Technische Universität Dresden, Centre for Tactile Internet with Human-in-the-Loop, Dresden, 01062, Germany.
Karlsruhe Institute of Technology, Computer Science, Karlsruhe, 76131, Germany.
Sci Data. 2024 Nov 9;11(1):1209. doi: 10.1038/s41597-024-04020-6.
Kinematic data is a valuable source of movement information that provides insights into the health status, mental state, and motor skills of individuals. Additionally, kinematic data can serve as biometric data, enabling the identification of personal characteristics such as height, weight, and sex. In CeTI-Locomotion, four types of walking tasks and the 5 times sit-to-stand test (5RSTST) were recorded from 50 young adults wearing motion capture (mocap) suits equipped with Inertia-Measurement-Units (IMU). Our dataset is unique in that it allows the study of both intra- and inter-participant variability with high quality kinematic motion data for different motion tasks. Along with the raw kinematic data, we provide the source code for phase segmentation and the processed data, which has been segmented into a total of 4672 individual motion repetitions. To validate the data, we conducted visual inspection as well as machine-learning based identity and action recognition tests, achieving 97% and 84% accuracy, respectively. The data can serve as a normative reference of gait and sit-to-stand movements in healthy young adults and as training data for biometric recognition.
运动学数据是一种有价值的运动信息来源，可以深入了解个体的健康状况、精神状态和运动技能。此外，运动学数据可以作为生物识别数据，用于识别个人特征，如身高、体重和性别。在 CeTI-Locomotion 中，我们记录了 50 名穿着配备惯性测量单元（IMU）的运动捕捉（mocap）套装的年轻人的四种行走任务和 5 次坐立测试（5RSTST）。我们的数据集具有独特性，因为它允许使用高质量的运动学运动数据来研究不同运动任务的个体内和个体间的可变性。除了原始运动学数据，我们还提供了相位分割的源代码和处理后的数据，这些数据已被分割成总共 4672 个单独的运动重复。为了验证数据，我们进行了视觉检查以及基于机器学习的身份和动作识别测试，分别达到了 97%和 84%的准确率。该数据集可用作健康年轻成年人的步态和坐立运动的标准参考，也可用作生物识别的训练数据。
