A library for machine learning research on motion capture data

We present MocapNET2, a real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned neural networks that regress the 3D human pose by also allowing for the decomposition of the body to an upper and lower kinematic hierarchy. This permits the recovery of the human pose even in the case of significant occlusions. (c) An efficient Inverse Kinematics solver that refines the neural-network-based solution providing 3D human pose estimations that are consistent with the limb sizes of a target person (if known). All the above yield a 33% accuracy improvement on the Human 3.6 Million (H3.6M) dataset compared to the baseline method (MocapNET) while maintaining real-time performance (70 fps in CPU-only execution).

Parse and visualize asf/amc files from CMU MoCap dataset.

The Machinima Studio mod

(Eyebeam #13 of 13) Output OSC, MIDI, and After Effects/Maya animation scripts from the Leap Motion controller.

(Eyebeam #1 of 13) Developed with @FakeGreenDress. Record, stream, and export Kinect mocap data to After Effects puppet pins. Record directly from the Kinect or over OSC. Compiling or running from source requires SimpleOpenNI.

A motion capture library for Three.js: Playing | Streaming | VR

Library to explore, process, and analyze movement acquisition data

Code for the tutorial on visualizing motion capture data using D3.js

Unreal plugin for real-time streaming from Qualisys Track Manager

A Win32 console application that can receive motion capture data from several sources (e.g., Cortex, File, Kinect), and converts them into a NatNet motion capture data stream.

VIVE Tracker Information Wiki

Repositório dedicado a uma aplicação que auxilia na recuperação de pacientes vítimas de AVC

Information of public available data sets for biomechanics.

FOHEART C1惯性动作捕捉与Unity3D虚拟人物模型互动演示

DeepMoCap Github page:

A visualization engine for human movement data

Passive optical distributed motion capture system

Code to reproduce experiments in 'LSTM-based real-time action detection and prediction in human motion streams'

MotionVenus官方帮助文档，适用于FOHEART X/C1无线动捕套装

(Eyebeam #11 of 13) Puppets driven by OSCeleton-format Kinect skeletons. Receives on port 61863 by default.

Blob track bright objects on a Raspberry Pi, send OSC coordinates or stream video. Based on the work of @jvcleave and @orgicus.

FOHEART C1惯性动作捕捉与Unity3D虚拟人物模型互动演示

Shogun Port of some of my Stage Helpers. But now I'm back in Industry, I can't work on these.

Many helper scripts for shooting & processing MoCap in Vicon Blade. Not getting much work as I'm back in Industry.

Python interface of C3Dserver software for reading and editing C3D motion capture files

Examples of PyC3Dserver module

Drag and drop a single script to visualize any mocap data without a mesh included, and stream the result over OSC.

A real life platformer made with MoCap and GearVR