This python package provides some helper scripts for the RadarScenes dataset.
Among others, the package contains a viewer for the radar data and camera images from the dataset.
The package is designed for Python versions >=3.6 and can be installed using pip. Installation using pip is the
recommended method.
The alternative is to clone this repository and manually install the package using the setup.py.
It is highly recommended to install the package in its own virtual environment. To do so, create a virtual environment prior to installation of the package:
python3 -m venv ~/.virtualenvs/radar_scenes
This will create a python virtual environment called radar_scenes in the folder .virtualenvs in your home directory.
This environment can be activated via
source ~/.virtualenvs/radar_scenes/bin/activate
An active virtual environment is indicated by a preceding (radar_scenes) line before the usual bash prompt.
Once the virtual environment is active, the package can be installed with the command
pip install radar_scenes
You do not have to clone this repository for the installation.
There are multiple guides available which give more information about virtual environments and installation of python packages, e.g. on python.org.
If no virtual environment is desired (again, this is discouraged!) , the package can be installed using the global version of pip
pip3 install --user radar_scenes
The flag --user can be omitted if a system wide installation is desired (may require root privileges).
Please refer to www.radar-scenes.com to get instructions on how to cite the data set.
After successful installation, the radar_scenes package is available in your python environment.
During installation, the command rad_viewer is made available. If you have installed the package into a virtual
environment, this command is only available while the virtual environment is active.
Calling rad_viewer launches the radar data viewer. As an optional command line argument, a path to a *.json file
from the RadarScenes dataset can be provided. The sequence will then be loaded directly on start up.
Example:
(radar_scenes)
$ rad_viewer ~/datasets/radar_scenes/data/sequence_128/scenes.json
The time slider itself or the arrow keys on your keyboard can be used to scroll through the sequence.
This project is licensed under the terms of the MIT license.
Notice, however, that the RadarScenes data set itself comes with a different license.