####仅作为笔记
环境:
ROS Kinetic
Boost
OpenCV
Eigen
fast
- 依赖
sudo apt-get install libopencv-dev #可以源码安装opencv
sudo apt-get install libboost-dev #boost库
sudo apt-get install libeigen3 #eigen3
- fast
https://github.com/uzh-rpg/fast.git
cd fast
mkdir build && cd build
make -j4
sudo make install
- 安装msckf
mkdir -p msckf_ws/src
cd msckf_ws/src
catkin_init_workspace
cd .. && catkin_make
sudo gedit ~/.bashrc 最后加入source ~/msckf_ws/devel/setup.bash 保存退出 在终端输入:source ~/.bashrc
cd ~/msckf_ws/src
git clone https://github.com/daniilidis-group/msckf_mono.git
cd ..
catkin_make
- 测试
#数据集下载:
wget http://robotics.ethz.ch/~asl-datasets/ijrr_euroc_mav_dataset/machine_hall/MH_03_medium/MH_03_medium.bag
mv MH_03_medium.bag <path_to_msckf_mono>/euroc/. #把下载好的数据集放到~/msckf_ws/src/msckf_mono/euroc/里面
roslaunch msckf_mono euroc.launch
或者:
下载ASL格式的数据集: https://projects.asl.ethz.ch/datasets/doku.php?id=kmavvisualinertialdatasets
#在下载的数据集中每一个YAML文件里面加入%YAML:1.0
roslaunch msckf_mono asl_msckf.launch data_set_path:=<directory of mav0 inside of sequence> stand_still_end:=<time to start at with dot at the end>
#stand_still_end这个参数需要自己去数据集查找对应的图像帧,找到无人机起飞的那一帧,对应的时间戳就是图片的名字
- 测试结果