Ask Your Question

object detection with color

asked 2011-07-22 08:17:46 -0500


I am using the tabletop object detector to give the robot a semantic map of the environment it is in.

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?

edit retag flag offensive close merge delete

1 Answer

Sort by ยป oldest newest most voted

answered 2011-09-02 10:42:51 -0500

Mac gravatar image

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.

edit flag offensive delete link more

Your Answer

Please start posting anonymously - your entry will be published after you log in or create a new account.

Add Answer

Question Tools


Asked: 2011-07-22 08:17:46 -0500

Seen: 1,238 times

Last updated: Sep 02 '11