Ask Your Question

narf descriptor

asked 2011-03-05 04:40:45 -0500

Yianni gravatar image


I was looking at the source code of the NARF descriptor and I modified the tutorial example (narf_feature_extraction) to calculate all the time the NARF descriptors from a pointcloud coming from a kinect camera. I have noticed a couple of things:

  1. Some times there are more descriptors than keypoints... I see that the size of the keypoints is taken from keypoint_indices2 and the descriptors are held in narf_descriptors. Is it correct that there are more descriptors than keypoints computed?

  2. I noticed the descritptor values for a pointcloud of a mug for example are around between -0.3 and 0.3, and with any object or the complete pointcould the values are between -0.5 and 0.5... If someone has experience and know the range of values it would be great... as I had a look on the paper (Steder et al., 2011) but I couldn't find out something specifically about it...

Many Thanks,

edit retag flag offensive close merge delete

2 Answers

Sort by ยป oldest newest most voted

answered 2011-03-06 19:49:12 -0500

Bastian Steder gravatar image

Hi Yianni,

  1. if the rotational invariance of the features is used there can be more than one descriptor per keypoint, if there was more than one strong rotation around the normal found for the extracted range value patch. Additionally, the number of descriptors can be lower than the number of keypoints. E.g., if the resolution in the area was too low.

  2. The values of the descriptor are normalized to -0.5 and 0.5, so that the difference between descriptor cells is between 0 and 1. I typically use the Manhattan distance divided by the descriptor size as the descriptor distance, which will always be in [0,1]. I prefer my values to be in areas where an interpretation is easy, which is why I use this normalization.

Cheers, Bastian

edit flag offensive delete link more


Although a bit delayed, thanks for your answer.
Yianni gravatar image Yianni  ( 2011-05-19 19:45:49 -0500 )edit

What is the frequency at which NARF features can be extracted on Kinect data?

sai gravatar image sai  ( 2013-05-19 18:17:28 -0500 )edit

answered 2013-01-26 06:16:08 -0500

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

Sources are available here:

edit flag offensive delete link more


SURE features are good but they work only at 5 Hz on the Kinect data.

sai gravatar image sai  ( 2013-05-19 18:16:47 -0500 )edit

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: 2011-03-05 04:40:45 -0500

Seen: 893 times

Last updated: Jan 26 '13