责人:
  • 金额:
    $ 37.01万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2002
  • 资助国家:
    美国
  • 起止时间:
    2002-08-01 至 2006-07-31
  • 项目状态:
    已结题

项目摘要

We propose a research program to develop vision algorithms that infer human form and action from video sequences. The main feature of the approach is the use of an animated humanoid avatar to provide strong expectations on body shape and motion. A temporal sequence of body silhouette images is collapsed using line projections into four two-dimensional patterns that can be analyzed using robust signal processing techniques. To identify activities, patterns generated from video of a person are matched against spatio-temporal prototypes generated from the humanoid avatar. A moment-based method for coarse temporal and spatial pattern alignment brings model and data patterns into registration, so that they can be compared to classify viewpoint and activity. The resulting coarse alignment predicts 2D body topology and occlusion in each video frame, which enables a 2D nonrigid shape matching method based on thin-plate splines to identify and delineate body parts in each image. The avatar data also predicts which body dimension measurements can be made most reliably in which image frames, leading to efficient and accurate recovery of 3D body shape, pose and motion. We initially plan to focus on observations of human gait. Gait analysis shares many of the same challenges as the general activity analysis problem, namely high degree of freedom articulated motion, occlusion of body parts from 2D viewpoints, and idiosyncratic performance by different individuals. At the same time, the periodic nature of the activity simplifies temporal alignment of model and data sequences, and improves overall resiliance to noisy data. Success in vision-based gait analysis would enable applications ranging from motion capture for orthopedics to computation of human biometrics for smart rooms and surveillance.
我们提出了一个研究计划,以开发视觉算法,推断人类的形式和行动,从视频序列。 该方法的主要特点是使用一个动画的人形化身,以提供对身体形状和运动的强烈期望。 使用线投影将身体轮廓图像的时间序列折叠成可以使用鲁棒的信号处理技术进行分析的四个二维图案。 为了识别活动,将从人的视频生成的模式与从人形化身生成的时空原型进行匹配。 基于矩的时空模式粗对齐方法将模型和数据模式进行配准,从而可以比较它们来分类视点和活动。 由此产生的粗对齐预测2D身体拓扑结构和闭塞在每个视频帧中,这使得基于薄板样条的2D非刚性形状匹配方法能够识别和描绘每个图像中的身体部位。 化身数据还预测在哪些图像帧中可以最可靠地进行哪些身体尺寸测量,从而导致3D身体形状、姿势和运动的高效且准确的恢复。 我们最初计划专注于观察人类步态。 步态分析与一般的活动分析问题有许多相同的挑战,即高自由度的关节运动,从2D角度看身体部位的遮挡,以及不同个体的特殊表现。 同时,活动的周期性性质简化了模型和数据序列的时间对齐,并提高了对噪声数据的整体顺应性。 基于视觉的步态分析的成功将使从骨科的运动捕捉到智能房间和监控的人体生物特征计算等应用成为可能。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Robert Collins其他文献

3106 – RESIDUAL MUTANT HEMATOPOIETIC STEM CELLS DRIVES POST-TRANSPLANT RELAPSE OF THE MYELODYSPLASTIC SYNDROMES
  • DOI:
    10.1016/j.exphem.2023.06.213
  • 发表时间:
    2023-01-01
  • 期刊:
  • 影响因子:
  • 作者:
    Benjamin Kroger;Albert Son;Yi Huang;Prapti Patel;Aimaz Afrough;Gurbakhash Kaur;Larry Anderson;Farrukh Awan;Praveen Ramakrishnan;Kunal Verma;Russell Vittrup;Robert Collins;Madhuri Vusirikala;Yazan Madanat;Carmelo Gurnari;Jaroslaw Maciejewski;Roni Tamari;Stephen Chung
  • 通讯作者:
    Stephen Chung
<strong>POSTER:</strong> HL-456 A Retrospective Analysis of Impact of EBV Status on Outcomes in Hodgkin Lymphoma
  • DOI:
    10.1016/s2152-2650(23)00684-5
  • 发表时间:
    2023-09-01
  • 期刊:
  • 影响因子:
  • 作者:
    Elif Yilmaz;Heather Reves;Aimaz Afrough;Julio Alvarenga;Larry Anderson;Robert Collins;Stephen Chung;Gurbakhash Kaur;Adeel Khan;Yazan Madanat;Alka Mallik;Heather Wolfe;Praveen Ramakrishnan;Farrukh T. Awan
  • 通讯作者:
    Farrukh T. Awan
Polymorphism in the natural cytotoxicity receptors(NCR) NKp30, NKp44 and NKp46 – a preliminary study
  • DOI:
    10.1016/j.humimm.2005.08.030
  • 发表时间:
    2005-08-01
  • 期刊:
  • 影响因子:
  • 作者:
    Michael A. Clare;Robert Collins;Robert Vaughan
  • 通讯作者:
    Robert Vaughan
Crenolanib and Intensive Chemotherapy in Adults With Newly Diagnosed FLT3-Mutated AML
新诊断 FLT3 突变 AML 成人患者的 Crenolanib 和强化化疗
  • DOI:
    10.1200/jco.23.01061
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    45.3
  • 作者:
    Eunice S. Wang;A. Goldberg;Martin S. Tallman;R. B. Walter;C. Karanes;Karamjeet Sandhu;C. Vigil;Robert Collins;Vinay Jain;Richard M Stone
  • 通讯作者:
    Richard M Stone
3089 – ELUCIDATING NEW MECHANISMS OF ACQUIRED RESISTANCE TO IDH INHIBITION BY SATURATION VARIANT SCREENING OF BASE-EDITED LEUKEMIA CELLS
  • DOI:
    10.1016/j.exphem.2021.12.307
  • 发表时间:
    2021-08-01
  • 期刊:
  • 影响因子:
  • 作者:
    Junhua Lyu;Yuxuan Liu;Lihu Gong;Mingyi Chen;Yazan Madanat;Yuannyu Zhang;Zhimin Gu;Feng Cai;Hui Cao;Pranita Kaphle;Kathryn Dickerson;Weina Chen;Stephen Chung;Robert Collins;Ralph DeBerardinis;Xin Liu;Jian Xu
  • 通讯作者:
    Jian Xu

