Visual Feature Part 1: Computing Keypoints (Cyrill Stachniss)

Visual Feature Part 1: Computing Keypoints
Cyrill Stachniss, 2020

[@prabhatkumar3725]

Brilliantly explained! Thank You. All set for Part 2

[@lovekesh88]

Thanks Cyrill for these.

[@khubaibraza8446]

One of the best explanations!!

[@andreysaenko5948]

Great videos, thank you

[@Hikatiehow]

Excellently Explained! Really clarified a lot of questions I had

[@rafaeloliveiraribeir]

Excellent lecture. Thank you very much for this content.

[@rezakhoshkbary7975]

Very nice. Now I am learning. Thank you for your time.

[@coemgeincraobhach236]

so good, thank you!

[@victorsheverdin3935]

Thank you!

[@jwoo6516]

i really love this lecture. thank you so much

[@sejong-ai]

Thank you for the lovely lecture!

[@Eng.AwsNafea]

Thank you very much Prof

[@marshallalkarim5385]

Great lecture sir! may I request the topic about the "Poisson surface reconstruction"? Thank you beforehand.

[@navneetkrc]

33:20 Finding locally distinct Keypoints

[@Dadosza]

Great Video!
I have tried to follow the logic of the video in Octave. And I ran into the problem. My values from strucure matrix are far below zero. Their absolute values are large, but they are negative. Do you have an idea what I am missing?

[@2309ps]

did you square the diagonal values?

[@loneband302]

38:22, may I know how to find the value of keypoints scale? Really appreciated if you can explain.thank you..

[@CyrillStachniss]

Selecting the extreme value over the scales (similarly to the way you do it for x/y)

[@sinaebrahimifarsangi4584]

can we have the slides ?

[@CyrillStachniss]

Sure, see my teaching website.