Sprague Alexander H, Vogel Christopher, Williams Mylah, Wolf Evelynne, Kamper Derek
Lampe Joint Department of Biomedical Engineering at the University of North Carolina at Chapel Hill (Chapel Hill, NC) and North Carolina State University (Raleigh, NC), Raleigh, NC 27695, USA.
Closed-Loop Engineering for Advanced Rehabilitation Research Core, University of North Carolina at Chapel Hill and North Carolina State University, Raleigh, NC 27695, USA.
Sensors (Basel). 2025 Sep 13;25(18):5716. doi: 10.3390/s25185716.
Tracking hand kinematics is essential for numerous clinical and scientific applications. Markerless motion capture devices have advantages over other modalities in terms of calibration, set up, and overall ease of use; however, their accuracy during dynamic tasks has not been fully explored. This study examined the performance of two popular markerless systems, the Leap Motion Controller 2 (LM2) and MediaPipe (MP), in capturing joint motion of the digits. Data were compared to joint motion collected from a marker-based multi-camera system (Vicon). Eleven participants performed six tasks with their dominant right hand at three movement speeds while all three devices simultaneously captured the position of hand landmarks. Using these data, digit joint angles were calculated. The root mean squared error (RMSE) and correlation coefficient () relative to the Vicon angles were computed for LM2 and MP. LM2 achieved a lower error ( < 0.001, mean RMSE = 14.8°) and a higher correlation ( = 0.007, mean = 0.58) than the MP system (mean RMSE = 22.5°, mean = 0.45). Greater movement speed led to significantly higher RMSE ( < 0.001) and lower ( < 0.001) for MP but not for LM2. Error was substantially greater for the proximal interphalangeal joint than for other finger joints, although values were higher for this joint. Overall, the LM2 and MP systems were able to capture motion at the joint level across digits for a variety of tasks in real time, although the level of error may not be acceptable for certain applications.
跟踪手部运动学对于众多临床和科学应用至关重要。无标记运动捕捉设备在校准、设置和整体易用性方面比其他方式具有优势；然而，其在动态任务中的准确性尚未得到充分探索。本研究考察了两种流行的无标记系统，即Leap Motion Controller 2（LM2）和MediaPipe（MP）在捕捉手指关节运动方面的性能。将数据与从基于标记的多摄像头系统（Vicon）收集的关节运动进行比较。11名参与者用其优势右手以三种运动速度执行六项任务，同时所有三种设备同步捕捉手部标志点的位置。利用这些数据计算手指关节角度。计算了相对于Vicon角度的均方根误差（RMSE）和相关系数（）。与MP系统（平均RMSE = 22.5°，平均 = 0.45）相比，LM2实现了更低的误差（< 0.001，平均RMSE = 14.8°）和更高的相关性（ = 0.007，平均 = 0.58）。更高的运动速度导致MP的RMSE显著更高（< 0.001）且相关性更低（< 0.001），但LM2并非如此。近端指间关节的误差比其他手指关节大得多，尽管该关节的相关性值更高。总体而言，LM2和MP系统能够实时捕捉各手指关节水平的各种任务的运动，尽管误差水平对于某些应用可能不可接受。
