Hand Motion Capture from a 3D Leap Motion Controller for a Musculoskeletal Dynamic Simulation

Abstract

The AnyBody Modeling System™ (AMS) is a musculoskeletal software simulation solution using inverse dynamics analysis. It enables the determination of muscle and joint forces for a given bodily motion. The recording of the individual movement and the transfer into the AMS is a complex and protracted process. Researches indicated that the contactless, visual Leap Motion Controller (LMC) provides clinically meaningful motion data for hand tracking. Therefore, the aim of this study was to integrate the LMC hand motion data into the AMS in order to improve the process of recording a hand movement. A Python-based interface between the LMC and the AMS, termed ROSE Motion, was developed. This solution records and saves the data of the movement as Biovision Hierarchy (BVH) data and AnyScript vector files that are imported into the AMS simulation. Setting simulation parameters, initiating the calculation automatically, and fetching results is implemented by using the AnyPyTools library from AnyBody. The proposed tool offers a rapid and easy-to-use recording solution for elbow, hand, and finger movements. Features include animation, cutting/editing, exporting the motion, and remote controlling the AMS for the analysis and presentation of musculoskeletal simulation results. Comparing the motion tracking results with previous studies, covering problems when using the LMC limit the correctness of the motion data. However, fast experimental setup and intuitive and rapid motion data editing strengthen the use of marker less systems as the herein presented compared to marker based motion capturing.

Arm Movement Analysis Technology of Wushu Competition Image Based on Deep Learning

“…It can be seen from the definition of progress label that progress label is related to the action category. A network can only learn the progress label information of one kind of action [27]. erefore, it is necessary to train the progress label prediction network belonging to each kind of action k. e training data are the video frame of the action instance belonging to the k-th progressive action in the training video sample.…”

Leap Motion Controller Video Game-Based Therapy for Upper Extremity Motor Recovery in Patients with Central Nervous System Diseases. A Systematic Review with Meta-Analysis

“…Chophuk et al [47] suggested small error angles in fingers using LMC to recognize real finger movement. Recently, Fonk et al [48] reported that the LMC is able to provide a correct estimation of the orientation of the hand bones and joint positions to be reproduced with precision in software with biomechanical applications.…”

Classification of Activities of Daily Living Based on Grasp Dynamics Obtained from a Leap Motion Controller

“…Joint Angle (JA) [ 64 , 65 ]: This feature represents the angle between every two adjacent bones at the interphalangeal and metacarpophalangeal joints. For example, for the distal interphalangeal joint, is derived by Equation ( 6 ).…”