Gait analysis offers vital insights into human movement, aiding in the diagnosis, treatment, and rehabilitation of various conditions. Analyzing gait in corridors, rather than in lab, provides unique advantages for a more comprehensive understanding of human locomotion. However, limited dedicated technologies constrain gait data analysis in this context. In this study, a markerless gait analysis system using an Azure Kinect sensor mounted on a mobile robot is proposed and validated as a potential solution for gait analysis in corridors. Ten healthy participants (4 males and 6 females) underwent two tests. The first test (5 trials per participant) took place in the laboratory. Here, Azure Kinect performance was validated against a Vicon system, assessing eight gait signals and 22 gait parameters. The second test (2 trials per participant) was performed in the corridors over a 32‐m walking distance to compare this gait pattern with the one developed within the laboratory. The intrasession Intraclass Correlation Coefficient (ICC) reliability for in‐lab experiments was assessed by calculating the ICC between gait cycles captured in each session per participant. Notably, knee flexion/extension (ICC‐0.95), hip flexion/extension (ICC‐0.96), pelvis rotation (ICC‐0.88), and interankle distance (ICC‐0.98) demonstrated excellent reliability with high confidence. Similarly, hip adduction/abduction showed good reliability (ICC‐0.79), while trunk rotation exhibited moderate reliability (ICC‐0.72). In contrast, both trunk tilt (ICC‐0.24) and pelvis tilt (ICC‐0.41) consistently displayed lower reliability. This was observed for both the Vicon and the Azure systems, highlighting the intricate nature of capturing precise data for these specific signals in both systems. Validity outcomes indicated comparable error rates to literature standards ( knee flexion/extension, hip flexion/extension, and hip adduction/abduction), with 11 parameters having no significant differences from Vicon. Comparison of in‐lab and in‐corridor experiments show that individuals exhibit significantly longer stride time (1.10 s vs. 1.05 s), lower pelvis tilt ( vs. ), and lower minimum pelvis rotation ( vs. ) when walking in the laboratory. This study demonstrates promising outcomes in outdoor gait analysis with a robot‐mounted camera, revealing significant distinctions from controlled laboratory evaluations

中文翻译：

---

机器人驱动的步态分析：评估 Azure Kinect 在实验室与走廊环境中的性能

步态分析提供了对人体运动的重要见解，有助于各种疾病的诊断、治疗和康复。在走廊而不是在实验室中分析步态为更全面地了解人类运动提供了独特的优势。然而，有限的专用技术限制了这种情况下的步态数据分析。在本研究中，提出并验证了一种使用安装在移动机器人上的 Azure Kinect 传感器的无标记步态分析系统，作为走廊步态分析的潜在解决方案。十名健康参与者（4 名男性和 6 名女性）接受了两项测试。第一个测试（每个参与者 5 次试验）在实验室进行。在这里，Azure Kinect 的性能针对 Vicon 系统进行了验证，评估了 8 个步态信号和 22 个步态参数。第二次测试（每个参与者进行 2 次试验）在走廊中进行，步行距离为 32 米，以将这种步态模式与实验室内开发的步态模式进行比较。通过计算每个参与者在每个会话中捕获的步态周期之间的 ICC 来评估实验室实验的会话内类内相关系数 (ICC) 可靠性。值得注意的是，膝关节屈曲/伸展 (ICC-0.95)、髋关节屈曲/伸展 (ICC-0.96)、骨盆旋转 (ICC-0.88) 和踝间距离 (ICC-0.98) 表现出出色的可靠性和高置信度。同样，髋关节内收/外展显示出良好的可靠性（ICC-0.79），而躯干旋转显示出中等可靠性（ICC-0.72）。相比之下，躯干倾斜（ICC-0.24）和骨盆倾斜（ICC-0.41）始终表现出较低的可靠性。Vicon 和 Azure 系统都观察到了这一点，凸显了在两个系统中捕获这些特定信号的精确数据的复杂性。有效性结果表明错误率与文献标准（膝关节屈曲/伸展、髋关节屈曲/伸展和髋关节内收/外展）相当，其中 11 个参数与 Vicon 没有显着差异。实验室内和走廊内实验的比较表明，个体在实验室行走时表现出明显更长的步幅时间（1.10 秒与 1.05 秒）、较低的骨盆倾斜（与 ）和较低的最小骨盆旋转（与 ）。这项研究展示了使用安装在机器人上的摄像头进行户外步态分析的良好结果，揭示了与受控实验室评估的显着区别