HTTPS SSH
Voxel planes creates a realtime mesh from a continuously updated pointcloud. Authors: [Julian Ryde](http://www.cse.buffalo.edu/~jryde/) [Vikas Dhiman](http://vikasdhiman.com) Original paper: [pdf](http://www.cse.buffalo.edu/~jryde/publications/iros2013_voxel_planes.pdf) # Running voxel planes mapping demo with Asus xtion * [Install ROS](http://wiki.ros.org/groovy/Installation/Ubuntu) and dependencies For Ubuntu 12.10: sudo sh -c 'echo "deb http://packages.ros.org/ros/ubuntu quantal main" > /etc/apt/sources.list.d/ros-latest.list' wget http://packages.ros.org/ros.key -O - | sudo apt-key add - sudo apt-get update sudo apt-get install ros-groovy-ros-base ros-groovy-openni-launch ros-groovy-nav-msgs The following assume that you download everything to your home directory * Install FOVIS library. * Download [fovis](https://fovis.googlecode.com/files/libfovis-1.0.0.tar.gz) * Make and install cd libfovis mkdir build cd build cmake .. make sudo make install * execute in terminal or put in .bashrc export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/usr/local/lib * Install [FOVIS ROS wrapper](http://wiki.ros.org/fovis) svn co https://fovis-pkg.googlecode.com/svn/trunk/ export ROS_PACKAGE_PATH=${ROS_PACKAGE_PATH}:~/fovis_lib sudo rosdep init rosdep update rosmake fovis rosmake fovis_lib * Get edgevoxel repo git clone https://jryde@bitbucket.org:/jryde/edgevoxels * Install packages for edgevoxels sudo apt-get install python-scipy python-matplotlib python-numpy mayavi2 * Add edgevoxels/ros/edgevoxels to the ROS package path export ROS_PACKAGE_PATH=${ROS_PACKAGE_PATH}:~/edgevoxels/ros * Run voxel\_planes.launch roslaunch edgevoxels voxel_planes.launch ## Rerunning experiments * Build cpp dependencies. sudo apt-get install libqhull-dev sudo add-apt-repository ppa:v-launchpad-jochen-sprickerhof-de/pcl sudo apt-get update sudo apt-get install libpcl-all cd cpp/; mkdir build cmake .. make * Add src/ and lib/ to the PYTHONPATH export PYTHONPATH=$PYTHONPATH:src/:lib/ * Running experiments on thermocolorlab dataset. The following will save experimental results in the data/ directory. *.vtk files can be visualized with pcl_viewer python scripts/voxel_planes_run_experiments.py data/thermocolorlab_scan000.pcd * The plots in the paper can be plotted by using (it uses the data saved by above script in the data directory): python scripts/voxel_planes_plot_error_vs_file_size.py data/thermocolorlab_scan000.pcd ## Running mapping on the freiburg dataset. * Run the mapping script on freiburg dataset. It will automatically download the dataset. python scripts/test_mapping_freiburg.py * The above script places the *.vtk file in /dev/shm directory. To visiualize it run the following script: python src/vis_process.py ## Acknowledgements This material is based upon work supported by the Fed- eral Highway Administration through CUBRC’s Coopera- tive Agreement No. DTFH61-07-H-00023 and NASA under grants NNX12AQ69G and NNX12AM06G. Any opinions, findings, conclusions or recommendations are those of the authors and do not necessarily reflect the views of the FHWA or NASA.