[ITK-users] IterativeClosestPoint2 example: how to get better results
Siavash Khallaghi
siavashk at ece.ubc.ca
Thu Aug 13 17:46:40 EDT 2015
ICP is notorious for its small capture range and suesceptibility to
noise/local minima. This is why soft correspondence schemes to point cloud
registration have been developed that generally have a larger capture range
(e.g. see CPD <http://arxiv.org/pdf/0905.2635.pdf> and GMM-FEM
<http://dx.doi.org/10.1109/TMI.2015.2440253> ). It could be that the code
is fine, but ICP fails to converge to the true solution.
Siavash
D'Isidoro Fabio wrote
>> I am not happy with the results, given that there is no additional noise
>> (the underlined values refer to error angles of up to 8 degrees and 3 mm
>> errors). I am surprised because there is no additional noise to the data,
>> so
>> I would expect an accurate registration. Are my results normal? How could
>> I
>> improve the results? Should I change the optimizer, or the transform?
--
View this message in context: http://itk-users.7.n7.nabble.com/ITK-users-IterativeClosestPoint2-example-how-to-get-better-results-tp35993p35998.html
Sent from the ITK - Users mailing list archive at Nabble.com.
More information about the Insight-users
mailing list