SEE-CSOM

SEE-CSOM: Sharp-Edged and Efficient Continous Semantic Occupancy Mapping through Multi-entropy Kernel Inference

This is a novel continuous semantic mapping algorithm, which can complete dense but not thick semantic map reconstruction efficiently.

Getting Started

Building with catkin

catkin_ws/src$ git clone https://github.com/BIT-DYN/SEE-CSOM
catkin_ws/src$ cd ..
catkin_ws$ catkin_make
catkin_ws$ source ~/catkin_ws/devel/setup.bash

Building using Intel C++ compiler (optional for better speed performance)

catkin_ws$ source /opt/intel/compilers_and_libraries/linux/bin/compilervars.sh intel64
catkin_ws$ catkin_make -DCMAKE_C_COMPILER=icc -DCMAKE_CXX_COMPILER=icpc
catkin_ws$ source ~/catkin_ws/devel/setup.bash

Running the Demo

$ roslaunch see_csom toy_example_node.launch

Running kitti (change the kitti dataset loction in launch)

$ roslaunch see_csom kitti_node.launch

Running SemanticKITTI

$ roslaunch see_csom semantickitti_quan.launch

Running Stanford

$ roslaunch see_csom stanford_node.launch

Citation

@article{see-csom,
  title={SEE-CSOM: Sharp-Edged and Efficient Continuous Semantic Occupancy Mapping for Mobile Robots}, 
  author={Deng, Yinan and Wang, Meiling and Yang, Yi and Wang, Danwei and Yue, Yufeng},
  journal={IEEE Transactions on Industrial Electronics}, 
  year={2024},
  volume={71},
  number={2},
  pages={1718-1728},
}