Building Volumetric Beliefs for Dynamic Environments Exploiting Map-Based Moving Object Segmentation

Our approach identifies moving objects in the current scan (blue points) and the local map (black points) of the environment and maintains a volumetric belief map representing the dynamic environment.

Click here for qualitative results!

[](https://github.com/PRBonn/MapMOS/assets/38326482/04c7e5a2-dd44-431a-95b0-c42d5605078a) Our predictions for the KITTI Tracking sequence 19 with true positives (green), false positives (red), and false negatives (blue).

Installation

First, make sure the MinkowskiEngine is installed on your system, see here for more details.

Next, clone our repository bash git clone git@github.com:PRBonn/MapMOS && cd MapMOS

and install with bash make install

or bash make install-all if you want to install the project with all optional dependencies (needed for the visualizer). In case you want to edit the Python code, install in editable mode: bash make editable

How to Use It

Just type

bash mapmos_pipeline --help to see how to run MapMOS.

Check the Download section for a pre-trained model. Like KISS-ICP, our pipeline runs on a variety of point cloud data formats like bin, pcd, ply, xyz, rosbags, and more. To visualize these, just type

bash mapmos_pipeline --visualize /path/to/weights.ckpt /path/to/data

Training

To train our approach, you need to first cache your data. To see how to do that, just cd into the MapMOS repository and type

bash python3 scripts/precache.py --help

After this, you can run the training script. Again, --help shows you how: bash python3 scripts/train.py --help

HeLiMOS

We provide additional training and evaluation data for different sensor types in our HeLiMOS paper. To train on the HeLiMOS data, use the following commands:

shell python3 scripts/precache.py /path/to/HeLiMOS helimos /path/to/cache --config config/helimos/*_training.yaml python3 scripts/train.py /path/to/HeLiMOS helimos /path/to/cache --config config/helimos/*_training.yaml

by replacing the paths and the config file names. To evaluate for example on the Velodyne test data, run

shell mapmos_pipeline /path/to/weights.ckpt /path/to/HeLiMOS --dataloader helimos -s Velodyne/test.txt

Note that our sequence -s encodes both the sensor type Velodyne and split test.txt, just replace these with Ouster, Aeva, or Avia and/or train.txt or val.txt to run MapMOS on different sensors and/or splits.

Downloads

You can download the post-processed and labeled Apollo dataset and KITTI Tracking sequence 19 from our website.

The weights of our pre-trained model can be downloaded as well.

Publication

If you use our code in your academic work, please cite the corresponding paper:

bibtex @article{mersch2023ral, author = {B. Mersch and T. Guadagnino and X. Chen and I. Vizzo and J. Behley and C. Stachniss}, title = {{Building Volumetric Beliefs for Dynamic Environments Exploiting Map-Based Moving Object Segmentation}}, journal = {IEEE Robotics and Automation Letters (RA-L)}, volume = {8}, number = {8}, pages = {5180--5187}, year = {2023}, issn = {2377-3766}, doi = {10.1109/LRA.2023.3292583}, codeurl = {https://github.com/PRBonn/MapMOS}, }

Acknowledgments

This implementation is heavily inspired by KISS-ICP.

License

This project is free software made available under the MIT License. For details see the LICENSE file.