Robert Collins的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Robert Collins', 18)}}的其他基金

Collaborative Research: Development of a Nanofabrication Lab Manual Featuring a Suite of Low-Cost Experiments to Enable Hands-On Training at Community and Technical Colleges
合作研究:开发纳米制造实验室手册,其中包含一套低成本实验,可在社区和技术学院进行实践培训
  • 批准号:
    2301140
  • 财政年份:
    2023
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Standard Grant
RI: Medium: From Vision to Dynamics
RI:媒介:从愿景到动态
  • 批准号:
    2312967
  • 财政年份:
    2023
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Standard Grant
RI: Small: Distributed Combinatorial Optimization for Crowd-Scene Analysis
RI:小型:人群场景分析的分布式组合优化
  • 批准号:
    1218729
  • 财政年份:
    2012
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Standard Grant
The End of Empire: The northern frontier in the fourth-fifth centuries AD
帝国的终结:公元四五世纪的北部边境
  • 批准号:
    AH/I015000/1
  • 财政年份:
    2011
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Fellowship
RI: EAGER: Robust Opportunistic Fitting of Partial Body Models
RI:EAGER:部分身体模型的鲁棒机会拟合
  • 批准号:
    0951386
  • 财政年份:
    2009
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Standard Grant
Persistent Tracking
持续追踪
  • 批准号:
    0535324
  • 财政年份:
    2005
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Continuing Grant
Novel Real Time Optics for Thin Film Materials Research
用于薄膜材料研究的新型实时光学
  • 批准号:
    0552159
  • 财政年份:
    2005
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Standard Grant
Novel Real Time Optics for Thin Film Materials Research
用于薄膜材料研究的新型实时光学
  • 批准号:
    0137240
  • 财政年份:
    2002
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Standard Grant
Real Time Polarimetry for Tailored Silicon Thin Films
定制硅薄膜的实时偏振测量
  • 批准号:
    9820170
  • 财政年份:
    1999
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Standard Grant
Mechanisms of Indirect Selection
间接选择机制
  • 批准号:
    9696138
  • 财政年份:
    1996
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Continuing grant

相似海外基金

Structure-guided optimisation of light-driven microalgae cell factories
光驱动微藻细胞工厂的结构引导优化
  • 批准号:
    DP240101727
  • 财政年份:
    2024
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Discovery Projects
CAREER: Resilient and Efficient Automatic Control in Energy Infrastructure: An Expert-Guided Policy Optimization Framework
职业:能源基础设施中的弹性和高效自动控制:专家指导的政策优化框架
  • 批准号:
    2338559
  • 财政年份:
    2024
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Standard Grant
CAREER: Probing structural dynamics and regulatory mechanisms of RNA-guided CRISPR-Cas12 endonucleases and their analogues
职业:探索 RNA 引导的 CRISPR-Cas12 核酸内切酶及其类似物的结构动力学和调控机制
  • 批准号:
    2339799
  • 财政年份:
    2024
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Continuing Grant
CRII: CPS: FAICYS: Model-Based Verification for AI-Enabled Cyber-Physical Systems Through Guided Falsification of Temporal Logic Properties
CRII:CPS:FAICYS:通过时态逻辑属性的引导伪造,对支持人工智能的网络物理系统进行基于模型的验证
  • 批准号:
    2347294
  • 财政年份:
    2024
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Standard Grant
Patterning Mesoscale Chirality by Guided Crystal Twisting
通过引导晶体扭曲形成中尺度手性图案
  • 批准号:
    2325911
  • 财政年份:
    2024
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Standard Grant
Novel techniques of percutaneous sonography-guided surgical operations (SonoSurgery
经皮超声引导外科手术新技术(SonoSurgery
  • 批准号:
    10087309
  • 财政年份:
    2024
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Collaborative R&D
A self-guided and monitored innovative AI-driven parental support intervention (mobile app), for families caring for a young one that self-harms: feasibility study
一种自我指导和监控的创新型人工智能驱动的家长支持干预措施(移动应用程序),适用于照顾自残儿童的家庭:可行性研究
  • 批准号:
    10101171
  • 财政年份:
    2024
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Collaborative R&D
Structure-guided modular phage engineering
结构引导的模块化噬菌体工程
  • 批准号:
    24K01675
  • 财政年份:
    2024
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Grant-in-Aid for Scientific Research (B)
FMO/ML-Guided Drug Design: Accelerating Novel Inhibitor Development and Drug Discovery
FMO/ML 引导的药物设计:加速新型抑制剂的开发和药物发现
  • 批准号:
    24K20888
  • 财政年份:
    2024
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Grant-in-Aid for Early-Career Scientists
Sensory Engineering: Investigating Altered and Guided Perception and Hallucination
感官工程:研究改变和引导的感知和幻觉
  • 批准号:
    AH/Y007638/1
  • 财政年份:
    2024
  • 资助金额:
    $ 37.01万
  • 项目类别:
    Research Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了