Pose Estimation on the Edge

    Pose Estimation on the Edge


    Pose estimation is a computer vision technique that estimates the human body pose by localizing the main joints, such as elbows, knees, and ankles, known as the key points. There are plenty of pose estimation applications that are especially useful on mobile and embedded devices, including exercise pose correction.

    In this work, we optimized a pose estimation model to deploy it on Jetson edge devices. The pose estimation model can work well on real-world CCTV data compared to the existing models.

    We have open-sourced our code, models, and Neuralet’s pose estimation Dockerfiles to enable users to run pose estimation on Jetson platforms conveniently.

    How it works

    We have used the open-source OpenPifPaf pose estimator model for this application. We exported the PyTorch OpenPifPaf model to ONNX format and used the exported model to generate a TensorRT inference engine deployable on Jetson platforms.

    Since the OpenPifPaf model is designed for the transportation domain in crowded areas, it works well even on real-world CCTV videos where the human bodies only occupy a small portion of the video frame.

    This is the first time that an OpenPifPaf model, which is a complex and heavy model, is deployed on Jetson devices. We faced many challenges along the way; we will share these challenges and the solution to each one with the community in our future blog posts.

    Supported devices

    We currently support the following device for this application:

    Support for other platforms is coming soon.

    Explore more

    You can read this blog post for instructions on running pose estimation on your Jetson device. The source code and the model are available on our GitHub repo.

    Get In Touch

    Have a question? Send us a message and we will respond as soon as possible.