table top segmentation from kinect
Hello,
Does anyone know how to best achieve table top object segmentation from kinect sensor? is there any module/tutorial you can recommend me to use?
ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange |
Hello,
Does anyone know how to best achieve table top object segmentation from kinect sensor? is there any module/tutorial you can recommend me to use?
Use the openni_kinect package to set up your Kinect. You should be able to view the published point cloud topic in RViz.
Then, you can go through the pcl tutorials and pcl_ros tutorials. Tutorial 6 from the pcl_ros tutorials (SACSegmentationFromNormals planar segmentation) should do exactly what you need.
Hi,
I'm using the tabletop_object_detector in my manipulation stack branch.
I wrote an (incomplete) tutorial explaining what's going on.
You can check the code from here:
lp:~ugocupcic/sr-ros-interface/manipulation
I went through tutorial link. I wish to implement this. Will it work in ROS Indigo (ubuntu 14.04)? Also I am unable to access the code.
the tutorial in my answer is really old. You should probably take a look at this: http://wg-perception.github.io/tabletop
thanks Ugo, is your code open source. Could I have a look at it. This link which you have given above does not work for me. Thanks again for your time
That is strange, the link to the wiki above works for me. It's not a link to the code directly though, it's a wiki. Let me know if you can access it?
Thanks Ugo the wiki link works for me. I thought you implemented it, so wanted to see the code, however, l have been going through the wiki and has been very comprehensive. Thanks again
You can use the fixation-based segmentation method to extract the objects on a table. The code is available at http://www.umiacs.umd.edu/~mishraka/codeToSegmentRGBDScene.html
Asked: 2011-06-20 21:44:43 -0600
Seen: 2,036 times
Last updated: Oct 13 '11
How to segment/extract a sphere using pcl_ros?
Navigation planning based on kinect data in 2.5D?
How to use pcl::registration::estimateRigidTransformation?
"roslaunch pi_tracker skeleton.launch" Fails
2D SLAM with gmapping and openni_kinect
PointCloud subscriber/publisher types
Best toolchain for recording kinect data and converting to pointcloud offline?