User Tools

Site Tools


ece4580:questionsformative

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision
Previous revision
ece4580:questionsformative [2017/01/31 10:34] pvelaece4580:questionsformative [2023/03/06 10:31] (current) – external edit 127.0.0.1
Line 78: Line 78:
  
 ===== Topic 5: Images as Functions ===== ===== Topic 5: Images as Functions =====
 +------------
  
 **Question 1:** What is a convolution kernel? What relationship is there with Fourier analysis? What purpose would a convolution kernel serve in image processing? **Question 1:** What is a convolution kernel? What relationship is there with Fourier analysis? What purpose would a convolution kernel serve in image processing?
  
  
------------- 
  
 ===== Topic 6: Optimization in Computer Vision ===== ===== Topic 6: Optimization in Computer Vision =====
Line 91: Line 91:
  
 **Question 2:** What is a Voronoi diagram (or Voronoi partition)?  How does it relate to Lloyd's algorithm?  What is Lloyd's algorithm? **Question 2:** What is a Voronoi diagram (or Voronoi partition)?  How does it relate to Lloyd's algorithm?  What is Lloyd's algorithm?
 +
 +===== Topic 7: Bayesian Statistics in Computer Vision =====
 +------------
 +
 +**Question 1:** What is Bayes' Rule? Why is it important to be aware of Bayes' rule when making decisions based on binary tests?
 +
 +===== Topic 8: Optical Flow =====
 +------------
 +
 +**Question 1:** What is the optical flow constraint? Why is it ill-posed (e.g., degenerate)?
 +
 +**Question 2:** What favorite trick do we apply to the optical flow constraint to obtain a well-posed optimization problem for dense optical flow?
 +
 +**Question 3:** //Optional:// Sparse optical flow doesn't have this problem.  Why not? (We covered it earlier in class)
  
  
ece4580/questionsformative.1485876880.txt.gz · Last modified: 2023/03/06 10:31 (external edit)