ROS Resources: Documentation | Support | Discussion Forum | Index | Service Status | ros @ Robotics Stack Exchange
Ask Your Question
1

How can I use NARF in PCL libray for Object regconition

asked 2011-04-18 19:46:33 -0600

embeddedheaven gravatar image

updated 2016-10-24 09:01:29 -0600

ngrennan gravatar image

Hello everyone,

I would like use kinect and PCL library to determine the location XYZ of a small object. I have try HSI threshold but it not really useful, the object bout 1mm1mm1mm.

Thanks you

edit retag flag offensive close merge delete

3 Answers

Sort by » oldest newest most voted
2

answered 2011-04-18 22:06:58 -0600

Did you have a look at the NARF section in the PCL tutorials?

Also, for such a tiny object, the Kinect's resolution is not high enough (for use with NARF, or anything else - there are simply not enough points on the object). Did you try visualize the Kinect point cloud in RViz, and had a look at it? If a human can't separate the object from the background noise, then forget about automated object recognition.

What other properties does the object have? Does it have a salient color? If yes, you would probably do much better with a high-resolution camera and some color blob detection. You mentioned trying a HSI threshold, why didn't it work?

edit flag offensive delete link more
1

answered 2011-04-18 22:45:31 -0600

embeddedheaven gravatar image

Thanks you,

With HSI threshold large object is work well, with small objects sometime it appear and some time it's disappear.

I used to use cvblob library of 2D blob detection, do we have blob detection in PCL library?

edit flag offensive delete link more
1

answered 2013-01-26 06:13:24 -0600

You might also want to give the SURE 3D features a try:

code.google.com/p/sure-3d-features

They have been used for place recognition:

"Place Recognition using Surface Entropy Features"

www.ais.uni-bonn.de/papers/ICRA_WS_SPME_2012_Fiolka_et_al.pdf

edit flag offensive delete link more

Comments

Thanks for the link, I wasn't aware of that. This looks really useful.

Martin Günther gravatar image Martin Günther  ( 2013-02-04 22:10:26 -0600 )edit

Question Tools

Stats

Asked: 2011-04-18 19:46:33 -0600

Seen: 1,118 times

Last updated: Jan 26 '13