https://github.com/PRBonn/MapClosures

Effectively Detecting Loop Closures using Point Cloud Density Maps
https://github.com/PRBonn/MapClosures

Last synced: 11 months ago
JSON representation

Effectively Detecting Loop Closures using Point Cloud Density Maps

• Host: GitHub
• URL: https://github.com/PRBonn/MapClosures
• Owner: PRBonn
• License: mit
• Created: 2024-02-28T08:54:26.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2024-04-12T16:32:20.000Z (almost 2 years ago)
• Last Synced: 2024-04-12T16:32:54.903Z (almost 2 years ago)
• Language: Python
• Size: 121 KB
• Stars: 141
• Watchers: 6
• Forks: 7
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE
  • Citation: CITATION.cff
  • Codeowners: .github/CODEOWNERS

Awesome Lists containing this project

README

          


    
MapClosures

    

    

    

    

    

    


    


      •  

    Install

      •  

    ICRA24 Paper

      •  

    Contact Us

  


  


Effectively Detecting Loop Closures using Point Cloud Density Maps.



![image](https://github.com/PRBonn/MapClosures/assets/28734882/18d5ee54-61a9-4d9f-87f2-8aba16de0f75)







## Use MapClosures in your C++ project

1. Include the following snippet in your project's `CMakeLists.txt`:

```cmake

set(USE_SYSTEM_EIGEN3 ON CACHE BOOL "use system eigen3")

set(USE_SYSTEM_OPENCV ON CACHE BOOL "use system opencv")

include(FetchContent)

FetchContent_Declare(

    map_closures

        GIT_REPOSITORY https://github.com/PRBonn/MapClosures.git

        GIT_TAG main

        SOURCE_SUBDIR cpp

)

FetchContent_MakeAvailable(map_closures)

```

You can trigger the automatic installation of the dependencies by playing around with the options in the first three lines of the snippet.

2. Link **MapClosures** against your library or executable:

```cmake

target_link_libraries(my_target PUBLIC map_closures)

```

3. The following _include_ directive in your source code file will provide access to the core API of MapClosures:

```cpp

#include 

```

## Install the Python API and CLI

`pip install map-closures`

### Usage

The following command will provide details about how to use our pipeline:

```sh

map_closure_pipeline --help

```

![CLI_usage](https://github.com/PRBonn/MapClosures/assets/28734882/6dfbd767-ca63-4671-9582-3129752d0244)

Providing the -v flag will initialize the visualizer:

```sh

map_closure_pipeline -v

```

![Visualizer](https://github.com/user-attachments/assets/34aa2b2f-c0ce-4dfb-a0e0-cbcc04487a5a)

## Citation

If you use this library for any academic work, please cite our original [paper](https://www.ipb.uni-bonn.de/pdfs/gupta2024icra.pdf).

```bibtex

@inproceedings{gupta2024icra,

    author     = {S. Gupta and T. Guadagnino and B. Mersch and I. Vizzo and C. Stachniss},

    title      = {{Effectively Detecting Loop Closures using Point Cloud Density Maps}},

    booktitle  = {IEEE International Conference on Robotics and Automation (ICRA)},

    year       = {2024},

    codeurl    = {https://github.com/PRBonn/MapClosures},

}

```

### Paper Results

As we decided to continue the development of **MapClosures** beyond the scope of the ICRA paper, we created a ``git tag`` so that researchers can consistently reproduce the results of the publication. To checkout at this tag, you can run the following:

```sh

git checkout ICRA2024

```

Our development aims to push the performances of **MapClosures** above the original results of the paper.

## Acknowledgement

This repository is heavily inspired by, and also depends on [KISS-ICP](https://github.com/PRBonn/kiss-icp)

## Contributors