ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange
Ask Your Question

Pcl ros image extraction

asked 2014-09-26 08:57:38 -0600

pnambiar gravatar image

I have extracted an object of interest using Euclidean Cluster Extraction in PCL. I would now like to extract the corresponding object in a 2D image that has been saved simultaneously. Are there any tools available in ros/pcl that can be used to do this?

edit retag flag offensive close merge delete

1 Answer

Sort by ยป oldest newest most voted

answered 2014-09-26 10:07:36 -0600

paulbovbel gravatar image

PCL has tools to generate an image from the point cloud directly (basic or range image), however not for dealing with two parallel objects. The above links will work if you're willing to take a hit in quality, but if you want to work with the original RGB image, you'll have to do some manual calculations.

You could project the pointcloud onto a plane representing the rectified* image, and use the points to mark which pixels you want to 'keep'. Or just project the bounding box and.

*: I am not a vision expert, so this may not be rigorous

edit flag offensive delete link more

Question Tools

1 follower


Asked: 2014-09-26 08:57:38 -0600

Seen: 543 times

Last updated: Sep 26 '14