ULTra-MoCap

Dataset files related to the paper ULTRA-MoCap: A Multimodal IMU and sEMG Dataset for Deep Learning-Based Upper Body Joint Kinematic<b>Authors</b>:Oliver Fritsche, Steven Camacho, Md Sanzid Bin Hossain, Tyler Halpenny, Carlos Archniegas, Joseph Dranetz, Dexter Hadley, Zhishan Guo, and Hwan Choi<b>Abstract: </b>Predicting human kinematics from multi-modal sensor data has applications in rehabilitation, sports analysis, assistive device control, and human-computer interaction, offering less intrusive alternatives to camera-based motion capture (MoCap) systems. However, current datasets often lack comprehensive multi-modal data integrating both IMU and sEMG sensors, with limited coverage for upper limb kinematics and insufficient capture of high-fidelity muscle activation and joint dynamics, especially for complex shoulder and elbow movements. These limitations impede the development of robust models for advanced applications. To address these gaps, we introduce the Upper Limb Tracking with Multi-modal Capture (ULTra-MoCap) dataset. It includes IMUs on the hand, wrist, and forearm, and combined sEMG/IMU sensors on the biceps brachii, triceps brachii, and deltoid, enabling detailed tracking of multiple degrees of freedom upper limb kinematics. Data was collected from 13 healthy subjects using Vicon Vero motion capture cameras and Delsys Trigno sEMG/IMU sensors with various upper limb movements. This paper details the data collection, sensor placement, and processing pipeline, establishing ULTRA-MoCap as a benchmark for deep learning applications.________________________________________________________ULTra-MoCap-processed contains already processed data reading for downstream deep learning.ULTra-MoCap-raw contains subjects [1-6](0) and [7-13](1) raw data for reproducibility._________________________________________________________________

本数据集对应论文《ULTRA-MoCap：面向基于深度学习的上肢关节运动学研究的多模态惯性测量单元（IMU）与表面肌电（sEMG）数据集》
**作者**：Oliver Fritsche、Steven Camacho、Md Sanzid Bin Hossain、Tyler Halpenny、Carlos Archniegas、Joseph Dranetz、Dexter Hadley、Zhishan Guo、Hwan Choi
**摘要**：从多模态传感器数据中预测人体运动学，在康复医学、运动分析、辅助设备控制以及人机交互领域均具有应用价值，可为基于摄像头的运动捕捉（MoCap）系统提供侵入性更低的替代方案。然而，现有数据集往往缺乏集成惯性测量单元与表面肌电传感器的全面多模态数据，对上肢体运动学的覆盖范围有限，且对高保真肌肉激活与关节动力学的捕捉不足，尤其是针对复杂肩肘运动的相关数据。这些局限性阻碍了面向高级应用的鲁棒模型开发。为填补上述研究空白，本团队推出了多模态捕捉上肢追踪数据集（ULTra-MoCap）。该数据集包含佩戴于手部、腕部与前臂的IMU，以及附着于肱二头肌、肱三头肌与三角肌的集成式sEMG/IMU传感器，可实现多自由度上肢体运动学的精细追踪。研究团队依托Vicon Vero运动捕捉相机与Delsys Trigno sEMG/IMU传感器，招募13名健康受试者完成各类上肢运动数据采集。本文详细阐述了该数据集的采集流程、传感器部署方案与数据处理管线，确立了ULTra-MoCap作为深度学习应用基准数据集的地位。
________________________________________________________
ULTra-MoCap-processed 包含已完成预处理的下游深度学习可用数据。
ULTra-MoCap-raw 包含受试者[1-6]（分组0）与[7-13]（分组1）的原始数据，以保障实验可重复性。
_________________________________________________________________

搜集汇总

背景与挑战

背景概述

ULTra-MoCap是一个多模态IMU和sEMG数据集，专注于上肢关节运动学的深度学习应用，包含13名健康受试者的数据，分为已处理和原始数据两部分，旨在为深度学习模型提供基准。