OUR VIO BRANCH IS RELEARSE IN https://github.com/LiXin97/Co-Planar-Parametrization-VIO
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.
We provide examples to run CP-Param in the EuRoC dataset using stereo or VIO. Considering that not every developer has a GPU for plane instance segmentation, we also provide our segmentation results of the EuRoc dataset. Please cite it if you use the repo in academic work.
@article{Li2020cpparam,
author = {Li, Xin and Li, Yanyan and \"{O}rnek, Evin Pınar and Lin, Jinlong and Tombari, Federico},
title = {Co-Planar Parametrization for Stereo-SLAM and Visual-Inertial Odometry},
journal = {IEEE Robotics and Automation Letters},
year = {2020},
publisher={IEEE}
}
CP-Param is released under a GPLv3 license. For a closed-source version of CP-Param for commercial purposes, please contact me lixin97@pku.edu.cn
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.
We use the new thread and chrono functionalities of C++11.
We use Pangolin for visualization and user interface. Dowload and install instructions can be found at: https://github.com/stevenlovegrove/Pangolin.
We use OpenCV 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.
Required by g2o (see below). Download and install instructions can be found at: http://eigen.tuxfamily.org. Required at least 3.1.0.
We use modified versions of the DBoW2 library to perform place recognition and g2o library to perform non-linear optimizations. Both modified libraries (which are BSD) are included in the Thirdparty folder.