Multi-person Human Pose Estimation with HigherHRNet in PyTorch

This is an unofficial implementation of the paper HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation.
The code is a simplified version of the official code with the ease-of-use in mind.

The code is fully compatible with the official pre-trained weights. It supports both Windows and Linux.

This repository currently provides:

• A slightly simpler implementation of HigherHRNet in PyTorch (>=1.0) - compatible with official weights (pose_higher_hrnet_*).
• A simple class (SimpleHigherHRNet) that loads the HigherHRNet network for the bottom-up human pose estimation, loads the pre-trained weights, and make human predictions on a single image or a batch of images.
• Support for multi-GPU inference.
• Multi-person support by design (HigherHRNet is a bottom-up approach).
• A reference code that runs a live demo reading frames from a webcam or a video file.
• NEW Support for TensorRT (thanks to @gpastal24, see #14 and #15).
• NEW A Jupyter Notebook compatible with Google Colab showcasing how to use this repository.
  • Click here to open the notebook on Colab!

This repository is built along the lines of the repository simple-HRNet.
Unfortunately, compared to HRNet, results and performance of HigherHRNet are somewhat disappointing: the network and the required post-processing are slower and the predictions does not look more precise. Moreover, multiple skeletons are often predicted for the same person, requiring additional steps to filter out the redundant poses.
On the other hand, being a bottom-up approach, HigherHRNet does not rely on any person detection algorithm like Yolo-v3 and can be used for person detection too.

Examples

Class usage

import cv2
from SimpleHigherHRNet import SimpleHigherHRNet

model = SimpleHigherHRNet(32, 17, "./weights/pose_higher_hrnet_w32_512.pth")
image = cv2.imread("image.png", cv2.IMREAD_COLOR)

joints = model.predict(image)

The most useful parameters of the __init__ function are:

c	number of channels (HRNet: 32, 48)
nof_joints	number of joints (COCO: 17, CrowdPose: 14)
checkpoint_path	path of the (official) weights to be loaded
resolution	image resolution (min side), it depends on the loaded weights
return_heatmaps	the `predict` method returns also the heatmaps
return_bounding_boxes	the `predict` method returns also the bounding boxes
filter_redundant_poses	redundant poses (poses being almost identical) are filtered out
max_nof_people	maximum number of people in the scene
max_batch_size	maximum batch size used in hrnet inference
device	device (cpu or cuda)

Running the live demo

From a connected camera:

python scripts/live-demo.py --camera_id 0

From a saved video:

python scripts/live-demo.py --filename video.mp4

For help:

python scripts/live-demo.py --help

Extracting keypoints:

From a saved video:

python scripts/extract-keypoints.py --format csv --filename video.mp4

For help:

python scripts/extract-keypoints.py --help

Converting the model to TensorRT:

Warning: require the installation of TensorRT (see Nvidia website) and onnx. On some platforms, they can be installed with

pip install tensorrt onnx

Converting in FP16:

python scripts/export-tensorrt-model.py --device 0 --half

For help:

python scripts/export-tensorrt-model.py --help

Installation instructions

• Clone the repository
  git clone https://github.com/stefanopini/simple-HigherHRNet.git

• Install the required packages
  pip install -r requirements.txt

• Download the official pre-trained weights from https://github.com/HRNet/HigherHRNet-Human-Pose-Estimation

  Direct links, COCO (official Drive folder):

  • w48 640 (more accurate, but slower)
    pose_higher_hrnet_w48_640.pth.tar
  • w32 640 (less accurate, but faster)
    pose_higher_hrnet_w32_640.pth.tar
  • w32 512 (even less accurate, but even faster) - Used as default in live_demo.py
    pose_higher_hrnet_w32_512.pth

  Remember to set the parameters of SimpleHigherHRNet accordingly (in particular c and resolution).

• Your folders should look like:

  simple-HigherHRNet
  ├── gifs                    (preview in README.md)
  ├── misc                    (misc)
  ├── models                  (pytorch models)
  ├── scripts                 (scripts)
  └── weights                 (HigherHRnet weights)
  

ToDos

• Add keypoint extraction script (thanks to @wuyenlin)
• Optimize the post-processing steps
• Add COCO dataset and evaluation
• Add Train/Test scripts
• Add TensorRT support
• Add notebook compatible with Colab