ipa-rar / VNect

Real-time 3D human pose estimation, implemented by tensorflow

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

VNect

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.

Environments

  • Python 3.x
  • tensorflow-gpu 1.x
  • pycaffe

Setup

Fedora 29

Install python dependencies:

pip3 install -r requirements.txt --user

Install caffe dependencies

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

Setup Caffe

git clone https://github.com/BVLC/caffe.git
cd caffe

Configure Makefile.config (Include python3 and fix path)

Build 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/

Usage

Preparation

  1. Drop the pretrained caffe model into models/caffe_model.
  2. Run init_weights.py to generate tensorflow model.

Application

  1. run_estimator.py is a script for video stream.
  2. (Recommended) run_estimator_ps.py is a multiprocessing version script. When 3d plotting function shuts down in run_estimator.py mentioned above, you can try this one.
  3. run_pic.py is a script for picture.
  4. (Deprecated) benchmark.py is a class implementation containing all the elements needed to run the model.
  5. (Deprecated) run_estimator_robot.py additionally provides ROS network and/or serial connection for communication in robot controlling.
  6. (Deprecated) The training script train.py is 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:

  1. click left mouse button to initialize the bounding box implemented by a simple HOG method;

  2. trigger any keyboard input to exit while running.

Notes

  1. With some certain programming environments, the 3d plotting function (from matplotlib) in run_estimator.py shuts down. Use run_estimator_ps.py instead.
  2. The input image is in BGR color format and the pixel value is mapped into a range of [-0.4, 0.6).
  3. The joint-parent map (detailed information in materials/joint_index.xlsx):

  1. Here I have a sketch to show the joint positions (don't laugh lol):

  1. Every input image is assumed to contain 21 joints to be found, which means it is easy to fit wrong results when a joint is actually not in the picture.

About Training Data

For MPI-INF-3DHP dataset, refer to my another repository.

Reference Repositories

About

Real-time 3D human pose estimation, implemented by tensorflow

License:Apache License 2.0


Languages

Language:Python 83.0%Language:Jupyter Notebook 17.0%