PFI:AIR-TT: Kinect-Based Low-Cost Motion Analysis System for Medical Applications

PFI:AIR-TT：适用于医疗应用的基于 Kinect 的低成本运动分析系统

• 批准号: 1543172
• 负责人: Ruigang Yang
• 金额: $ 19.99万
• 依托单位: University of Kentucky Research Foundation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-09-01 至 2018-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1543172&HistoricalAwards=false
• 关键词: PFI; AIR; TT; Kinect; Based

This PFI: AIR Technology Translation project focuses on translating innovative single-view motion capture technology to fill the need of medical professionals to quantify a patient?s body movement. This single-view motion capture system is important because it will be a transformational technological improvement that is available to physicians and physical therapists to diagnosis, treat, and monitor patients with a movement disorder. The project will result in a prototype system that will provide a live demonstration to potential customers and investors. This prototype system will consist of a single Kinect camera and a laptop. It will acquire motion data, process the data close to real-time, and provide visual feedback to the patients as well as the clinicians. In particular the performance measures for the clinicians will be anatomically correct and accurate so progress in treating movement dysfunction can be quantified. Compared to the leading motion capture system in the market place today, this project will lead to a portable, low-cost single-camera system that will give medical professionals accurate and precise 3D measurements of movement dysfunction in any environment. This project addresses the following technology gaps as it translates from research discovery toward commercial application. The first and foremost is the need to automatically identify anthropometric landmarks in the input data to define an anatomically correct coordinate system. A novel data-driven method is to going to be investigated. The second is the need to achieve faster processing speed and consolidate the processing pipeline. Simplified tracking algorithm and code optimization will be implemented to achieve the required real-time performance. In addition, personnel involved in this project, in particular both graduate and undergraduate students, will not only receive innovation experiences throughout the research and development cycles, but also cultivate their entrepreneurship through the business development activities.

这个项目专注于翻译创新的单视图运动捕捉技术，以满足医疗专业人员量化患者-S身体运动的需求。这种单视图运动捕捉系统很重要，因为它将是一项革命性的技术进步，医生和理疗师可以用来诊断、治疗和监测运动障碍患者。该项目将产生一个原型系统，向潜在客户和投资者提供现场演示。这个原型系统将由一台Kinect摄像头和一台笔记本电脑组成。它将采集运动数据，对数据进行接近实时的处理，并向患者和临床医生提供视觉反馈。特别是，临床医生的绩效测量将在解剖学上正确和准确，因此在治疗运动功能障碍方面的进展可以被量化。与当今市场上领先的运动捕捉系统相比，该项目将带来一种便携式、低成本的单摄像头系统，将为医疗专业人员提供在任何环境下准确和精确的运动障碍3D测量。该项目在从研究发现转化为商业应用的过程中解决了以下技术差距。第一个也是最重要的是需要自动识别输入数据中的人体测量地标，以定义解剖学上正确的坐标系。一种新的数据驱动方法即将被研究。二是需要实现更快的处理速度，巩固处理流水线。将实施简化的跟踪算法和代码优化，以达到所需的实时性能。此外，参与该项目的人员，特别是研究生和本科生，不仅将在整个研发周期获得创新经验，还将通过商业发展活动培养他们的创业精神。