Die Suche ergab 33 Treffer

von qgao
6. Aug 2012 17:04
Forum: Computer Vision
Thema: alte Klausuren
Antworten: 5
Zugriffe: 1764

Re: alte Klausuren

Gibt es alte CV-Klausuren? Ich bin auf der Suche nach CV Klausuren. Hat jemand sie oder könntet jemand mir sagen, wie sie aussah. Vielen Dank im Voraus. Sorry, no old exams we can offer. But we prepared some examples in case people have no ideas how the exam questions look like. Please come to my o...
von qgao
6. Aug 2012 16:59
Forum: Computer Vision
Thema: Aids in the exam? (Hilfsmittel)
Antworten: 2
Zugriffe: 838

Re: Aids in the exam? (Hilfsmittel)

Ibliss hat geschrieben:What aids are allowed in the exam?

Calculator? Open book?
Calculator not allowed, books not allowed.

You can only bring a hand-written help sheet (up to A4 size, one-side).
von qgao
17. Jun 2012 15:12
Forum: Computer Vision
Thema: Lecture on wednesday?
Antworten: 2
Zugriffe: 729

Re: Lecture on wednesday?

We DO have class on 20.06 as usual.
von qgao
17. Jun 2012 15:10
Forum: Computer Vision
Thema: Exam, SS2012
Antworten: 1
Zugriffe: 821

Re: Exam, SS2012

Written exam on 13.08.2012, Monday, 10:00 -- 12:00am (place: S3|05, rooms TBA)
von qgao
29. Mai 2012 18:14
Forum: Computer Vision
Thema: Asgn 2, Problem 1
Antworten: 3
Zugriffe: 1024

Re: Asgn 2, Problem 1

I am confused too regarding 'sharping with the finest laplace layers'. Regarding the rebuilding: You shall rebuild the image from the laplace pyramide. It is expected that you already have the laplace for this task. Accordingly to the slides you start with the lowest layer (8x8) scale it up add and...
von qgao
29. Mai 2012 17:59
Forum: Computer Vision
Thema: Asgn 2, Problem 1
Antworten: 3
Zugriffe: 1024

Re: Asgn 2, Problem 1

First, "scale up" means "take the Laplacian images and multiply with some number", right? Otherwise, which purpose would scaling the image up (with our function upsample2) have? yes, you are right. Second, "reassemble the pyramid" does not refer to the construction of the Laplace pyramids, but rath...
von qgao
29. Mai 2012 17:42
Forum: Computer Vision
Thema: Ex 2 Task 2
Antworten: 4
Zugriffe: 932

Re: Ex 2 Task 2

Sete hat geschrieben:I am a little bit confused by this issue, too. If i am not mistaken, by applying SVD on all the images we obtain 760 eigenvectors, each with a dimension of something about 8000.
So where does the "20" come from? Should we only use the 20 "most important" vectors to form our subspace?
Right!
von qgao
22. Mai 2012 16:47
Forum: Computer Vision
Thema: Ex 2 Task 2
Antworten: 4
Zugriffe: 932

Re: Ex 2 Task 2

I have a question about the last ToDo in Task2. It says, the image has to be projected on our 20 dimensional subspace. Why is our subspace 20 dimensional? I calculated the subspace from the 760 images in yale_faces/, which resulted in a 760 dimensional subspace. It seems you do not well understand ...
von qgao
7. Mai 2012 12:45
Forum: Computer Vision
Thema: Compute Derivatives by central differences
Antworten: 4
Zugriffe: 1258

Re: Compute Derivatives by central differences

In practice, the sign of derivatives is usually not that important.

But in the exercise problem, we should compute the filters and the derivatives based on the given definition from the problem description.
von qgao
3. Mai 2012 15:08
Forum: Computer Vision
Thema: Ex1 Task 2
Antworten: 7
Zugriffe: 1500

Re: Ex1 Task 2

The aim is to use the x,y-coordinates and perform the inverse operations?! apply inverse projection with in/extrinsics on x,y -> add the separatly provided z coordinates, undo the remaining operations. Is that correct? Sorry for asking so much, but I really have troubles to understand the aim here....
von qgao
3. Mai 2012 15:06
Forum: Computer Vision
Thema: Ex1 Task3
Antworten: 3
Zugriffe: 952

Re: Ex1 Task3

kleinβeta hat geschrieben: so what should we normalize the filter to? should rows sum up to 1 (or -1) or should the maximum value of a row be 1 or something else?
sum to 1 for the Gaussian filter.
von qgao
26. Apr 2012 13:03
Forum: Computer Vision
Thema: Ex1 Task 2
Antworten: 7
Zugriffe: 1500

Re: Ex1 Task 2

Regarding task 2) The data obj_2d.mat provides me with x,y points and you provided the steps that were performed on the 3D points? I shall perform the provided operations on my 2D points and obtain my 3D points, which have the same z-values like those in obj_2d.mat, is that right? Seems you misunde...
von qgao
25. Apr 2012 17:05
Forum: Computer Vision
Thema: Ex1 Task 2
Antworten: 7
Zugriffe: 1500

Re: Ex1 Task 2

Hi, is the ordering of the tasks fo task 2 correct? The first two tasks are independent to the third (load and show 2D points). Firstly, I shall write 2 functions hom->cart and cart->hom and Right! Secondly, draw the transformation+projection matrix out of the blue and I don't understand "draw the ...
von qgao
20. Jul 2011 12:58
Forum: Computer Vision
Thema: A4 - Problem 3 - eightpoint algorithm
Antworten: 5
Zugriffe: 943

Re: A4 - Problem 3 - eightpoint algorithm

robert.n hat geschrieben:T and T' are two entirely different matrices, too! Arggghhh... me :arrow: dumbass... gah :cry:
Right! T' is not the transpose of T, but a different matrix.
von qgao
20. Jul 2011 12:56
Forum: Computer Vision
Thema: A4 - Problem 3 - eightpoint algorithm
Antworten: 5
Zugriffe: 943

Re: A4 - Problem 3 - eightpoint algorithm

robert.n hat geschrieben:My \(V_A^T\) has only 8 entries.
\(V_A^T\) should have 9 entries, because there is one additional constraint |f| = 1.

Zur erweiterten Suche