3D Volumertic Semantic Mapping based on voxblox and yolact-ros-pro. The repo is modified from voxblox-plusplus
nstall ROS following the instructions at the ROS installation page. The full install (ros-kinetic-desktop-full, ros-melodic-desktop-full) are recommended.
Make sure to source your ROS setup.bash script by following the instructions on the ROS installation page.
environment: ROS kinetic or ROS melodic
export ROS_VERSION=kinetic # (Ubuntu 16.04: kinetic, Ubuntu 18.04: melodic)
catkin config --cmake-args -DCMAKE_CXX_STANDARD=14 -DCMAKE_BUILD_TYPE=Release
Enter your ros workspace , suppose you workspace is ~/catkin_ws
cd ~/catkin_ws/
catkin init
catkin config --extend /opt/ros/$ROS_VERSION --merge-devel
catkin config --cmake-args -DCMAKE_CXX_STANDARD=14 -DCMAKE_BUILD_TYPE=Release
wstool init src
cd ~/catkin_ws/src
git clone --recurse-submodules https://github.com/ethz-asl/voxblox-plusplus.git
wstool merge -t . voxblox-plusplus/voxblox-plusplus_https.rosinstall
wstool update
build rosnodes
catkin build depth_segmentation gsm_node
source ../devel/setup.bash # (bash shell: ../devel/setup.bash, zsh shell: ../devel/setup.zsh)
Since this package needs to run with yolact-ros-pro. We highly recommend to use a ubuntu 16.04 (ROS kinetic) docker container or ubuntu 18.04 (ROS melodic) docker container to build this package.
Instance semantic segmentation result on dataset sceneNN
or run this command to download dataset sceneNN
wget http://robotics.ethz.ch/~asl-datasets/RAL-2019-voxblox-plusplus/scenenn_231/scenenn_231.bag
3D mapping result of dataset sceneNN
3D mapping result of dataset asl_office_floor
or run this command to download dataset asl_office_floor
wget http://robotics.ethz.ch/~asl-datasets/RAL-2019-voxblox-plusplus/office_floor/asl_office_floor.bag
roslaunch gsm_node scenenn_dataset.launch bag_file:=/path/to/scenenn_231.bag
roslaunch gsm_node asl_office_floor_dataset.launch bag_file:=/path/to/asl_office_floor.bag