Git Product home page Git Product logo

ndtmc's Introduction

NDT-Map-Code

NDT-Map-Code: A 3D global descriptor for real-time loop closure detection in lidar SLAM

You can find the paper here NDT-Map-Code.

Example

  • We implemented the SLAM package of NDTMC and LIOSAM integration, which can be found at NDTMC-LIO-SAM.

  • We tested our descriptor on KITTI sequences 00, 02, 05, 06, 07 and 08:

image

image

  • F1 score and extended precision results on the KITTI dataset:

image

How to use

  1. Create GT of LCD

    Use script/create_ground_truth.py to generate the LCD GT value, you need to modify the two file paths in the script/create_ground_truth.py (odometry ground truth file path, LCD GT value result path).

  2. Save descriptors

    Modify the main function in run_demo.cpp as follow:

    int main(int argc, char **argv)
    {
        saveDesc(argv);
        // matchForKitti(argv);
        // matchForNIO(argv);
        return 0;
    }
    
    

    Build and run script/auto_test.py to generate descriptors, where input_folder and output_folder need to be modified to the voledyne folder path of the currently processed sequence and the folder path where you want to save the descriptor results, respectively.

  3. Descriptors matching

    Modify the main function in run_demo.cpp as follow:

    int main(int argc, char **argv)
    {
        // saveDesc(argv);
        matchForKitti(argv);
        // matchForNIO(argv);
        return 0;
    }
    
    

    Build and run script/auto_match.py to perform descriptor matching, where input_folder and output_txt need to be modified to the folder path where the descriptor was saved in the previous step and the txt file path where you want to save the matching result, respectively.

At this point, you can get the matching result of each frame, and you can process it yourself to get more result information, such as: precision-recall curve, F1 Score and Extended Precision.

Cite NDTMC

@misc{liao2023ndtmapcode,
      title={NDT-Map-Code: A 3D global descriptor for real-time loop closure detection in lidar SLAM}, 
      author={Lizhou Liao and Li Sun and Xinhui Bai and Zhenxing You and Hongyuan Yuan and Chunyun Fu},
      year={2023},
      eprint={2307.08221},
      archivePrefix={arXiv},
      primaryClass={cs.RO}
}

Contact

Contributors

  • Lizhou Liao: completed the code

Acknowledgement

  • Thanks for NIO low-speed localization and mapping group.

ndtmc's People

Contributors

slamcabbage avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.