A gesture recognition system powered by OpenPose, k-nearest neighbours, and local outlier factor.

Last update: Jan 10, 2022

Overview

OpenHands

OpenHands is a gesture recognition system powered by OpenPose, k-nearest neighbours, and local outlier factor. Currently the system can identify thumbs up, peace, palm, and out of distribution hand gestures of right hands.

🎬 Video demo

Watch a demo of OpenHands being used in the camera web app Jester (app code in /examples directory).

📝 Documentation

🚕 Roadmap

Short term

Record more accuracy and performance metrics.
~~Implement github actions testing pipeline.~~
Improve documentation.

Longer term

Improve performance
1. KNN approximations.
2. Keypoint dimension reduction.
3. Implement classifier in C.
Left hand gesture support.
SDK for adding custom gestures.

📋 Contributing

I'm not currently looking for contributors, but feedback is always welcome!

⚖️ License

OpenHands uses the GPLv3 license. This means you are free to make copies, modify, and distributed OpenHands, just make the source code available. Full details of the GPLv3 license can be found here.

✏️ Author

Paul Treanor

Email: [email protected]
Github: @paultreanor

👏 Acknowledgements

Thanks to Colin Gorman for help with the dataset collection, dataset processing, and system testing.
Credit to Róise McGagh for the fantastic artwork!

A gesture recognition system powered by OpenPose, k-nearest neighbours, and local outlier factor.

Related tags

Overview

OpenHands

🎬 Video demo

📝 Documentation

🚕 Roadmap

Short term

Longer term

📋 Contributing

⚖️ License

✏️ Author

👏 Acknowledgements

Owner

Paul Treanor

Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

Parameterized Explainer for Graph Neural Network

Differentiable rasterization applied to 3D model simplification tasks

Self-Regulated Learning for Egocentric Video Activity Anticipation

中文语音识别系列，读者可以借助它快速训练属于自己的中文语音识别模型，或直接使用预训练模型测试效果。

Build a small, 3 domain internet using Github pages and Wikipedia and construct a crawler to crawl, render, and index.

SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

This is the repository for paper NEEDLE: Towards Non-invertible Backdoor Attack to Deep Learning Models.

Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera.

Implementation of MA-Trace - a general-purpose multi-agent RL algorithm for cooperative environments.

Super Resolution for images using deep learning.

《LXMERT: Learning Cross-Modality Encoder Representations from Transformers》(EMNLP 2020)

Official PyTorch implementation of DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection? (ICCV 2021), Dennis Park, Rares Ambrus, Vitor Guizilini, Jie Li, and Adrien Gaidon.

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Anomaly detection analysis and labeling tool, specifically for multiple time series (one time series per category)

Answering Open-Domain Questions of Varying Reasoning Steps from Text

A sequence of Jupyter notebooks featuring the 12 Steps to Navier-Stokes

Single Image Deraining Using Bilateral Recurrent Network (TIP 2020)

Using python and scikit-learn to make stock predictions

A gesture recognition system powered by OpenPose, k-nearest neighbours, and local outlier factor.

Related tags

Overview

OpenHands

🎬 Video demo

📝 Documentation

🚕 Roadmap

Short term

Longer term

📋 Contributing

⚖️ License

✏️ Author

👏 Acknowledgements

Owner

Paul Treanor

Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning

DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.

Parameterized Explainer for Graph Neural Network

Differentiable rasterization applied to 3D model simplification tasks

Self-Regulated Learning for Egocentric Video Activity Anticipation

中文语音识别系列，读者可以借助它快速训练属于自己的中文语音识别模型，或直接使用预训练模型测试效果。

Build a small, 3 domain internet using Github pages and Wikipedia and construct a crawler to crawl, render, and index.

SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

This is the repository for paper NEEDLE: Towards Non-invertible Backdoor Attack to Deep Learning Models.

Tools to create pixel-wise object masks, bounding box labels (2D and 3D) and 3D object model (PLY triangle mesh) for object sequences filmed with an RGB-D camera.

Implementation of MA-Trace - a general-purpose multi-agent RL algorithm for cooperative environments.

Super Resolution for images using deep learning.

《LXMERT: Learning Cross-Modality Encoder Representations from Transformers》(EMNLP 2020)

Official PyTorch implementation of DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection? (ICCV 2021), Dennis Park*, Rares Ambrus*, Vitor Guizilini, Jie Li, and Adrien Gaidon.

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Anomaly detection analysis and labeling tool, specifically for multiple time series (one time series per category)

Answering Open-Domain Questions of Varying Reasoning Steps from Text

A sequence of Jupyter notebooks featuring the 12 Steps to Navier-Stokes

Single Image Deraining Using Bilateral Recurrent Network (TIP 2020)

Using python and scikit-learn to make stock predictions

Official PyTorch implementation of DD3D: Is Pseudo-Lidar needed for Monocular 3D Object detection? (ICCV 2021), Dennis Park, Rares Ambrus, Vitor Guizilini, Jie Li, and Adrien Gaidon.