Skip to content

Question 1 example 1

⬅️ [Question 1 example 2](<./Question 1 example 2.md>) | ⬆️ [Generated Test Questions](<./README.md>) | [Prompt](<./Prompt.md>) ➡️

Problem 1: Recall (25pts, 5pts each) Directions: Answer the following 5 subquestions. Use only the space provided.

  1. What is the fundamental relationship between disparity and depth in a stereo vision system?

  2. How many degrees of freedom are there in a 2D Affine transformation?

  3. When formulating image segmentation as a graph-based max-flow min-cut problem, what do the two special nodes, the Source ($S$) and the Sink ($T$), represent?

  4. True or False: When applying geometric transformations to warp an image, forward transformation mapping is preferred over backward transformation mapping.

  5. When evaluating the local uniqueness of an image patch using the eigenvalues ($\lambda_0, \lambda_1$) of the structure tensor, what geometric feature does the window represent if both eigenvalues are large?


Solutions:

  1. Solution: Disparity is inversely proportional to depth. (Note: The instructor explicitly stated this was a "fundamental equation to remember" and promised it would be asked on the exam).

  2. Solution: 6 degrees of freedom. (Note: The instructor explicitly warned that students would be tested on the degrees of freedom for various transformations).

  3. Solution: The Source ($S$) represents the foreground and the Sink ($T$) represents the background.

  4. Solution: False. Backward transformation is preferred because forward mapping pushes source pixels into the target grid, which can leave "holes" requiring arbitrary intensity distribution.

  5. Solution: A corner.


⬅️ [Question 1 example 2](<./Question 1 example 2.md>) | ⬆️ [Generated Test Questions](<./README.md>) | [Prompt](<./Prompt.md>) ➡️