用单目视频和姿态估计，自动建立步态的正常参数基准。
Developing Normative Gait Cycle Parameters for Clinical Analysis Using Human Pose Estimation
- 基于2D姿态估计分析关节角度，实现步态周期内多关节同步测量。
- 仅需单目RGB视频即可对比个体与人群正常值，识别异常偏差。
- 适合临床医生用于客观评估步态障碍，提升诊断效率。
基于计算机视觉的步态分析是人工智能领域的新兴方向，为临床提供一种客观、多特征的复杂运动分析方法。尽管前景广阔，现有仅使用RGB视频的方法在测量临床相关的空间与时间运动学参数方面仍存在局限，难以建立必要的正常参考标准。本文提出一种数据驱动方法，利用单目RGB视频与2D人体姿态估计，构建步态周期的正常运动学参数。通过分析关节角度（一种生物力学与临床实践中广泛使用的运动学指标），我们提升了步态分析能力并增强可解释性。该逐周期的运动学分析使临床医生仅凭单目视频即可同步测量并比较多个关节角度，将个体与正常人群进行对比，扩展了临床评估能力，支持客观决策，并自动化识别步态周期内的特定空间与时间偏离及异常。
原文摘要 · Abstract (English)
Gait analysis using computer vision is an emerging field in AI, offering clinicians an objective, multi-feature approach to analyse complex movements. Despite its promise, current applications using RGB video data alone are limited in measuring clinically relevant spatial and temporal kinematics and establishing normative parameters essential for identifying movement abnormalities within a gait cycle. This paper presents a data-driven method using RGB video data and 2D human pose estimation for developing normative kinematic gait parameters. By analysing joint angles, an established kinematic measure in biomechanics and clinical practice, we aim to enhance gait analysis capabilities and improve explainability. Our cycle-wise kinematic analysis enables clinicians to simultaneously measure and compare multiple joint angles, assessing individuals against a normative population using just monocular RGB video. This approach expands clinical capacity, supports objective decision-making, and automates the identification of specific spatial and temporal deviations and abnormalities within the gait cycle.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。