Scribd
Upload
20 views1 page

End Sem Computer Vision

The document outlines the End Semester Exam for the Computer Vision course at the Indian Institute of Information Technology, Nagpur. It includes various questions related to camera projection matrices, optical flow, histogram of oriented gradients, RANSAC, and block matching methods. The exam is closed book and closed notes, with all questions being compulsory and a total duration of 3 hours.

Uploaded by

gauravgreat777
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
20 views1 page

End Sem Computer Vision

The document outlines the End Semester Exam for the Computer Vision course at the Indian Institute of Information Technology, Nagpur. It includes various questions related to camera projection matrices, optical flow, histogram of oriented gradients, RANSAC, and block matching methods. The exam is closed book and closed notes, with all questions being compulsory and a total duration of 3 hours.

Uploaded by

gauravgreat777
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
You are on page 1/ 1

INDIAN INSTITUTE OF INFORMATION TECHNOLOGY, NAGPUR

Department of Electronics and Communication


Computer Vision
EndSem Exam
Duration: 3 hour Semester- VI &VIII Max. Marks: 50

Sample Important Instructions:


This is a closed book,closed notes examination.
Allthe questions are compulsory.
Maximum marks that can be obtained for a particular question are indicated in the brackets
| on the extreme right of the corresponding question
1. Calculate the projection matrix if principle point, focal length, orientation, andcarnera center of a
[0.36 0.48 -0.81
pin hole camera are given as (1,2), 0.5,-0.8 0.6 0 and (1,2,1) respectively. (5M]) CO-1
L0,48 0.64 0.6

2. Suppose, in stereo camerasetup, acameramatrix is represented as P= K[I|0]and the other


camera has pure translational motion in x-direction with e = (1,0,0). Compute fundamental
matrix. [SM] CO-2
5 4 0
3. Consider a projection matrix P =7 8 9 0. Compute the camera center in cartesian
1 -5 8 1
system. [SM]CO-2

4.Derive the optical flow using Lucas-Kanade Method. (5M] CO-3


2 5 22 3 5
2 4 12 5 4
5. Consider amatrix M=|3 5 22 8 6find histogram of oriented gradient containing 9bins
5 6 10 23 2
l6 2 18 21
at angles, 0, 20,40, 60, 80, 100, 120, 140, and 160. (5M (gradients) +5M (HoG)] (Note: solve for
internal 3x3 matrix.) CO-3

6. (a) Explain the problem with Least Square Method and how RANSAC can overcome the same?
Also specify the early stopping criterion for RANSAC. [5M] co-4
(b) Compute the iteration required to achieve 99% chance of gating pure inlier and 16.67% of
outliers, considering the minimal sample size of 2. (5M] CO-4
7. Ilustrate the block matching method using 3-point search algorithm. [5M] C0-4

8. (a) Given two features of size 4 as f(4,1,24) and g(9,1,2,2), compute L1 and L2 norms and
comment. (3M] CO-5
f0.6 0.4 0.21
(b) Consider a 3x3 matrix 0.2 0.6 0 apply Sobel mask both in x and y direction at the
Lo.6 0.5 0.6]
center pixel. (2M] CO-5

--;- Best Luck

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy