├── Fig
    └── teaser.png
└── README.md


/Fig/teaser.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/LiXin97/Co-Planar-Parametrization/79803d5392cc7474d3d90ef76ba6a27fc4361ce9/Fig/teaser.png


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # Co-Planar Parametrization
 2 | 
 3 | #### OUR VIO BRANCH IS RELEARSE IN https://github.com/LiXin97/Co-Planar-Parametrization-VIO
 4 | 
 5 | Co-Planar Parametrization (CP-Param) provides a  new parametrization for co-planar points and lines, which leverages specific geometric constraints to improve camera pose optimization in terms of both efficiency and accuracy.   Based on the parametrization, we implement a framework for Stereo SLAM and  Visual-Inertial Odometry. 
 6 | 
 7 | ![teaser](Fig/teaser.png)
 8 | 
 9 | We provide examples to run CP-Param in the [EuRoC dataset](http://projects.asl.ethz.ch/datasets/doku.php?id=kmavvisualinertialdatasets) using stereo or VIO. Considering that not every developer has a GPU for plane instance segmentation, we also provide our [segmentation results](https://drive.google.com/drive/folders/1yf_nSMm0lbcTm04J7g2RkAbriEWCNlbq?usp=sharing) of the EuRoc dataset. Please cite it if you use the repo in academic work.
10 | 
11 | ```
12 | @article{Li2020cpparam,
13 |   author = {Li, Xin and Li, Yanyan and \"{O}rnek, Evin Pınar and Lin, Jinlong and Tombari, Federico},
14 |   title = {Co-Planar Parametrization for Stereo-SLAM and Visual-Inertial Odometry},
15 |   journal = {IEEE Robotics and Automation Letters},
16 |   year = {2020},
17 |   publisher={IEEE}
18 |  }
19 | ```
20 | 
21 | # 1. License 
22 | 
23 | CP-Param is released under a [GPLv3 license](https://github.com/raulmur/StructureSLAM/blob/master/License-gpl.txt). For a closed-source version of CP-Param for commercial purposes, please contact me lixin97@pku.edu.cn
24 | 
25 | # 2. Prerequisites
26 | 
27 | We have tested the library in **Ubuntu** **16.04**, but it should be easy to compile in other platforms. A powerful computer (e.g. i7) will ensure real-time performance and provide more stable and accurate results.
28 | 
29 | ## C++11 or C++0x Compiler
30 | 
31 | We use the new thread and chrono functionalities of C++11.
32 | 
33 | ## Pangolin
34 | 
35 | We use [Pangolin](https://github.com/stevenlovegrove/Pangolin) for visualization and user interface. Dowload and install instructions can be found at: https://github.com/stevenlovegrove/Pangolin.
36 | 
37 | ## OpenCV
38 | 
39 | We use [OpenCV](http://opencv.org) to manipulate images and features. Dowload and install instructions can be found at: http://opencv.org. **Required at least 2.4.3. Tested with OpenCV 3.4.0**.
40 | 
41 | ## Eigen3
42 | 
43 | Required by g2o (see below). Download and install instructions can be found at: http://eigen.tuxfamily.org. **Required at least 3.1.0**.
44 | 
45 | ## DBoW2 and g2o (Included in Thirdparty folder)
46 | 
47 | We use modified versions of the [DBoW2](https://github.com/dorian3d/DBoW2) library to perform place recognition and [g2o](https://github.com/RainerKuemmerle/g2o) library to perform non-linear optimizations. Both modified libraries (which are BSD) are included in the *Thirdparty* folder.
48 | 
49 | # 3. Test CP-Param
50 | 
51 | ## Download and build
52 | 
53 | 
54 | ## Run on the EuRoc dataset
55 | 
56 | 
57 | # Acknowledgements
58 | 
59 |  
60 | 
61 | 


--------------------------------------------------------------------------------