Skip to main content

PifPaf: Composite Fields for Human Pose Estimation

Project description

openpifpaf

Build Status

We propose a new bottom-up method for multi-person 2D human pose estimation that is particularly well suited for urban mobility such as self-driving cars and delivery robots. The new method, PifPaf, uses a Part Intensity Field (PIF) to localize body parts and a Part Association Field (PAF) to associate body parts with each other to form full human poses. Our method outperforms previous methods at low resolution and in crowded, cluttered and occluded scenes thanks to (i) our new composite field PAF encoding fine-grained information and (ii) the choice of Laplace loss for regressions which incorporates a notion of uncertainty. Our architecture is based on a fully convolutional, single-shot, box-free design. We perform on par with the existing state-of-the-art bottom-up method on the standard COCO keypoint task and produce state-of-the-art results on a modified COCO keypoint task for the transportation domain.

@article{kreiss2019pifpaf,
  title={PifPaf: Composite Fields for Human Pose Estimation},
  author={Kreiss, Sven and Bertoni, Lorenzo and Alahi, Alexandre},
  journal={CVPR, arXiv preprint arXiv:1903.06593},
  year={2019}
}

arxiv.org/abs/1903.06593

Demo

example image with overlaid pose skeleton

Image credit: "Learning to surf" by fotologic which is licensed under CC-BY-2.0.
Created with: python3 -m openpifpaf.predict --show docs/coco/000000081988.jpg

For more demos, see the openpifpafwebdemo project and the openpifpaf.webcam command. There is also a Google Colab demo.

example image

Install

Python 3 is required. Python 2 is not supported. Do not clone this repository and make sure there is no folder named openpifpaf in your current directory.

pip3 install openpifpaf

For a live demo, we recommend to try the openpifpafwebdemo project. Alternatively, openpifpaf.webcam provides a live demo as well. It requires OpenCV. To use a globally installed OpenCV from inside a virtual environment, create the virtualenv with the --system-site-packages option and verify that you can do import cv2.

For development of the openpifpaf source code itself, you need to clone this repository and then:

pip3 install numpy cython
pip3 install --editable '.[train,test]'

The last command installs the Python package in the current directory (signified by the dot) with the optional dependencies needed for training and testing.

Interfaces

  • python3 -m openpifpaf.predict --help
  • python3 -m openpifpaf.webcam --help
  • python3 -m openpifpaf.train --help
  • python3 -m openpifpaf.eval_coco --help
  • python3 -m openpifpaf.logs --help

Example commands to try:

# live demo
MPLBACKEND=macosx python3 -m openpifpaf.webcam --scale 0.1 --source=0

# single image
python3 -m openpifpaf.predict my_image.jpg --show

Pre-trained Models

Put the files from this Google Drive into your outputs folder. The three standard, pretrained models are also available when using the command line option --checkpoint resnet50, --checkpoint resnet101 and --checkpoint resnet152.

To visualize logs:

python3 -m openpifpaf.logs \
  outputs/resnet50block5-pif-paf-edge401-190424-122009.pkl.log \
  outputs/resnet101block5-pif-paf-edge401-190412-151013.pkl.log \
  outputs/resnet152block5-pif-paf-edge401-190412-121848.pkl.log

Train

See datasets for setup instructions. See studies.ipynb for previous studies.

Train a model:

python3 -m openpifpaf.train \
  --lr=1e-3 \
  --momentum=0.95 \
  --epochs=75 \
  --lr-decay 60 70 \
  --batch-size=8 \
  --basenet=resnet50block5 \
  --head-quad=1 \
  --headnets pif paf \
  --square-edge=401 \
  --regression-loss=laplace \
  --lambdas 30 2 2 50 3 3 \
  --freeze-base=1

You can refine an existing model with the --checkpoint option.

To produce evaluations at every epoch, check the directory for new snapshots every 5 minutes:

while true; do \
  CUDA_VISIBLE_DEVICES=0 find outputs/ -name "resnet101block5-pif-paf-l1-190109-113346.pkl.epoch???" -exec \
    python3 -m openpifpaf.eval_coco --checkpoint {} -n 500 --long-edge=641 --skip-existing \; \
  ; \
  sleep 300; \
done

Person Skeletons

COCO / kinematic tree / dense:

Created with python3 -m openpifpaf.data.

Video

Processing a video frame by frame from video.avi to video.pose.mp4 using ffmpeg:

export VIDEO=video.avi  # change to your video file

mkdir ${VIDEO}.images
ffmpeg -i ${VIDEO} -qscale:v 2 -vf scale=641:-1 -f image2 ${VIDEO}.images/%05d.jpg
python3 -m openpifpaf.predict --checkpoint resnet152 ${VIDEO}.images/*.jpg
ffmpeg -framerate 24 -pattern_type glob -i ${VIDEO}.images/'*.jpg.skeleton.png' -vf scale=640:-1 -c:v libx264 -pix_fmt yuv420p ${VIDEO}.pose.mp4

In this process, ffmpeg scales the video to 641px which can be adjusted.

Documentation Pages

Related Projects

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
openpifpaf-0.8.0.tar.gz (177.3 kB) Copy SHA256 hash SHA256 Source None

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page