Markerless motion capture equipment for the development of a multi-centre biomechanical analysis tool

用于开发多中心生物力学分析工具的无标记动作捕捉设备

• 批准号: RTI-2022-00451
• 负责人: Deluzio, Kevin
• 金额: $ 8.35万
• 依托单位: Queen's University
• 依托单位国家: 加拿大
• 项目类别: Research Tools and Instruments
• 财政年份: 2021
• 资助国家: 加拿大
• 起止时间: 2021-01-01 至 2022-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=743068
• 关键词: Markerless; motion; capture; equipment; development

Human movement researchers across Canada have an opportunity to reimagine what data collection looks like with innovative new technology. Using a machine learning-based markerless motion capture system that extracts biomechanical data from synchronized videos, we are developing the next generation of biomechanical analysis tools. This equipment grant will support the purchase of the optimal video camera systems for markerless motion capture. One system will be used in the Human Mobility Research Laboratory of Dr. Kevin Deluzio, who is an experienced human motion researcher and a pioneer in the adoption of markerless technology. Two additional systems will be a set of mobile systems for our collaborator and for remote site data collection. This will allow us to take a motion capture lab to any site. The result will be the most cost-effective and least invasive way of collecting human movement data. By removing physical barriers to data collection, we can partner with our collaborator Dr. Janie Wilson at the Dynamics of Human Motion Laboratory at Dalhousie University to do multi-site biomechanics research. Markerless motion capture provides a feasible way to collect biomechanical data with a level of reliability that is not achievable by legacy technologies, unlocking the potential to collect these data at an epidemiological scale. Building biomechanical analysis tools from large datasets collected on diverse populations, including individuals with musculoskeletal diseases, will ensure the development of robust and effective tools. This type of research on vulnerable patients has been severely limited by the nature of the preceding marker-based technology and underscores the forthcoming expansion of human mobility research resulting from this new technology. This research (currently supported by NSERC-DG and NSERC-CRD grants) will be severely impacted by a delay in acquisition of equipment as the requested camera systems will replace existing equipment that is not suitable for the proposed work due to limits in the area that can be recorded. Over the next five years it is projected that 50 HQPs will use these systems in addition to the 8 current post-graduates that have research planned and ongoing working with the system. Markerless motion capture marks a major advancement in the field of biomechanics and will have an incredible impact on both the progression of fundamental research and the application of this research to musculoskeletal diseases, clinical movement disorders, injuries, and athletic performance. By supporting the purchase of markerless motion capture video camera systems, the Human Mobility Research Laboratory in partnership with Dynamics of Human Motion Laboratory will lead the way towards the development of biomechanical analysis tools that can be used for future translational research.

加拿大各地的人类运动研究人员有机会通过创新的新技术重新想象数据收集的样子。使用基于机器学习的无标记运动捕捉系统，从同步视频中提取生物力学数据，我们正在开发下一代生物力学分析工具。这笔设备赠款将用于支持购买用于无标记动作捕捉的最佳摄像机系统。其中一个系统将用于Kevin Bazzio博士的人体移动研究实验室，他是一位经验丰富的人体运动研究人员，也是采用无标记技术的先驱。另外两个系统将是一套移动的系统，用于我们的合作者和远程站点数据收集。这将使我们能够将动作捕捉实验室带到任何地点。其结果将是最具成本效益和最少侵入性的方式收集人类运动数据。通过消除数据收集的物理障碍，我们可以与达尔豪西大学人体运动动力学实验室的合作者Janie Wilson博士合作进行多地点生物力学研究。无标记运动捕捉提供了一种可行的方法来收集生物力学数据，其可靠性水平是传统技术无法实现的，从而释放了在流行病学规模上收集这些数据的潜力。从不同人群（包括肌肉骨骼疾病患者）收集的大型数据集构建生物力学分析工具，将确保开发强大有效的工具。这类对弱势患者的研究受到了先前基于标记的技术性质的严重限制，并强调了这项新技术即将带来的人类流动性研究的扩展。这项研究（目前由NSERC-DG和NSERC-CRD赠款）将受到设备采购延迟的严重影响，因为所要求的摄像机系统将取代现有设备，这些设备由于可以记录的区域限制而不适合拟议的工作。在今后五年中，预计将有50名HQP使用这些系统，此外还有8名正在计划和正在使用该系统进行研究的研究生。无标记运动捕捉标志着生物力学领域的重大进步，将对基础研究的进展以及这项研究在肌肉骨骼疾病、临床运动障碍、损伤和运动表现方面的应用产生令人难以置信的影响。通过支持购买无标记运动捕捉摄像机系统，人类移动研究实验室与人体运动动力学实验室合作，将引领生物力学分析工具的发展，可用于未来的转化研究。