Home

Awesome

SuperPoint-SLAM

UPDATE: This repo is no longer maintained now. Please refer to https://github.com/jiexiong2016/GCNv2_SLAM if you are intereseted in SLAM with deep learning image descriptors.

NOTE: SuperPoint-SLAM is not guaranteed to outperform ORB-SLAM. It's just a trial combination of SuperPoint and ORB-SLAM. I release the code for people who wish to do some research about neural feature based SLAM.

This repository was forked from ORB-SLAM2 https://github.com/raulmur/ORB_SLAM2. SuperPoint-SLAM is a modified version of ORB-SLAM2 which use SuperPoint as its feature detector and descriptor. The pre-trained model of SuperPoint come from https://github.com/MagicLeapResearch/SuperPointPretrainedNetwork.

overview

traj

1. License (inherited from ORB-SLAM2)

See LICENSE file.

2. Prerequisites

We have tested the library in Ubuntu 12.04, 14.04 and 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.

C++11 or C++0x Compiler

We use the new thread and chrono functionalities of C++11.

Pangolin

We use Pangolin for visualization and user interface. Dowload and install instructions can be found at: https://github.com/stevenlovegrove/Pangolin.

OpenCV

We use OpenCV to manipulate images and features. Dowload and install instructions can be found at: http://opencv.org. Required at leat 2.4.3. Tested with OpenCV 2.4.11 and OpenCV 3.2.

Eigen3

Required by g2o (see below). Download and install instructions can be found at: http://eigen.tuxfamily.org. Required at least 3.1.0.

DBoW3 and g2o (Included in Thirdparty folder)

We use modified versions of DBoW3 (instead of 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.

Libtorch

We use Pytorch C++ API to implement SuperPoint model. It can be built as follows:

git clone --recursive -b v1.0.1 https://github.com/pytorch/pytorch
cd pytorch && mkdir build && cd build
python ../tools/build_libtorch.py

It may take quite a long time to download and build. Please wait with patience.

NOTE: Do not use the pre-built package in the official website, it would cause some errors.

3. Building SuperPoint-SLAM library and examples

Clone the repository:

git clone https://github.com/KinglittleQ/SuperPoint_SLAM.git SuperPoint_SLAM

We provide a script build.sh to build the Thirdparty libraries and SuperPoint_SLAM. Please make sure you have installed all required dependencies (see section 2). Execute:

cd SuperPoint_SLAM
chmod +x build.sh
./build.sh

This will create libSuerPoint_SLAM.so at lib folder and the executables mono_tum, mono_kitti, mono_euroc in Examples folder.

TIPS:

If cmake cannot find some package such as OpenCV or EIgen3, try to set XX_DIR which contain XXConfig.cmake manually. Add the following statement into CMakeLists.txt before find_package(XX):

set(XX_DIR "your_path")
# set(OpenCV_DIR "usr/share/OpenCV")
# set(Eigen3_DIR "usr/share/Eigen3")

4. Download Vocabulary

You can download the vocabulary from google drive or BaiduYun (code: de3g). And then put it into Vocabulary directory. The vocabulary was trained on Bovisa_2008-09-01 using DBoW3 library. Branching factor k and depth levels L are set to 5 and 10 respectively.

5. Monocular Examples

KITTI Dataset

  1. Download the dataset (grayscale images) from http://www.cvlibs.net/datasets/kitti/eval_odometry.php

  2. Execute the following command. Change KITTIX.yamlby KITTI00-02.yaml, KITTI03.yaml or KITTI04-12.yaml for sequence 0 to 2, 3, and 4 to 12 respectively. Change PATH_TO_DATASET_FOLDER to the uncompressed dataset folder. Change SEQUENCE_NUMBER to 00, 01, 02,.., 11.

./Examples/Monocular/mono_kitti Vocabulary/ORBvoc.txt Examples/Monocular/KITTIX.yaml PATH_TO_DATASET_FOLDER/dataset/sequences/SEQUENCE_NUMBER

6. Evaluation Results on KITTI

Here are the evaluation results of monocular benchmark on KITTI using RMSE(m) as metric.

Seq.DimensionORBSuperPoint
00564 x 4965.33X
011157 × 1827XX
02599 × 94621.28X
03471 × 1991.511.04
040.5 × 3941.620.35
05479 × 4264.853.73
0623 × 45712.3414.27
07191 × 2092.263.02
08808 × 39146.6839.63
09465 × 5686.62X
10671 × 1778.805.31

Citation

If you find this useful, please cite our paper.

@inproceedings{deng2019comparative,
  title={Comparative Study of Deep Learning Based Features in SLAM},
  author={Deng, Chengqi and Qiu, Kaitao and Xiong, Rong and Zhou, Chunlin},
  booktitle={2019 4th Asia-Pacific Conference on Intelligent Robot Systems (ACIRS)},
  pages={250--254},
  year={2019},
  organization={IEEE}
}