0

Rosanswers logo

Hello,

I am using the tabletop object detector to give the robot a semantic map of the environment it is in. http://www.ros.org/wiki/tabletop_object_detector

I would like to be able to somehow also extract color information about the objects - for example if the robot detects a coca-cola can, the tag of the object should look something like ['can','red','white','metallic'] or ['can','red'] for example.

Does anybody know of a tool that does anything similar, maybe using the object detector positions as a part of the input?


Originally posted by Dimitar Simeonov on ROS Answers with karma: 535 on 2011-07-22

Post score: 0

1 Answer 1

0

Rosanswers logo

We're working on a system that does something like this (for large environments), but it's not released yet.

Until then, you could use the point clouds extracted by your segmenter as a source of data for labeling. For example, you could compute the mean color of the cloud, and then bucket that into "red", "blue", "orange", or whatever. Computing a "can" label could be done using cylinder fitting; computing "metallic" would be quite a bit trickier.


Originally posted by Mac with karma: 4119 on 2011-09-02

This answer was ACCEPTED on the original site

Post score: 1

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.