• Stars
    star
    709
  • Rank 63,849 (Top 2 %)
  • Language
    C++
  • Created over 5 years ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

VINS-Mono code without Ceres or ROS

Vins Course

Build Status

作者:贺一家,高翔,崔华坤,赵松

描述: 这是一个用于深蓝学院教学的代码,她基于 VINS-Mono 框架,但不依赖 ROS, Ceres, G2o。这个代码非常基础,目的在于演示仅基于 Eigen 的后端 LM 算法,滑动窗口算法,鲁棒核函数等等 SLAM 优化中常见的算法。 该代码支持 Ubuntu or Mac OS.

安装依赖项:

  1. pangolin: https://github.com/stevenlovegrove/Pangolin

  2. opencv

  3. Eigen

  4. Ceres: vins 初始化部分使用了 ceres 做 sfm,所以我们还是需要依赖 ceres.

编译代码

mkdir vins_course
cd vins_course
git clone https://github.com/HeYijia/VINS-Course
mkdir build 
cd build
cmake ..
make -j4

运行

1. CurveFitting Example to Verify Our Solver.

cd bin
./testCurveFitting 

2. VINs-Mono on Euroc Dataset

cd bin
./run_euroc /home/dataset/EuRoC/MH-05/mav0/ ../config/

vins

3. VINs-Mono on Simulation Dataset (project homework)

you can use this code to generate vio data.

https://github.com/HeYijia/vio_data_simulation

4. Validation Results

evo package

evo_ape euroc euroc_mh05_groundtruth.csv pose_output.txt -a -p

results

Licence

The source code is released under GPLv3 license.

We are still working on improving the code reliability. For any technical issues, please contact Yijia He [email protected] , Xiang Gao https://github.com/gaoxiang12 or Huakun Cuihttps://github.com/StevenCui.

For commercial inquiries, please contact Song Zhao [email protected]

感谢

我们使用了港科大沈老师组的 VINS-Mono 作为基础代码,非常感谢该组的工作。