Real-time 3D human pose estimation, implemented by tensorflow
A tensorflow implementation of VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera.
For the caffe model/weights required in the repository: please contact the author of the paper.
pip3 install -r requirements.txt --user
sudo dnf install protobuf-devel leveldb-devel snappy-devel opencv-devel boost-devel hdf5-devel glog-devel gflags-devel lmdb-devel atlas-devel python-lxml boost-python3-devel
git clone https://github.com/BVLC/caffe.git cd caffe
sudo make all sudo make runtest sudo make pycaffe sudo make distribute sudo cp .build_release/lib/ /usr/lib64 sudo cp -a distribute/python/caffe/ /usr/lib/python3.7/site-packages/
init_weights.pyto generate tensorflow model.
run_estimator.pyis a script for video stream.
run_estimator_ps.pyis a multiprocessing version script. When 3d plotting function shuts down in
run_estimator.pymentioned above, you can try this one.
run_pic.pyis a script for picture.
benchmark.pyis a class implementation containing all the elements needed to run the model.
run_estimator_robot.pyadditionally provides ROS network and/or serial connection for communication in robot controlling.
train.pyis not complete yet (I failed to reconstruct the model: ( So do not use it. Also pulling requests are welcomed.
[Tips] To run the scripts for video stream:
click left mouse button to initialize the bounding box implemented by a simple HOG method;
trigger any keyboard input to exit while running.
run_estimator.pyshuts down. Use
For MPI-INF-3DHP dataset, refer to my another repository.