https://github.com/izhengfan/se2clam

SE(2)-Constrained Localization and Mapping by Fusing Odometry and Vision (IEEE Transactions on Cybernetics 2019)
https://github.com/izhengfan/se2clam

g2o graph-optimization robotics ros slam state-estimation visual-slam

Last synced: 2 months ago
JSON representation

SE(2)-Constrained Localization and Mapping by Fusing Odometry and Vision (IEEE Transactions on Cybernetics 2019)

• Host: GitHub
• URL: https://github.com/izhengfan/se2clam
• Owner: izhengfan
• License: mit
• Created: 2019-03-04T07:55:28.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2020-05-10T02:26:28.000Z (over 4 years ago)
• Last Synced: 2024-08-02T07:06:57.911Z (5 months ago)
• Topics: g2o, graph-optimization, robotics, ros, slam, state-estimation, visual-slam
• Language: C++
• Homepage: https://github.com/izhengfan/se2clam
• Size: 137 KB
• Stars: 161
• Watchers: 9
• Forks: 55
• Open Issues: 3
• Metadata Files:
  • Readme: README.MD
  • License: LICENSE

Awesome Lists containing this project

• Awesome-SLAM - se2clam - Constrained Localization and Mapping by Fusing Odometry and Vision (2. Visual SLAM / 2.5 Others)

README

        
se2clam

---

SE(2)-Constrained Localization and Mapping by Fusing Odometry and Vision

[![](../../workflows/Build/badge.svg)](../../actions?query=workflow%3A"Build")

### Related Publication

- Fan Zheng, Hengbo Tang, Yun-Hui Liu. "Odometry-Vision-Based Ground Vehicle Motion Estimation With SE(2)-Constrained SE(3) Poses". _IEEE Transactions on Cybernetics_, vol. 49, no. 7, 2019

  To cite it in bib:

  ```

  @article{fzheng2018tcyb,

    author  = {Fan Zheng and Hengbo Tang and Yun-Hui Liu},

    journal = {IEEE Trans. Cybernetics},

    title   = "{Odometry-Vision-Based Ground Vehicle Motion Estimation With SE(2)-Constrained SE(3) Poses}",

    volume  = {49},

    number  = {7},

    year    = {2019},

  }

  ```

### Dependencies

- ROS (tested on Kinetic/Melodic)

- OpenCV 2.4.x / 3.1 above

- g2o ([2016 version](https://github.com/RainerKuemmerle/g2o/releases/tag/20160424_git))

### Build

Build this project as a ROS package

### Demo

1. Download [DatasetRoom.zip](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155051778_link_cuhk_edu_hk/Ef4NuXvLZI1JhfljH9LkNxUB5xrDrCOrRnxwztO5bGKlew?e=U4aind), and extract it. In a terminal, `cd` into `DatasetRoom/`.

   We prepare two packages of odometry measurement data, one is more accurate (`odo_raw_accu.txt`), the other less accurate (`odo_raw_roug.txt`). To use either one of them, copy it to `odo_raw.txt` in `DatasetRoom/`.

2. Download [ORBvoc.bin](https://mycuhk-my.sharepoint.com/:u:/g/personal/1155051778_link_cuhk_edu_hk/EaF2ZkP17rdJrUHT0mrcf74Bl1h_691xZrxNILGbQbYFmA?e=nXRSS4).

3. Run rviz:

   ```

   roscd se2clam

   rosrun rviz rviz -d rviz.rviz

   ```

4. Run se2clam:

   

   ```

   rosrun se2clam test_vn PATH_TO_DatasetRoom PATH_TO_ORBvoc.bin

   ```

   ![result in rviz](https://images.gitee.com/uploads/images/2019/0304/231649_cdb48a5e_874043.png)

   

   

### Related Project

[izhengfan/se2lam](https://github.com/izhengfan/se2lam)  

[izhengfan/ORB_SLAM2](https://github.com/izhengfan/ORB_SLAM2)

### License 

[MIT](LICENSE)