CAREER: Data-driven Bottom-Up Humanoid Articulations

职业：数据驱动的自下而上的人形关节

• 批准号: 0952720
• 负责人: Georgeta-Elisab Marai
• 金额: $ 53.68万
• 依托单位: University of Pittsburgh
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2010
• 资助国家: 美国
• 起止时间: 2010-04-01 至 2015-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0952720&HistoricalAwards=false
• 关键词: CAREER; Data; driven; Bottom; Up

This project investigates in much more detail the human anatomy and dynamics to further progress in replicating human articulation capabilities. To overcome long-standing imaging limitations, the project follows a data-driven approach, in which sampled dynamic motion data is used to infer unknown parameters such as soft-tissue geometry and behavior. The project is cross-disciplinary and driven by specific problems in orthopaedics and human character animation, although its focus is fundamentally on computational and automated analysis tools. The research plan develops computational tools for capturing robustly and accurately dynamic skeletal motion from medical images, for inferring biological shape and behavior from dynamic motion information, and for representing and calculating with these data. The education effort is naturally integrated with the research work, and includes recruiting and training graduate, undergraduate, and high-school students into multi-disciplinary work, through a modeling and simulation approach to teaching computer graphics. The outcome of the project is a set of human-anatomy based (i.e., humanoid) models of articulations that impacts orthopaedists' understanding of articulation injury and disease, leads to improved diagnosis and medical treatment, and improves the realism of digital character animation. The broad impact of the project includes applications in biology, bioengineering, ergonomics, evolutionary biology and robotics. Results of this project, including software, data, and publications, are publicly available through the project web site, http://vis.cs.pitt.edu/marai_nsf_career

这个项目更详细地研究了人体解剖学和动力学，以进一步在复制人类发音能力方面取得进展。为了克服长期存在的成像限制，该项目遵循数据驱动的方法，使用采样的动态运动数据来推断未知参数，如软组织几何形状和行为。该项目是跨学科的，由骨科和人体角色动画中的特定问题驱动，尽管它的重点基本上是计算和自动分析工具。该研究计划开发计算工具，用于从医学图像中捕获健壮而准确的动态骨骼运动，用于从动态运动信息推断生物形状和行为，并用于使用这些数据来表示和计算。教育工作自然与研究工作相结合，包括招募和培训研究生、本科生和高中生从事多学科的工作，通过建模和模拟方法教授计算机图形学。该项目的成果是一套基于人体解剖学的(即，类人的)关节模型，影响骨科医生对关节损伤和疾病的理解，导致改善诊断和医疗，并提高数字角色动画的真实感。该项目的广泛影响包括在生物学、生物工程、人体工程学、进化生物学和机器人方面的应用。该项目的成果，包括软件、数据和出版物，可通过项目网站http://vis.cs.pitt.edu/marai_nsf_career公开获得