Authors: Chanwoo Lee
Note This is my personal project. SuperPoint-SLAM is a project to analyze the slightly modified ORB-SLAM by replacing ORB feature extractor with SuperPoint feature extractor.
ORB-SLAM's license is as below
ORB-SLAM2 Authors Raul Mur-Artal, Juan D. Tardos, J. M. M. Montiel and Dorian Galvez-Lopez (DBoW2)
ORB-SLAM2 is a real-time SLAM library for Monocular, Stereo and RGB-D cameras that computes the camera trajectory and a sparse 3D reconstruction (in the stereo and RGB-D case with true scale). It is able to detect loops and relocalize the camera in real time. We provide examples to run the SLAM system in the KITTI dataset as stereo or monocular, in the TUM dataset as RGB-D or monocular, and in the EuRoC dataset as stereo or monocular. We also provide a ROS node to process live monocular, stereo or RGB-D streams. The library can be compiled without ROS. ORB-SLAM2 provides a GUI to change between a SLAM Mode and Localization Mode, see section 9 of this document.
ORB-SLAM2 is released under a GPLv3 license. For a list of all code/library dependencies (and associated licenses), please see Dependencies.md.
For a closed-source version of ORB-SLAM2 for commercial purposes, please contact the authors: orbslam (at) unizar (dot) es.
If you use ORB-SLAM2 (Monocular) in an academic work, please cite:
@article{murTRO2015,
title={{ORB-SLAM}: a Versatile and Accurate Monocular {SLAM} System},
author={Mur-Artal, Ra\'ul, Montiel, J. M. M. and Tard\'os, Juan D.},
journal={IEEE Transactions on Robotics},
volume={31},
number={5},
pages={1147--1163},
doi = {10.1109/TRO.2015.2463671},
year={2015}
}
if you use ORB-SLAM2 (Stereo or RGB-D) in an academic work, please cite:
@article{murORB2,
title={{ORB-SLAM2}: an Open-Source {SLAM} System for Monocular, Stereo and {RGB-D} Cameras},
author={Mur-Artal, Ra\'ul and Tard\'os, Juan D.},
journal={IEEE Transactions on Robotics},
volume={33},
number={5},
pages={1255--1262},
doi = {10.1109/TRO.2017.2705103},
year={2017}
}
We have tested the library in Ubuntu 16.04, but it would be easy to compile in other platforms. To build SuperPoint-SLAM, you need a GPU that supports CUDA 10.2 or higher. Of course, you can use a lower CUDA version by modifying the LibTorch code accordingly. However, I cannot guarantee normal operation. Also, To some extent, powerful cpu is required for real-time performance and more stable and accurate results of SuperPointSLAM.
So, Let's first look at the build requirements.
You can conveniently install the necessary libraries using the Basg Scripts we wrote. However, you can also install it yourself after looking at the official website by looking at the library list described below. If you install it yourself, keep in mind that we put all the important libraries in "/usr/local" in our project.
To use our scripts. Note that the order of execution matters because Eigen3 can be used other libraries' build.
git clone https://github.com/ChanWoo25/SuperPoint-SLAM.git
cd SuperPoint-SLAM
chmod +x INSTALL_*
bash INSTALL_Eigen3.sh
bash INSTALL_OpenCV.sh
bash INSTALL_LibTorch.sh
bash INSTALL_Pangolin.shWe use the new thread and chrono functionalities of C++11.
Required by g2o (see below). Download and install instructions can be found at: http://eigen.tuxfamily.org. (Tested with Eigen 3.3.8 (At least 3.1.0 required)).
We used the latest version of OpenCV for stable operation. (Tested with OpenCV 3.2.0 and 3.4.11)
We used the 1.6.0 version of LibTorch for SuperPoint Implementation.
We use Pangolin for visualization and user interface. Dowload and install instructions can be found at: https://github.com/stevenlovegrove/Pangolin.
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.
TODO...
TUM Dataset
- See runtum.sh
KITTI Dataset
- See runkitti.sh
Unfortunately, I lost my SuperPoint feature Vocabulary created by kitti dataset only. However, you can craete your own Vocabulary using my DBoW2 code which changed to deal with SuperPoint features.