conda create -n ros1_py27 python=2.7
mkdir ~/catkin_ws && cd catkin_ws
mkdir src && cd src
git clone https://github.com/daxiongpro/ros-kitti-project.git # catkin_create_pkg ros-kitti-project
cd ../../ # catkin_ws
catkin_init_workspace
catkin_make
- Add ros dist-package in your environment.
- Set up Environment Variable in Pycharmlibcv_bridge.so,tf2_ros, it is for the same purpose of
source devel/setup.zsh
in Pycharm.
- Download kitti raw dataset
2011_09_26_calib.zip
and2011_09_26_drive_0005_sync.zip
,label_02
.Download in baidu netdisk, password:k1f5
- Generate dataset directory as follows:
kitti_raw_data
kitti
├── bag
│ ├── 2020-07-04-15-31-16.bag
│ ├── kitti_2011_09_26_drive_0005_synced.bag
│ ├── kitti2bag.py
│ └── readme.txt
├── RawData
│ └── 2011_09_26
│ ├── 2011_09_26_drive_0005_sync
│ │ ├── image_00
│ │ ├── image_01
│ │ ├── image_02
│ │ ├── image_03
│ │ ├── oxts
│ │ └── velodyne_points
│ ├── calib_cam_to_cam.txt
│ ├── calib_imu_to_velo.txt
│ └── calib_velo_to_cam.txt
└── training
└── label_02
├── 0000.txt
├── 0001.txt
├── 0002.txt
├── 0003.txt
├── 0004.txt
├── 0005.txt
├── 0006.txt
├── 0007.txt
├── 0008.txt
├── 0009.txt
├── 0010.txt
├── 0011.txt
├── 0012.txt
├── 0013.txt
├── 0014.txt
├── 0015.txt
├── 0016.txt
├── 0017.txt
├── 0018.txt
├── 0019.txt
└── 0020.txt
- Change the dataset path in python script
- Run python:
eg1:
python kitti.py
(in ros-kitti-project/src) eg2:runros-kitti-project/src/kitti.py
in Pycharm
- Run rviz
roscore
rviz
- Add Pointcloud topic