hyye / dsl

Implementation of Monocular Direct Sparse Localization in a Prior 3D Surfel Map (DSL)

DSL

Project page: https://sites.google.com/view/dsl-ram-lab/

Monocular Direct Sparse Localization in a Prior 3D Surfel Map

Authors: Haoyang Ye, Huaiyang Huang, and Ming Liu from RAM-LAB.

Paper and Video

Related publications:

@inproceedings{ye2020monocular,
  title={Monocular direct sparse localization in a prior 3d surfel map},
  author={Ye, Haoyang and Huang, Huaiyang and Liu, Ming},
  booktitle={2020 IEEE International Conference on Robotics and Automation (ICRA)},
  pages={8892--8898},
  year={2020},
  organization={IEEE}
}
@inproceedings{ye20213d,
  title={3D Surfel Map-Aided Visual Relocalization with Learned Descriptors},
  author={Ye, Haoyang and Huang, Huaiyang and Hutter, Marco and Sandy, Timothy and Liu, Ming},
  booktitle={2021 International Conference on Robotics and Automation (ICRA)},
  pages={5574-5581},
  year={2021},
  organization={IEEE}
}

Video: https://www.youtube.com/watch?v=LTihCBGcURo

Dependency

1. Pangolin.
2. CUDA.
3. Ceres-solver.
4. PCL, the default version accompanying by ROS.
5. OpenCV, the default version accompanying by ROS.

Build

0. git submodule update --init --recursive
1. mkdir build && cd build
2. cmake .. -DCMAKE_BUILD_TYPE=RelWithDebInfo
3. make -j8

Example

The sample config file can be downloaded from this link.

To run the example:

[path_to_build]/src/dsl_main --path "[path_to_dataset]/left_pinhole"

Preparing Your Own Data

1. Collect LiDAR and camera data.
2. Build LiDAR map and obtain LiDAR poses (the poses are not necessary).
3. Pre-process LiDAR map to make the [path_to_dataset]/*.pcd map file contains normal_x, normal_y, normal_z fields (downsample & normal estimation).
4. Extract and undistort images into [path_to_dataset]/images.
5. Set the first camera pose to initial_pose and other camera parameters in [path_to_dataset]/config.yaml.

Note

This implementation of DSL takes Ceres Solver as backend, which is different from the the implementation of the original paper with DSO-backend. This leads to different performance, i.e., speed and accuracy, compared to the reported results.

Credits

This work is inspired from several open-source projects, such as DSO, DSM, Elastic-Fusion, SuperPoint, DBoW2, NetVlad, LIO-mapping and etc.

Licence

The source code is released under GPL-3.0.

dsl's Issues

The sample config is lost.

Dear Professor:
Thank you for your wonderful work. However, the config file is lost and could you please provide some sample data for us to do some test？
Yours
Qi Wu

Pangolin version

How to build surfel map

Hi,
I'm reading your code these days, it's a brilliant work. And I try to run the code on the KITTI dataset, but I failed. I'm wondering how to build a surfel map from a Lidar PointCloud map? And what value you set about surfel_size when you tested the code on the outside scene?
Thanks !