Human hand motion data collected by commercial motion capture system and custom-made data glove

This dataset presents diverse <b>human hand motions </b>in various forms including:<b>Forward kinematic hand model </b>implemented in 3d computer graphics software tool (<i>/Joint angles/HandModel.blend</i>);<b>Bone lengths </b>of 13 subjects (9 males, 4 females);<b>Motion-captured rotations of the finger bones </b>in Euler angles;<b>Joint angles of the finger joints </b>that were calculated by post-processing the motion-captured rotations.Also, with the aim of <b>real-time tracking </b>of these hand motions using the <b>custom-made data glove</b>, we provide:<b>Sensor signals </b>measured by the data glove during the hand motions;<b>Regression model </b>that relates the <b>bone lengths </b>and the <b>sensor signals </b>measured at the zero pose for instantaneous estimation of the bone lengths of the wearer;<b>Filtering process </b>for further refinement of the <b>bone lengths </b>estimation using the subsequent sensor signals;<b>Filtering process </b>for estimation of the <b>joint angles </b>using the subsequent sensor signals.<b>Readme</b>The dataset is composed of three folders (<i>/Initial bone lengths</i>, <i>/Refined bone lengths</i>, and <i>/Joint angles</i>) and in each folder there exists Matlab or Python script that infers the collected motion-capture data and sensor signals in the <i>/Data</i> folder.How to use:Initial bone lengths: Run InitialBoneLengthsEstimation.m<br>Refined bone lengths: Run RefinedBoneLengthsEstimation.m<br>Joint angles<br>1. Run Calibration.py to output the linear model (already included in ./Data/230703_1440/model)<br>2. Open HandModel.blend, Open Text editor, and Press Run script (Alt+P)<br>3. Run JointAngleEstimation.py<br>Detailed results, experimental procedures, post-processing methods of the data, and the filtering algorithms are described in <b>Stretchable glove for accurate and robust hand pose reconstruction based on comprehensive motion data</b>, <i>Nature Communications</i>, 2024 (https://doi.org/10.1038/s41467-024-50101-w).