[ros-users] How to compare two point clouds?

[Christian Mueller]

On 02/18/2011 03:11 PM, Raymond Sheh wrote:
> Hi Christan,
>
> I guess it really depends what the purpose of your comparison is. What
> are you trying to do?
>
> ICP and other related alignment techniques are useful if you're trying
> to fit data to a model (eg. a new scan into an existing map, a possible
> object into a scene, etc.) and generally also provides transform
> information but if you're trying to do other things with your comparison
> perhaps a different (and possibly simpler) technique may be more suited.
>
> - Raymond
>
> On 18/02/2011 7:02 PM, Christian Mueller wrote:
>> Hello everybody,
>>
>> I have general question about 3D point cloud perception, since I am not
>> really familiar in processing point clouds. I would like to measure the
>> similarity of two point clouds ... a kind of fitness score between a
>> reference point cloud and another point cloud.
>>
>> Currently I am checking the literature, however I couldn't find a
>> "basic" algorithm. The only common way I found, is the alignment of both
>> points clouds by their center of mass. Afterwards one of the point cloud
>> is rotated till a best fit is achieved with the other point could.
>>
>> Is there maybe some other approach or technique?
>>
>> Thanks for any comment.
>>
>> Christian
>>
>>
>>
>>
>> _______________________________________________
>> ros-users mailing list
>> ros-users at code.ros.org
>> https://code.ros.org/mailman/listinfo/ros-users
> _______________________________________________
> ros-users mailing list
> ros-users at code.ros.org
> https://code.ros.org/mailman/listinfo/ros-users
>
Hi all,

thanks for the replies.
I am working at an object categorization project based on 3D information.
I would like to classify objects through their shape properties ( from 
the object point cloud).
First I thought, I can try to fit some primitive shapes like cylinders, 
spheres, cones, etc.
However most of the objects are not symmetric and more complex.
Hence I would like to create a kind of codebook of point-cloud-parts 
from the entire point cloud of the object.
Later on, these point-cloud-parts could be compared with a query 
point-cloud of an object in order to find a similarity.
However, to do so a reliable point-cloud similarity measure is required. 
As far as I know, ICP might be not that good for this purpose, since a 
good initial guess is required for a reliable alignment. Also the points 
clouds which are supposed to be compared have to be  similar.

Christian