Die Suche ergab 20 Treffer

von Christoph Vogel
7. Jul 2010 22:57
Forum: Computer Vision
Thema: Precision of this exercise
Antworten: 4
Zugriffe: 874

Re: Precision of this exercise

Hello. A distance of 2 is fine, but I think there should be a lot more inliers. So either you have too few inliers from the start or you do not find all of them. When visualizing your best pairs, how many inliers do you count ? With my parameter setting I have a rather large fraction of inliers. I g...
von Christoph Vogel
6. Jul 2010 11:45
Forum: Computer Vision
Thema: Precision of this exercise
Antworten: 4
Zugriffe: 874

Re: Precision of this exercise

Your result looks almost correct.

But it seems that you do not find the best homography.
If you visualize your result without blending, that should be clear.

Your homography points are very localized, therefore small errors in the estimation might become more severe.


Best regards,
Christoph
von Christoph Vogel
3. Jul 2010 15:01
Forum: Computer Vision
Thema: Exercise 5 - functions needed from exercise 3
Antworten: 0
Zugriffe: 352

Exercise 5 - functions needed from exercise 3

Hello everyone,

maybe I did not make myself clear enough.

All the functions you need to call from exercise 3 are already added to the startingKit.
Please take a look at the utils folder.

Best regards,
Christoph
von Christoph Vogel
1. Jul 2010 20:12
Forum: Computer Vision
Thema: Scale of extracted parameters (projecting matrix)
Antworten: 11
Zugriffe: 4092

Re: Scale of extracted parameters (projecting matrix)

You should return the orientation matrix, not the rotation. But that does not solve your problem here. We have the knowledge that we have a right handed system. Therefore we can verify that this is the case in our decomposition. The rq-decomposition does not guarantee that the second matrix is a rot...
von Christoph Vogel
1. Jul 2010 15:42
Forum: Computer Vision
Thema: Scale of extracted parameters (projecting matrix)
Antworten: 11
Zugriffe: 4092

Re: Scale of extracted parameters (projecting matrix)

You do not have to do that before, you can also do the re-scaling after the rq-decomposition. I will shortly explain why that re-scaling is equivalent to the early re-scaling of P and why the re-scaling is helpful to get the principal point. Rescaling is equivalent: The reason is that the third row ...
von Christoph Vogel
30. Jun 2010 15:21
Forum: Computer Vision
Thema: Scale of extracted parameters (projecting matrix)
Antworten: 11
Zugriffe: 4092

Re: Scale of extracted parameters (projecting matrix)

This is an answer to both questions. Let me start with the answer for Marc Schmitt. At first the rq-decomposition is not uniquely defined. As in the slides, if M = K*R, the following is also a valid decomposition: K * D * D^-1 R with D = (+- 1 0 0; 0 +-1 0; 0 0 +-1). Since if K is an upper triangle,...
von Christoph Vogel
30. Jun 2010 13:18
Forum: Computer Vision
Thema: Exercise 4 Q1c)
Antworten: 1
Zugriffe: 581

Re: Exercise 4 Q1c)

No do not use the original squares, but build a complete matrix by concatenating the previous matrices.
This also applies for the calibration matrices.

Best regards,
Christoph
von Christoph Vogel
29. Jun 2010 15:37
Forum: Computer Vision
Thema: Scale of extracted parameters (projecting matrix)
Antworten: 11
Zugriffe: 4092

Re: Scale of extracted parameters (projecting matrix)

At first sight I am not sure what your problem is, therefore I ask some questions first. 1) When only the scale of the points is wrong here, you are probably very close to the solution. Is your conversion from homogeneous to cartesian coordinates doing the right thing? Your cartesian coordinates are...
von Christoph Vogel
28. Jun 2010 10:47
Forum: Computer Vision
Thema: Exercise 4, Q1b
Antworten: 1
Zugriffe: 845

Re: Exercise 4, Q1b

Yes indeed, since the matrix squares stores cartesian coordinates, the call is the wrong way round.
Nevertheless the result of the line is nowhere used.

I am sorry for this inconvenience. I hope the line did not confuse somebody.
von Christoph Vogel
15. Jun 2010 20:21
Forum: Computer Vision
Thema: Registration for oral exam
Antworten: 0
Zugriffe: 387

Registration for oral exam

Dear all, the oral exam of the computer vision lecture will take place on the 22nd and 23rd of July. You need to register to us if you want to participate, and you will be notified about your exact date and time after we received all the emails. The DEADLINE FOR REGISTRATION is the 23rd of June. Ple...
von Christoph Vogel
15. Jun 2010 18:03
Forum: Computer Vision
Thema: Project Question 8 c)
Antworten: 1
Zugriffe: 413

Re: Project Question 8 c)

The parameter PARAMS.svmThreshold is used to reduce the amount of bounding boxes returned by the detector, while the parameter PARAMS.prec_recall_threshold is used for the evaluation. Both are used in Part 3 of the project. More precisely, PARAMS.svmThreshold is considered for the non-max suppressio...
von Christoph Vogel
15. Jun 2010 14:02
Forum: Computer Vision
Thema: Execution time of classification (Q4a)
Antworten: 2
Zugriffe: 542

Re: Execution time of classification (Q4a)

This is probably because your evaluation is currently dominated by the computation of the descriptor. The question was aiming at the evaluation of the SVM and not at the whole process of descriptor extraction. But I think that is not completely clear from the task description. So you could just ment...
von Christoph Vogel
14. Jun 2010 20:27
Forum: Computer Vision
Thema: sliding_window_faster
Antworten: 5
Zugriffe: 1784

Re: sliding_window_faster

The larger the training set the more the results will be unaffected. I actually didn' t and will not do a study on how much training with border artefacts will hurt your performance here. You might loose a percent in ERR or more or maybe nothing at all. In general you might introduce a pattern that ...
von Christoph Vogel
14. Jun 2010 11:03
Forum: Computer Vision
Thema: sliding_window_faster
Antworten: 5
Zugriffe: 1784

Re: sliding_window_faster

Thank you for the pictures. What you are seeing here is exactly the case of border effects I shortly described in my last reply. The red areas are different, which are the borders of your sliding window. These artefacts occur because of the behaviour of the derivative filter you are using. The borde...
von Christoph Vogel
11. Jun 2010 14:39
Forum: Computer Vision
Thema: sliding_window_faster
Antworten: 5
Zugriffe: 1784

Re: sliding_window_faster

There should be no difference in the gradients, regradless whether it is computed over the whole image or just over a small patch. The values at the pixel coverd by the patch should be equal to the corresponding values in the image. Regarding your comment 1.1 this seems to be the case for you. Did y...

Zur erweiterten Suche