A lightweight tool for labeling 3D bounding boxes in point clouds.

🆕 We are currently evaluating labelCloud and invite you to fill this questionaire https://forms.gle/moEyjGSa1Eiiq7VT8 (~5 min)!

ℹ️ Currently labelCloud supports Python 3.6 to 3.8; Python 3.9 will be supported as soon as Open3D supports it!

git clone https://github.com/ch-sa/labelCloud.git  # 1. Clone repository
pip install -r requirements.txt  # 2. Install requirements
# 3. Copy point clouds into `pointclouds` folder.
python3 labelCloud.py  # 4. Start labelCloud

Configure the software to your needs by editing the config.ini file or settings according to the docs.

labelCloud supports two different ways of labeling (picking & spanning) as well as multiple mouse and keyboard options for subsequent correction.

(See also https://www.youtube.com/watch?v=8GF9n1WeR8A for a short introduction and preview of the tool.)

Picking Mode

• Pick the location of the bounding box (front-top edge)
• Adjust the z-rotation by scrolling with your mouse wheel

Spanning Mode

• Subsequently span the length, width and height of the bounding box by selecting four vertices
• The layers for for the last two vertices (width & height) will be locked to allow easy selection

Correction

• Use the buttons on the left-hand side or shortcuts to correct the translation, dimension and rotation of the bounding box
• Resize the bounding box by holding your cursor above one side and scrolling with the mouse wheel

By default the x- and y-rotation of bounding boxes will be prohibited. For labeling 9 DoF-Bounding Boxes deactivate z-Rotation Only Mode in the menu, settings or config.ini file. Now you will be free to rotate around all three axes.

labelCloud is built for a versatile use and aims at supporting all common point cloud file formats and label formats for storing 3D bounding boxes. The tool is designed to be easily adaptable to multiple use cases. To change the settings, simply edit the corresponding line in the config.ini (see the documentation for a description of all parameters).

Supported Import Formats

Supported Export Formats

You can easily create your own exporter by implementing the IFormattingInterface. All rotations are counterclockwise (i.e. a z-rotation of 90°/π is from the positive x- to the negative y-axis!).

See documentation.md for software conventions.

When using the tool feel free to drop me a mail with feedback or a description of your use case (christoph.sager[at]tu-dresden.de). If you are using the tool for a scientific project please consider citing our pending publication:

# forthcoming
@article{sager_2021,
  title={labelCloud: A Lightweight Domain-Independent Labeling Tool for 3D Object Detection in Point Clouds},
  journal={Computer-Aided Design and Applications},
  author={Sager, Christoph and Zschech, Patrick and Kühl, Niklas},
  year={2021}}

# published
@misc{sager2021labelcloud,
  title={labelCloud: A Lightweight Domain-Independent Labeling Tool for 3D Object Detection in Point Clouds}, 
  author={Christoph Sager and Patrick Zschech and Niklas Kühl},
  year={2021},
  eprint={2103.04970},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}

I would like to thank the Robotron RCV-Team for the support in the preparation and user evaluation of the software. The software was developed as part of my diploma thesis titled "labelCloud: Development of a Labeling Tool for 3D Object Detection in Point Clouds" at the Chair for Business Informatics, especially Intelligent Systems of the TU Dresden. The ongoing research can be followed in our project on ResearchGate.