ICP & Point Cloud Registration - Part 1: Known Data Association & SVD (Cyrill Stachniss, 2021)

39,581

1,187 0

Published 2021-03-20

Note: The derived SVD solution contains a small mistake. Either one has to swap the definition of a_n and b_n or one transposes the matrix R (out of the SVD). In the literature, both variants are used: either changing a_n and b_n (which equals to transposing H) or using R^T instead of R. Sorry for this mistake.

Part 1 of 3: Point cloud registration with known data associations using SVD, including the full derivation of the solution, which forms the basis for the Iterative Closest Point (ICP) algorithm.
Cyrill Stachniss, Spring 2021

#UniBonn #StachnissLab #robotics #computervision #photogrammetry #lecture

All Comments (21)

@georgebethel1320 1 year ago

This is a very insightful lecture Cyrill. You are the best; you make difficult concepts easy in a short video.
@bithigh8301 2 months ago

Sharing knowledge is the best thing you can do. Most of us will not have the chance to have access to great teachers like Cyrill. The explanations are neat and easily understandable. Thank you very much Cyrill
@matthewwithum8372 3 years ago

Does anyone on the planet convey remote sensing knowledge better than this man? I think not.
@antoniogarest7516 2 years ago

Such a great lecture! Thank you
@maryG128 9 months ago

Great lecture!!!! I'm dealing with an ICP algorithm for my thesis. Thanks for the lecture!!!
@longfeizhang4510 7 months ago

Great lecture!!! Thanks for sharing!
@francocipollone4679 2 years ago

Great lecture! Thanks Cyrill
@majidseydgar8643 2 years ago

That was a great lecture, thanks professor.
@oldcowbb 3 years ago

best way to spend spring break
@linray707 3 months ago

The lecture is very clear. Thank you professor
@WasserundLuft 1 year ago

This not only provided me with everything I needed to know about this subject for my thesis, it was also really really enjoyable to watch! Edit: Could the solution matrix R be a reflection matrix? As U or V may be.
@harrypotter1155 2 years ago

You are the absolute best!
@Shaharsarshalom1 9 months ago

Thank you so much for this lecture, you are my idol!; This lecture is like superman on execution
@marlonmalheiros8395 2 years ago

Excelent!
@skodsrs9453 9 months ago

Thanks for the incredible lecture! Just a slight question, in what ways is this different from the Kabsch-Umeyama algorithm described by Jim Larence et. Al. in "A Purely Algebraic Justification of the Kabsch-Umeyama Algorithm"? Or is this a different approach to arrive at that same algorithm?
@hetshah5260 1 year ago

Very informative video as always. May you also share the name of author or research paper of this method ?
@user-yp8yf9cx7u 2 years ago

Hi, I'm really thanks for your great lecture. BTW, I'm not sure about your Note. According to your Note, when i defined an = (xn - x0), bn = (yn - y0), R = UV^T is the right equation. Is my understanding correct? Then, how can get tr(RH) = tr(VDV^T) ? Can you explain more about it? Thanks,
@mahaaforoughnia9076 2 years ago

Very very useful lecture, Thank you. I just wanted to make sure that if we will get translation and rotation vectors for the whole surface? Or for each correspondence point?
@lirec6 2 years ago

Why is R computed like V*U(T) on slide 13 and U*V(T) on slide 17? Thank you
@ilhamwicaksono5802 3 years ago

Is there any literature to read more about this and related stuff? Very very grateful for your lecture Prof, very very well explained!