0% found this document useful (0 votes)
5 views4 pages

Computer Vision In-Class Exercise Guide

The document is an in-class exercise for the EC 9580 Computer Vision course at the University of Jaffna, consisting of 25 multiple-choice questions covering various topics in computer vision, such as the pinhole camera model, BRDF, depth estimation methods, and stereo vision principles. Each question tests knowledge on fundamental concepts and techniques relevant to the field. The exercise is designed to assess students' understanding of key computer vision topics within a one-hour timeframe.
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
5 views4 pages

Computer Vision In-Class Exercise Guide

The document is an in-class exercise for the EC 9580 Computer Vision course at the University of Jaffna, consisting of 25 multiple-choice questions covering various topics in computer vision, such as the pinhole camera model, BRDF, depth estimation methods, and stereo vision principles. Each question tests knowledge on fundamental concepts and techniques relevant to the field. The exercise is designed to assess students' understanding of key computer vision topics within a one-hour timeframe.
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

EC 9580 Computer Vision

Department of Computer Engineering


Faculty of Engineering, University of Jaffna
In Class Exercise
Duration: 1 hour Date:30th OCT 2024

1. Which of the following components is essential in the pinhole camera model?

A) Light source
B) Principal axis
C) Digital sensor
D) Camera aperture

2. In computer vision, the Bidirectional Reflectance Distribution Function (BRDF)


describes:

A) The color distribution of an image


B) Light reflection properties on surfaces
C) The transformation from 3D to 2D
D) Pixel intensity quantization

3. Which factor does NOT affect digital image sensor performance?

A) Shutter speed
B) Sampling pitch
C) Baseline distance
D) Fill factor

4. Which type of reflection occurs uniformly in all directions?

A) Specular reflection
B) Diffuse reflection
C) Anisotropic reflection
D) Ambient reflection

5. What is the main purpose of Phong shading in computer vision?

A) Creating realistic textures


B) Simulating light interaction with surfaces
C) Enhancing object boundaries
D) Emphasizing shadows

6. Chromatic aberration in a camera lens leads to:

A) Misalignment of color channels


B) Lower light sensitivity
C) Vignetting
D) Specular highlights

7. Image sampling in the digitization process involves:

A) Adjusting pixel color depth


B) Dividing the image into blocks
C) Converting a continuous image to discrete pixel values
D) Adding noise to improve contrast

8. Which property of light sources does NOT typically influence image formation?

A) Intensity C)Position
B) Frequency D)Exposure time

9. In the context of BRDF, Helmholtz reciprocity implies:

A) Light absorption is angle-dependent


B) The light path can be reversed
C) Only a portion of the light is reflected
D) Light reflects equally in all directions

10. The CRF (camera response function) is primarily used in photometric


calibration to:

A) Transform 2D images into 3D reconstructions


B) Correct nonlinear light intensity responses
C) Estimate the brightness of objects in HDR images
D) Simulate texture gradients

11. Which depth estimation method relies on visual cues like shading and
occlusion?

A) Monocular depth estimation


B) Stereo vision
C) LIDAR
D) Time of Fligh

12. In binocular stereopsis, what parameter is inversely proportional to depth?

A) Baseline C)Focal Length


B) Disparity D)Image width

13. Epipolar geometry is fundamental in stereo vision because it:

A) Simplifies correspondence search to a 1D line


B) Enables depth calculation without a baseline
C) Assumes parallel camera positions
D) Compensates for lens distortions

14. The fundamental matrix in stereo vision is used to:

A) Transform 2D images into 3D point clouds


B) Establish correspondences between stereo images
C) Calculate lens distortion effects
D) Adjust for light variations

15. Which of the following best describes the use of homography in depth
estimation?

A) Matches points across stereo images


B) Aligns planes for depth calculation
C) Maps disparities to intensity levels
D) Calculates exposure times

16. Which method is best for depth estimation in textureless regions?

A) Feature-based stereo matching


B) Block matching
C) Structured light
D) Monocular depth cues

17. Time of Flight (ToF) sensors estimate depth by:

A) Comparing two images from different viewpoints


B) Calculating the time light takes to reflect back
C) Using occlusion effects between objects
D) Measuring pixel intensity

18. What is the purpose of stereo rectification in stereo vision?

A) Correcting image distortions


B) Aligning epipolar lines for easier matching
C) Increasing baseline distance
D) Enhancing depth resolution

19. In active depth estimation, structured light involves:

A) Using laser pulses to detect surfaces


B) Measuring time delay between emitted and reflected light
C) Projecting known patterns to calculate depth
D) Applying a high-frequency light source
20. Which technique enhances stereo matching performance in challenging areas?

A) Epipolar rectification
B) Semi-global matching (SGM)
C) Perspective transformation
D) Lens calibration

21. For a perfectly flat scene, two images captured from slightly different angles
will have a depth map:

A) That can only be calculated using the BRDF


B) Derived from perspective cues alone
C) That can be described using a single homography
D) Only applicable to active stereo systems

22. In stereo vision, what does the baseline represent?

A) The focal length required for depth estimation


B) Distance between the two cameras
C) Distance from the object to each camera
D) Vertical alignment of the two images

23. Which of the following is a key challenge in depth estimation for stereo vision?

A) High computational cost


B) Low image contrast
C) Misalignment of vertical lines
D) Changes in pixel intensity

24. To compute depth, disparity between two stereo images is found by:

A) Converting pixel intensities to depth units


B) Aligning points between corresponding image regions
C) Calculating distance from focal points
D) Matching identical features in epipolar lines

25. In homography-based depth estimation, which condition would lead to


unreliable results?
A) Multiple occluding objects in the scene
B) Changes in exposure time
C) Low disparity across images
D) Uniform intensity levels throughout the scene

You might also like