Scribd
Upload
38 views4 pages

CV Quiz-1

The document outlines the structure and instructions for a Computer Vision quiz at the International Institute of Information Technology, Hyderabad, scheduled for January 31, 2024. It consists of 7 questions worth a total of 6 points, with the first three questions being compulsory and the remaining four allowing for the selection of any three to answer. The questions cover various topics in computer vision, including image retrieval, camera positioning, and mathematical concepts related to image processing.

Uploaded by

Pratyush Harsh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
38 views4 pages

CV Quiz-1

The document outlines the structure and instructions for a Computer Vision quiz at the International Institute of Information Technology, Hyderabad, scheduled for January 31, 2024. It consists of 7 questions worth a total of 6 points, with the first three questions being compulsory and the remaining four allowing for the selection of any three to answer. The questions cover various topics in computer vision, including image retrieval, camera positioning, and mathematical concepts related to image processing.

Uploaded by

Pratyush Harsh
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF or read online on Scribd
You are on page 1/ 4
International Institute of Information Technology, Hyderabad Spring 2024 CS7.505: Computer Vision Quiz1 31 January 2024 10:20 - 11:00 [40 minutes] Roll number: Name: Instructions: ‘© The quiz is of 6 points. There are 7 questions, each of 1 point. Questions Q1-Q3 are compulsory. * Among questions Q4-Q7, you can attempt any 3. + Feel free to draw over the gray lines for answering questions. * Please answer within the provided space, no extra sheets will be given. There is some extra space on the last page. Q1. (compulsory) Explain with an example why parallel lines in the real world converge to a point on the image plane. Hint: You may assume the camera is at the world ori Q2. (compulsory) Provide and explain three different reasons due to which the bag of visual words representations may perform poorly at image retrieval. } Q3. (comp ¥) How would you capture the perpendicular distance between a camera C placed at point P and a texture-less wall? Note, point P is not on the wall! You may assume access to multiple other cameras with the same known intrinsic properties. Think like computer vision students, Assume no access to length measuring devices/instruments, chessboards, any light sources, stickers, etc, Don’t damage the wall. Q4. Given the fundamental matrix, what does the epipolar constraint mean? Explain how this can be useful with an example. QS. How does a square camera sensor of 1.08cm x 1.08cm capture images or videos at a non- square resolution, such as HD 1920 x 1080? How is this codified in the camera intrinsics? Q6. Under what assumptions can we rewrite the 3x4 projection matrix as 3x3? Provide an example where this assumption is reasonable in the real-world. Q7. Mathematically, what differentiates an edge from a corner? Use the relationships between eigen vectors and eigen values of the following matri RR Igly w(t, eh where /y is the image gradient in the x-direction and ly is the gradient i the y-direction.

You might also like