Skip to content

rob-med-usp/hydrapose

Repository files navigation

Real Time 3D Human Pose Estimation in Operating Rooms

Description

Two models implemented

  • Pose 2D

    • Keypoint RCNN
    • OpenPose
  • Pose 3D

    • SeffPose

Installation

  1. Clone this repository

  2. Install pytorch for your machine using the link:

https://pytorch.org/get-started/locally/

  1. Install OpenCV, Matplotlib, Numpy and Pillow.
pip install opencv-contrib-python matplotlib numpy Pillow
  1. Download pre-trained model from this link. (Do not uncompress. Let the model with .tar end)

https://drive.google.com/file/d/1CSpx5hGD18y8Wp_RysoxUhIPvgYuzl9c/view?usp=sharing

  1. Download necessary data from this link. (Do not uncompress. Let the model with .tar end)

https://drive.google.com/file/d/1Q8YnEPMnIXYy7shK-JSCRs3AGnDa9efq/view?usp=sharing

  1. Move the pre-trained model and the necessary data to the models/seffpose/ folder.

Usage

For image:

python rcnn_seffpose_image.py

For video:

python rcnn_seffpose_video.py

For webcam:

python rcnn_seffpose_webcam.py

Contributing

Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.

Please make sure to update tests as appropriate.

License

MIT

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published