Differences

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

--- ece4580:questionsformative [2017/01/31 10:34] – pvela
+++ ece4580:questionsformative [2023/03/06 10:31] (current) – external edit 127.0.0.1
@@ Line 25: / Line 25: @@
 equations? (related to Question 4.3 part 3)
-==== Topic 2: Camera Geometry ====
+===== Topic 2: Camera Geometry =====
 ------------
@@ Line 45: / Line 45: @@
-==== Topic 3: Camera Calibration ====
+===== Topic 3: Camera Calibration =====
 ------------
@@ Line 64: / Line 64: @@
 In my notes, I use the symbol M, however Szeleski (Sec 2.1.5) and the DLT reading use the symbol P to denote the camera (projection) matrix.
-==== Topic 4: Stereo and Multiview Geometry ====
+===== Topic 4: Stereo and Multiview Geometry =====
 ------------
@@ Line 77: / Line 77: @@
-==== 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?
-------------
-==== 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?
+===== 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)