Human Pose Detection on Brainy Pi

Installing OpenVINO

Before we dive into the demo, let’s start by installing OpenVINO and its dependencies on BrainyPi. Follow these simple steps:

1. Open a terminal on your BrainyPi device and enter the following command to install OpenVINO and the necessary OpenCV development files:

   sudo apt install openvino-toolkit libopencv-dev

   This command will ensure that OpenVINO is installed and ready to use.

Compiling Demos

Now that OpenVINO is installed, we can proceed to compile the demos. These demos serve as valuable resources for understanding and exploring the capabilities of OpenVINO. Here’s how you can compile the demos:

1. Set up the OpenVINO environment by sourcing the setupvars.sh script:

   source /opt/openvino/setupvars.sh

2. Clone the Open Model Zoo repository, which contains the demos, using the following command:

   git clone --recurse-submodules https://github.com/openvinotoolkit/open_model_zoo.git
   cd open_model_zoo/demos/

3. Build the demos by executing the build_demos.sh script:

   ./build_demos.sh

   This will compile the demo applications and make them ready for execution.

Running the Demos

With the demos compiled, we can now download the required models and run the human pose detection demo. Follow these steps:

1. Download the models needed for the demo by running the following command:

   omz_downloader --list ~/open_model_zoo/demos/human_pose_estimation_demo/cpp/models.lst -o ~/models/ --precision FP16

   This command will download the necessary models for the demo and save them in the ~/models/ directory.

2. Download the test video that will be used for the demo:

   cd ~/
   wget https://raw.githubusercontent.com/intel-iot-devkit/sample-videos/master/face-demographics-walking.mp4

   This command will download a sample video called face-demographics-walking.mp4.

3. Once the models and the test video are downloaded, you can run the demo using the following command:

   ~/omz_demos_build/aarch64/Release/human_pose_estimation_demo -i ~/face-demographics-walking.mp4 -m ~/models/intel/human-pose-estimation-0001/FP16/human-pose-estimation-0001.xml -at openpose

   This command will execute the human pose estimation demo using OpenVINO on the test video.

Conclusion

Congratulations! You have successfully installed OpenVINO, compiled the demos, and run the human pose detection demo on BrainyPi. This demo showcases the power of AI and computer vision in predicting human poses, providing a solid foundation for developers and entrepreneurs to build their own computer vision products.

To delve deeper into the human pose detection demo and explore additional features and options, refer to the OpenVINO documentation.

Get creative and leverage the potential of OpenVINO to unlock a world of possibilities in computer vision applications. Happy coding!

Note: The content of this blog is based on OpenVINO 2023.0 documentation and may be subject to updates in future releases.