SBIR Phase II: 3D Markerless Motion Capture Technology For Gait Analysis

这项小企业创新研究（SBIR）二期项目的广泛影响/商业潜力使美国7000万与步态障碍作斗争的人受益。步态分析监测个人如何行走，以预测或预防受伤，并跟踪康复进展。由于潜在的高设备成本、空间要求以及收集和解释结果所需的技术专长，详细的步态分析仅限于少数几个中心，主要用于手术决策。该项目使用人工智能（AI）进行步态分析，成本比典型成本低约70%，同时减少了设置时间，提高了工作流程效率。拟议的项目将解决现有的技术和商业障碍，使步态分析成为一种独家临床工具，仅限于全国300个步态实验室。该项目将开发一种具有成本效益的无标记运动3d跟踪系统。技术活动包括：(1)将运动数据库扩展到不同的人群，包括儿童和行动障碍患者；(2)改进计算机视觉算法，以考虑相机系统视场内的多个个体；(3)整合肌电图与力板；(4)实现基于计算机断层扫描的骨骼几何估计；(5)开发可与高清低成本摄像机配合使用的自标定系统；(5)大大提高准确性和可用性，以减少计算步态分析所需的专业知识。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase II project benefitd the 70 million people struggling with gait disorders in the US. Gait analysis monitors how individuals walk to predict or prevent injuries and track rehabilitation progress. Due to the potentially high equipment costs, space requirements, and required technical expertise to collect and interpret results, detailed gait analyses are limited to a few centers and mainly used for surgical decision-making. This project uses Artificial Intelligence (AI) for gait analysis at roughly 70% less than typical costs, as well as offering reduced set-up time and improved workflow efficiency.The proposed project will address the existing technological and commercial barriers that make gait analysis an exclusive clinical tool restricted to only 300 gait labs across the country. This project will develop a cost-effective markerless motion 3D-tracking system. Technical activities include: (1) increase the motion database to a diverse population, including children and patients with mobility impairments; (2) improve the computer vision algorithms to account for multiple individuals within the camera system’s field of view; (3) integrate EMG and Force Plates; (4) implement skeletal geometry estimation from computed tomography; (5) develop a self-calibration system that can operate with HD low cost cameras; and (5) improve accuracy and usability substantially to reduce the expertise required for computational gait analysis.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.