完整的惯性位姿数据集:从原始测量到使用低成本和高端的MARG传感器的位姿
Complete Inertial Pose Dataset: from raw measurements to pose with low-cost and high-end MARG sensors
摘要:
由于其低侵入性和符合日常使用要求,用于姿势监测的可穿戴技术的使用一直在扩大。然而,仍然存在限制其广泛使用的公开挑战,特别是在处理低成本系统时。大多数解决方案要么是成本高的功能齐全的商业产品,要么是性能较低的临时解决方案。此外,很少有数据集,从其中可以得出完整的和一般的解决方案。本研究提出了两个数据集,分别包含低成本和高端的【形】形状的磁、角速率和重力(MARG)传感器数据。它为完整的惯性姿态管道的分析提供数据,从原始测量到传感器到分段校准,多传感器融合,骨架运动学,到完整的人体姿态。分别收集了21名和10名受试者的多项试验,执行6种类型的序列(从校准到日常活动和随机运动)。它呈现出高度的可变性和复杂的动力学,几乎具有完整的运动范围,同时包含在真实条件下发现的常见误差源。这相当于350万个样本,与60 Hz的地面真实惯性运动捕捉系统同步。简要介绍了一种简单的端到端惯性姿态方法,并用于验证两次采集的数据质量。该数据库可以有助于评估、基准测试和开发用于管道的每个处理步骤的新颖算法,其应用于经典或数据驱动的惯性姿态估计算法、人类运动理解和预测以及工业或康复环境中的人体工程学评估。所有数据都可以在在线数据库上免费获得,并附带代码来处理和分析完整的数据管道。
英文摘要:
The use of wearable technology for posture monitoring has been expanding due to its low-intrusiveness and compliance with daily use requirements. However, there are still open challenges limiting its widespread use, especially when dealing with low-cost systems. Most solutions falls either into fully functioning commercial products with high costs, or ad-hoc solutions with lower performance. Moreover, there are few datasets available, from which complete and general solutions can be derived. This work presents 2 datasets, containing low-cost and high-end Magnetic, Angular Rate, and Gravity (MARG) sensor data respectively. It provides data for the analysis of the complete inertial pose pipeline, from raw measurements, to sensor-to-segment calibration, multi-sensor fusion, skeleton kinematics, to the complete human pose. Multiple trials were collected with 21 and 10 subjects respectively, performing 6 types of sequences (ranging from calibration, to daily-activities and random movements). It presents a high degree of variability and complex dynamics with almost complete range-of-motion, while containing common sources of error found on real conditions. This amounts to 3.5M samples, synchronized with a ground-truth inertial motion capture system at 60hz. A simple end-to-end inertial pose method was briefly described and used to validate the quality of the data in both acquisitions. This database may contribute to assess, benchmark and develop novel algorithms for each of the pipelines' processing steps, with applications in classic or data-driven inertial pose estimation algorithms, human movement understanding and forecasting and ergonomic assessment in industrial or rehabilitation settings. All the data is freely available on an online database and accompanied with code to process and analyze the complete data pipeline.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。