Scribd
Upload
22 views23 pages

Lecture 1 S

Uploaded by

Fatima
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
22 views23 pages

Lecture 1 S

Uploaded by

Fatima
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 23

CS-477: Computer Vision

Lecture 1:
Introduction
Course Overview and Grading Policy

1
CS-477: Computer Vision
Instructor A/p Kamran Aziz Bhatti
Text book and References
 Richard Szeliski,“Computer Vision:
Algorithms and Applications”
http://szeliski.org/Book/
 David A. Forsyth and Jean Ponce, “Computer Vision A Modern
Approach”, 2nd edition, Prentice Hall, Inc., 2003.
 Trucco, Alessandro Verri, “Introductory Techniques for 3-D
Computer Vision”.
 Class slides and research papers to be uploaded on Portal
Reference books
1. Mubarak Shah, "Fundamentals of Computer Vision"
2. On-line tutorial: http://www.cs.unc.edu/~marc/tutorial.pdf

2
CS-477: Computer Vision

Prerequisites for this course


 Digital image processing
 Working knowledge of Matlab/Python
 Requires mathematical tools related to:
– Euclidean and projective geometry
– Linear Algebra
– Vector calculus
– Probabilistic estimation

3
CS-477: Computer Vision

GRADING POLICY:
Midterm: ~30%
Quizzes: ~10%
Assignments / Project (Matlab/Python) ~10%
Final: ~50%

4
What is Computer Vision?

 Extract descriptions of the world from pictures or sequences of


pictures (videos) [Forsyth & Ponce, 2003].

 "Vision is the process of discovering from images what is


present in the world, and where it is" (David Marr).

 Computer vision is the study of analysis of pictures and videos


in order to achieve results similar to those as by men.

5
What is Computer Vision?
Vision

Computer Vision

6
What is Computer Vision?

Computer Vision focus on the following problems:


– What information should be extracted from the visual sensors?
– How is this information extracted?
– How should it be represented?
– How must the information be used to allow a robotic system to
perform its tasks?

7
Why study computer vision?

 Computer vision is at an extraordinary point in its development.


– Fast computers and image systems are cheaper;
– We are beginning to solve difficult problems that a lot of people
care about.
– There is a large market out there.
– There are still plenty of unsolved problems.
– None of the hard problems have been solved yet.
– It is a great time to research and study computer vision

8
Applications of Computer Vision

 Mobile robot navigation


 Industrial inspection
 Military intelligence
 Human computer interaction
 Image and video retrieval in digital libraries
 Medical image analysis
 Realistic rendering of synthetic scenes in CG

9
Computer Vision Overview
Real world

Image Formation and Processing on


Multiple Images
Camera Geometry Single Image  Multi-view geometry
 Modeling and  Linear Filters
 Stereo imaging
Calibration  Edge
 Structure from motion
 Image detection
rectification  Texture
Segmentation
Interpretation  Impose some order on
Recognition  Interpret
 Recognize objects group of pixels to
objects using
using separate them from
geometric
probabilistic each other or infer
information
techniques shape information

Action
10
Image Formation and Camera Geometry

12
Camera Calibration and Rectification
 Perspective Removal and Ortho-rectification

13
Camera Calibration and Rectification
 Radial Distortion

Computer Vision CS-477 14


Ortho-rectification of Aerial Images
Aerial Image

Reference Satellite Image

Ortho-rectified
Aerial Image

Computer Vision CS-477 16


Stereo Imaging
Geometry for calculation of vertical distance of objects/terrain by stereo images

18
Stereo Images: Examples
Stereo images from Satellite

19
Image Mosaic

Perspective removal + Mosaicing

20
Modeling based on Computer Vision Techniques

[Pollefeys9
9]
21
Segmentation and Thresholding
Region Segmentation

23
Segmentation and Thresholding

Global
Thresholding
Technique

Local
Thresholding
Technique

24
Extracting planted areas from Satellite
Image

25
Extraction of settlement area from an aerial image

26
Application of Computer Vision (Class Projects)

1. Computer vision is used to detect and classify objects

(e.g., road signs or traffic lights or Pedestrian detection)

2. Create 3D maps or motion estimation

3. Played a key role in making autonomous vehicles

4. Object Tracking

5. Health Care

26

You might also like