https://github.com/natlee/openpose-detect-hands-with-heatmap

This is a simply application for using OpenPose model for detecting hands and showing the visualization with a heatmap.
https://github.com/natlee/openpose-detect-hands-with-heatmap

deep-learning hand-detection hand-tracking heatmap opencv openpose visualization

Last synced: about 1 month ago
JSON representation

This is a simply application for using OpenPose model for detecting hands and showing the visualization with a heatmap.

• Host: GitHub
• URL: https://github.com/natlee/openpose-detect-hands-with-heatmap
• Owner: NatLee
• License: afl-3.0
• Created: 2023-05-10T05:35:19.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2023-05-30T06:12:31.000Z (about 3 years ago)
• Last Synced: 2025-03-15T05:24:55.491Z (over 1 year ago)
• Topics: deep-learning, hand-detection, hand-tracking, heatmap, opencv, openpose, visualization
• Language: Python
• Homepage:
• Size: 2.18 MB
• Stars: 3
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          


# **OpenPose Detect Hands with Heatmap**



  

  

  





> Source from [요룰레히 9_21- HEYYEYAAEYAAAEYAEYAA (What's Up)](https://www.youtube.com/watch?v=u6w9HYmQMgQ)

This is a simply application for using OpenPose model for detecting hands and showing the heatmap.

## Model

You can get the pre-trained model from Hugging Face.

Download it into `./model`.

https://huggingface.co/NatLee/openpose-keras-model

```bash

git clone --depth=1 git@hf.co:NatLee/openpose-keras-model ./model/

```

```

model

└── weights.h5

```

## Usage

> Tested on x86/64 CPU, Intel 12th-i5 with 16 GB RAM.

1. Prepare the model from [#Model](#model).

2. Prepare your video in `./data` named `test.mp4`.

    The directory will like below:

    ```

    .

    ├── data

    │   ├── README.md

    │   └── test.mp4 <--- Your video

    ├── doc

    │   ├── heatmap-motion.gif

    │   ├── heatmap.png

    │   └── original-frame.png

    ├── docker-compose.yml

    ├── Dockerfile

    ├── LICENSE

    ├── model

    │   └── weights.h5 <--- The model

    ├── README.md

    ├── requirements.txt

    └── src

        ├── convert-png-to-gif.py

        ├── docker-entrypoint.sh

        ├── main.py

        ├── openpose

        │   ├── __init__.py

        │   ├── model.py

        │   ├── OpenposeModel.py

        │   ├── prediction.py

        │   └── util.py

        └── utils

            ├── draw_heat.py

            ├── FPS.py

            ├── heatmapper

            │   ├── assets

            │   │   ├── 450pxdot.png

            │   │   ├── default.png

            │   │   └── reveal.png

            │   ├── heatmapper.py

            │   └── __init__.py

            ├── __init__.py

            └── ROIs.py

    8 directories, 28 files

    ```

3. Just run docker command with the following:

    ```bash

    docker-compose build && docker-compose up

    ```

    The result will be generated in the folder `./tmp`.

## Contributor

  

    

      
Nat Lee

    

  

## Reference

- Heatmap package is from [HeatMappy](https://github.com/LumenResearch/heatmappy/tree/master/heatmappy).

- The version of keras with Open Pose model is from [Open-Pose-Keras](https://github.com/cchamber/Open-Pose-Keras).

## LICENSE

[AFLv3](LICENSE)