TrackTech: Real-time tracking of subjects and objects on multiple cameras

This project is part of the 2021 spring bachelor final project of the Bachelor of Computer Science at Utrecht University. The team that worked on the project consists of eleven students from the Bachelor of Computer Science and Bachelor of Game Technology. This project has been done for educational purposes. All code is open-source, and proper credit is given to respective parties.

GPU support

Updating/Installing drivers

Update the GPU drivers and restart the system for changes to take effect. Optionally, use a different driver listed after running ubuntu-drivers devices

sudo apt install nvidia-driver-460
sudo reboot

Installing the container toolkit

Add the distribution, update the package manager, install NVIDIA for Docker, and restart Docker for changes to take effect. For more information, look at the install guide

distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \
   && curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add - \
   && curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list
sudo apt update
sudo apt install -y nvidia-docker2
sudo systemctl restart docker

Acquire the GPU ID

According to this read the GPU UUID like GPU-a1b2c3d (just the first part) from

nvidia-smi -a

Add the resource

Add the GPU UUID from the last step to the Docker engine configuration file typically at /etc/docker/daemon.json. Create the file if it does not exist yet.

{
  "runtimes": {
    "nvidia": {
      "path": "/usr/bin/nvidia-container-runtime",
      "runtimeArgs": []
    }
  },
  "default-runtime": "nvidia",
  "node-generic-resources": ["gpu=GPU-a1b2c3d"]
}

Pylint

We use Pylint for python code quality assurance.

Installation

Input following command terminal:

pip install pylint

Run

To run linting on the entire repository, run the following command from the root: pylint CameraProcessor docs Interface ProcessorOrchestrator utility VideoForwarder --rcfile=.pylintrc --reports=n

Explanation

pylint <Subsystem> --rcfile=.pylintrc --reports=n

<Subsystem> is the Python module to run.

--rcfile is the linting specification used by Pylint.

--reports sets whether the full report should be displayed or not. Our recommendation would be n since this only displays linting errors/warnings and the eventual score.

Constraints

Pylint needs an __init__.py file in the subsystem root to parse all folders to lint. This run must be a subsystem since the root does not contain an __init__.py file.

Ignoring folders from linting

Some folders should be excluded from linting. The exclusion could be for multiple reasons like, the symlinked algorithms in the CameraProcessor folder or the Python virtual environment folder. Add folder name to ignore= in .pylintrc.