Laboratoire Jean Kuntzmann, CNRS UMR 5224, Université Grenoble Alpes, 38400 Saint Martin d'Hères, France.
Institut Pprime, CNRS UPR 3346, Université de Poitiers, 86360 Chasseneuil-du-Poitou, France.
Sensors (Basel). 2022 Apr 1;22(7):2712. doi: 10.3390/s22072712.
Two-dimensional deep-learning pose estimation algorithms can suffer from biases in joint pose localizations, which are reflected in triangulated coordinates, and then in 3D joint angle estimation. Pose2Sim, our robust markerless kinematics workflow, comes with a physically consistent OpenSim skeletal model, meant to mitigate these errors. Its accuracy was concurrently validated against a reference marker-based method. Lower-limb joint angles were estimated over three tasks (walking, running, and cycling) performed multiple times by one participant. When averaged over all joint angles, the coefficient of multiple correlation (CMC) remained above 0.9 in the sagittal plane, except for the hip in running, which suffered from a systematic 15° offset (CMC = 0.65), and for the ankle in cycling, which was partially occluded (CMC = 0.75). When averaged over all joint angles and all degrees of freedom, mean errors were 3.0°, 4.1°, and 4.0°, in walking, running, and cycling, respectively; and range of motion errors were 2.7°, 2.3°, and 4.3°, respectively. Given the magnitude of error traditionally reported in joint angles computed from a marker-based optoelectronic system, Pose2Sim is deemed accurate enough for the analysis of lower-body kinematics in walking, cycling, and running.
二维深度学习姿势估计算法可能会受到关节姿势定位的偏差影响，这些偏差反映在三角坐标中，进而影响到 3D 关节角度估计。我们的强大无标记运动学工作流程 Pose2Sim 配备了物理一致的 OpenSim 骨骼模型，旨在减轻这些误差。它的准确性与基于参考标记的方法同时进行了验证。一位参与者多次执行三个任务（步行、跑步和骑自行车），并估计了下肢关节角度。当平均所有关节角度时，除了跑步时髋关节受到 15°系统偏差影响（CMC=0.65）和骑自行车时踝关节部分遮挡影响（CMC=0.75）外，矢状面的多重相关系数（CMC）均保持在 0.9 以上。当平均所有关节角度和所有自由度时，步行、跑步和骑自行车的平均误差分别为 3.0°、4.1°和 4.0°；运动范围误差分别为 2.7°、2.3°和 4.3°。考虑到传统上从基于标记的光电系统计算关节角度时报告的误差幅度，Pose2Sim 被认为足以准确分析步行、跑步和骑自行车时的下肢运动学。
