jnhuanghao/kitti360_visualize

Visualize KITTI360 sequences on ROS with full tf support.

Kitti360 Visualization

Ros package to visualize KITTI-360 data with RVIZ

Getting Started:

Data Preparation

Download the KITTI360 dataset to your computer. We support the perspective images, Raw Velodyne Scans, calibrations, vehicle poses.

Ended up as : KITTI-360/{calibration/data_2d_raw/data_3d_raw/data_poses}.

Overwrite the folder names in the launch file to your data.

Software Prerequisite

This repo runs with ROS python3 (noetic), and we expect PyQt5 correctly setup with ROS installation.

Clone the repo under the {workspace}/src/ folder. Overwrite the folder names in the launch file to point to your data.

cd catkin_ws/src
git clone https://github.com/Owen-Liuyuxuan/kitti360_visualize
cd ..
catkin_make
source devel/setup.bash # devel/setup.zsh or devel/setup.sh for your own need.

# modify and check the data path!! Also control the publishing frequency of the data stream.
nano src/kitti360_visualize/launch/visualize_launch.launch 

# this will launch the data publisher / rviz / GUI controller
roslaunch kitti360_visualize visualize_launch.launch 

Core Features:

• KITTI-360 raw data sequence support.
• Stereo RGB cameras.
• LiDAR, RGB point clouds.
• TF-tree (camera and LiDAR).
• GUI control & ROS topic control.

GUI

User manual:

index: integer selection notice do not overflow the index number.

Stop: stop any data loading or processing of the visualization node.

Pause: prevent pointer of the sequantial data stream from increasing, keep the current frame.

Cancel: quit. (click this before killing the entire launch process)

Raw Data & Depth Prediction Dataset

We support video-like streaming raw data. Depth Prediction dataset follows similar structure of raw data, thus can be visualized in RGB point clouds together(optionally).

ROS Topics

/kitti360/left_camera/image (sensor_msgs/Image)

/kitti360/right_camera/image (sensor_msgs/Image)

/kitti360/left_camera/camera_info (sensor_msgs/CameraInfo)

/kitti360/right_camera/camera_info (sensor_msgs/CameraInfo)

/kitti360/lidar (sensor_msgs/PointCloud2)

The tf trees are also well constructed. We have a predefined rviz file for visualizing all topics and tf trees.