下载地址:https://www.zora.uzh.ch/id/eprint/175991/1/IROS18_Zhang.pdf
Z. Zhang and D. Scaramuzza, "A Tutorial on Quantitative Trajectory
Evaluation for Visual(-Inertial) Odometry," 2018 IEEE/RSJ
International Conference on Intelligent Robots and Systems (IROS),
Madrid, Spain, 2018, pp. 7244-7251, doi: 10.1109/IROS.2018.8593941.
安装python2 的pip
bash
wget https://bootstrap.pypa.io/pip/2.7/get-pip.py
// 或者curl https://bootstrap.pypa.io/pip/2.7/get-pip.py --output get-pip.py
sudo python2 get-pip.py
sudo apt-get install python-dev
安装成功之后可以查看
bash
pf@pf-NUC12WSKi7:~$ pip -V
pip 20.3.4 from /home/pf/.local/lib/python2.7/site-packages/pip (python 2.7)
安装依赖
bash
pip install numpy
pip install matplotlib
pip install colorama
pip install ruamel.yaml
sudo apt install texlive-fonts-recommended texlive-fonts-extra
sudo apt install dvipng
pip install PyYAML==5.1
下载编译如下
bash
mkdir catkin_ws
cd catkin_ws
mkdir src
cd src
git clone https://github.com/uzh-rpg/rpg_trajectory_evaluation.git
git clone https://github.com/catkin/catkin_simple.git
cd ..
catkin_make
简单评测
bash
source devel/setup.bash
rosrun rpg_trajectory_evaluation analyze_trajectory_single.py <result_folder>
直接将 <result_folder>替换为iTest文件夹即可,文件夹中放置真值和对应的估计值如下:
bash
├── analyze_trajectories_config
│ ├── euroc_vio_mono_stereo.yaml
│ └── euroc_vislam_mono.yaml
├── CMakeLists.txt
├── iTest
│ ├── stamped_groundtruth.txt
│ └── stamped_traj_estimate.txt
深入说明:
数据格式:
stamped_groundtruth.txt
: groundtruth poses with timestampsstamped_traj_estimate.txt
: estimated poses with timestamps- (optional)
eval_cfg.yaml
: specify evaluation parameters - (optional)
start_end_time.yaml
: specify the start and end time (in seconds) for analysis.,0
toN-1
*** stamped_groundtruth.txt
😗*
timestamp tx ty tz qx qy qz qw
1.403636580013555527e+09 1.258278699999999979e-02 -1.561510199999999963e-03 -4.015300900000000339e-02 -5.131151899999999988e-02 -8.092916900000000080e-01 8.562779200000000248e-04 5.851609599999999523e-01 ...
scripts/dataset_tools
文件下的脚本可以转换以上数据格式 (EuRoC style, ROS bag)
参数说明:
eval_cfg.yaml
trajectory alignment (used in absolute errors):
align_type
:sim3
: a similarity transformation (for vision-only monocular case)se3
: a rigid body transformation (for vision-only stereo case)posyaw
: a translation plus a rotation around gravity (for visual-inertial case)none
: do not align the trajectory
align_num_frames
: the number of poses (starting from the beginning) that will be used in the trajectory alignment.-1
means all poses will be used.
If this file does not exist, trajectory alignment will be done using sim3
and all the poses.
Start and end times
start_end_time.yaml
can specify the following (according to groundtruth time):
start_time_sec
: only poses after this time will be used for analysisend_time_sec
: only poses before this time will be used for analysis
If this file does not exist, analysis be done for all the poses in stamped_traj_estimate.txt
.
rosrun
rpg_trajectory_evaluation
analyze_trajectories.py
euroc_vislam_mono.yaml
--output_dir=./results/euroc_vislam_mono
--results_dir=./results/euroc_vislam_mono
--platform laptop
--odometry_error_per_dataset
--plot_trajectories
--rmse_table
--rmse_boxplot
--mul_trials=10