search

FORTH-ModelBasedTracker / MocapNET

We present MocapNET, 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
https://www.youtube.com/watch?v=Jgz1MRq-I-k
Other
858 stars 137 forks source link

The output bvh file dose not contains t pose and it is hard to use #62

Closed he1016060110 closed 3 years ago

he1016060110 commented 3 years ago

The output bvh file dose not contains t pose at the beginning and it is hard to use.

AmmarkoV commented 3 years ago

Hello!

By adding the commandline argument 

--tpose 

for example 

./MocapNET2LiveWebcamDemo --from /path/to/yourfile.mp4 --tpose

A T-Pose should be prepended to the BVH output..

As seen in the code of the live webcam demo and the CSV Demo and the simple BVH writer code