Continuously tested on Linux, MacOS and Windows:
CVPR 2019 paper
PifPaf: Composite Fields for Human Pose Estimation
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.
Image credit: "Learning to surf" by fotologic which is licensed under CC-BY-2.0.
Created with:
pip3 install openpifpaf matplotlib
python3 -m openpifpaf.predict coco/000000081988.jpg --image-outputContinue to our OpenPifPaf Guide.
This software is available for licensing via the EPFL Technology Transfer Office (https://tto.epfl.ch/, [email protected]).