样例问题 Example question for A4M33MPV course

Example question for A4M33MPV course

1. Describe the algorithm for Harris points detection. Which parameters it has? How they influence the number of detected points? To which transformation (geometric/photometric) is this detector invariant?
2. Describe the choice of scale using Laplacian.
3. Describe steps to generalize Harriss detector to become affine invariant.
4. Define Maximally Stable Extremal Regions (MSER). Describe the algorithm for their detection.
5. Descriptor SIFT. Describe the algorithm and its properties.
6. Describe the “Shape context” descriptor.
7. Describe “Local Binary Patterns” like descriptors.
8. How are local affine frames used for invariant description?
9. Describe the steps for obtaining correspondences between a pair of images, which are taken from different viewpoints (wide-baseline matching).
10. How to find similar descriptors in a sub-linear time?
11. How does the “bag-of-words” method work?
12. What is the “inverted file” and how it is used for the image retrieval?
13. Define the tf-idf reweighting for visual words.
14. Describe the “query expansion” mechanism for improving the recall of the image retrieval.
15. Describe how the min-Hash method describes the images. Which properties it has?
16. Describe the RANSAC algorithm, its properties, advantages and disadvantages. Which parameters it has?
17. Describe some of the novel improvements to RANSAC method (WaldSac, PROSAC).
18. Describe the steps for object detection using “sliding windows” (“scanning windows”). How is the reasonable speed achieved?
19. Describe how to use an integral image for computing the sum of intensity function for rectangular region.
20. Why is the Adaboost algorithm often used for the “sliding window” methods? Give more than one good reason.
21. Describe the Hough transformation algorithm for detection or parametrized structure (line, circle, …). Discuss the properties of the algorithm (time and memory requirements, parameters).
22. Compare the Hough transformation with a brute-force space search algorithm.
23. Compare the Hough transformation with RANSAC.
24. For the problem of image patch search in an image (“patch matching”). Give some criterion functions and discuss their complexity, differentiability, etc….
25. For a static scene and viewing by camera with only horizontal movement. Draw a image patch, which will be useful for a tracking using a gradient method (KLT tracker). Which properties should has such image patch to be suitable for tracking?
26. Which image patches are suitable for tracking by gradient method such as KLT tracker? Why? Which patches are not suitable or totaly useless?
27. Mean-shift algorithm. Describe the principles and simulate calculation for 1D example.
28. Mean-shift algorithm. Color pixels [R,G,B] represented in 3D space. How you can reduce the color-space into 256 color-space?

from:　https://cw.fel.cvut.cz/wiki/courses/ae4m33mpv/labs/exam_questions