tf-pose-estimation-3d

This repo added Z output from the Tensorflow version of 'Openpose' human pose estimation using Convolutional 3D Pose Estimation from a Single Image. The code for the 3D Pose Estimation was taken from Lifting from the Deep by Denis Tome', Chris Russell, Lourdes Agapito.

Original Repo of Lifting from the Deep :

For details, see README in the lifting code.

Installation

It is recommended to perform the installation under a Python3 Virtual Environment. To do so, run:

python3 -m venv tf-pose-venv
. tf-pose-venv/bin/activate

Mac OSX

To use tf-post-estimation-3d on the Mac OSX, you will need to install swig, to do so, run:

brew install swig

There is no installation necessary for using the Lifting from the Deep except to download the models. To do so, following the installation instructions of tf-pose-estimation below. When finished, run setup.sh:

bash setup.sh

Docker

Unfortunately, docker is not yet implemented with this feature.

tf-pose-estimation

'Openpose', human pose estimation algorithm, have been implemented using Tensorflow. It also provides several variants that have some changes to the network structure for real-time processing on the CPU or low-power embedded devices.

You can even run this on your macbook with a descent FPS!

Original Repo(Caffe) : https://github.com/CMU-Perceptual-Computing-Lab/openpose

CMU's Original Model on Macbook Pro 15"	Mobilenet-thin on Macbook Pro 15"	Mobilenet-thin on Jetson TX2
~0.6 FPS	~4.2 FPS @ 368x368	~10 FPS @ 368x368
2.8GHz Quad-core i7	2.8GHz Quad-core i7	Jetson TX2 Embedded Board

Implemented features are listed here : features

Important Updates

• 2019.3.12 Add new models using mobilenet-v2 architecture. See : experiments.md
• 2018.5.21 Post-processing part is implemented in c++. It is required compiling the part. See: https://github.com/ildoonet/tf-pose-estimation/tree/master/src/pafprocess
• 2018.2.7 Arguments in run.py script changed. Support dynamic input size.

Install

Dependencies

You need dependencies below.

• python3
• tensorflow 1.4.1+
• opencv3, protobuf, python3-tk
• slidingwindow
  • https://github.com/adamrehn/slidingwindow
  • I copied from the above git repo to modify few things.

Install

Clone the repo and install 3rd-party libraries.

$ git clone https://www.github.com/ildoonet/tf-pose-estimation
$ cd tf-pose-estimation
$ pip3 install -r requirements.txt

Build c++ library for post processing. See : https://github.com/ildoonet/tf-pose-estimation/tree/master/tf_pose/pafprocess

$ cd tf_pose/pafprocess
$ swig -python -c++ pafprocess.i && python3 setup.py build_ext --inplace

Package Install

Alternatively, you can install this repo as a shared package using pip.

$ git clone https://www.github.com/ildoonet/tf-pose-estimation
$ cd tf-openpose
$ python setup.py install  # Or, `pip install -e .`

Models & Performances

See experiments.md

Download Tensorflow Graph File(pb file)

Before running demo, you should download graph files. You can deploy this graph on your mobile or other platforms.

• cmu (trained in 656x368)
• mobilenet_thin (trained in 432x368)
• mobilenet_v2_large (trained in 432x368)
• mobilenet_v2_small (trained in 432x368)

CMU's model graphs are too large for git, so I uploaded them on an external cloud. You should download them if you want to use cmu's original model. Download scripts are provided in the model folder.

$ cd models/graph/cmu
$ bash download.sh

Demo

Test Inference

You can test the inference feature with a single image.

$ python run.py --model=mobilenet_thin --resize=432x368 --image=./images/p1.jpg

The image flag MUST be relative to the src folder with no "~", i.e:

--image ../../Desktop

Then you will see the screen as below with pafmap, heatmap, result and etc.

Realtime Webcam

$ python run_webcam.py --model=mobilenet_thin --resize=432x368 --camera=0

Then you will see the realtime webcam screen with estimated poses as below. This Realtime Result was recored on macbook pro 13" with 3.1Ghz Dual-Core CPU.

Python Usage

This pose estimator provides simple python classes that you can use in your applications.

See run.py or run_webcam.py as references.

e = TfPoseEstimator(get_graph_path(args.model), target_size=(w, h))
humans = e.inference(image)
image = TfPoseEstimator.draw_humans(image, humans, imgcopy=False)

If you installed it as a package,

import tf_pose
coco_style = tf_pose.infer(image_path)

ROS Support

See : etcs/ros.md

Training

See : etcs/training.md

References

See : etcs/reference.md