CAP5415 Computer Vision Spring 2003

1
CAP5415 Computer VisionSpring 2003

• Khurram Hassan-Shafique

2
Vision

• Vision is the process of discovering what is
  present in the world and where it is by looking.

3
Computer Vision

• Computer Vision is the study of analysis of
  pictures and videos in order to achieve results
  similar to those as by men.

4
Example

• Finding People in images
• Problem 1 Given an image I
• Question Does I contain an image of a person?

5
Yes Instances
6
No Instances
7
From Turing to Marr
A Brief History
8
Course Overview
9
Imaging Geometry
10
Camera Modeling

• Pinhole Cameras
• Lenses
• Camera Parameters and Calibration

11
Image Filtering and Enhancing

• Linear Filters and Convolution
• Image Smoothing
• Edge Detection
• Pyramids

12
Image Filtering and Enhancing
13
Region Segmentation
14
Color
15
Texture
16
Perceptual Organization
17
Perceptual Organization
18
Shape Analysis
19
Stereopsis
20
Motion and Optical Flow
21
High Level Vision
22
Applications (Mosaics)
23
Imaging Geometry
24
Pinhole Camera
25
Perspective Projection
26
Perspective Projection
27
Perspective Projection

• Points go to Points
• Lines go to Lines
• Planes go to whole image or Half-planes
• Polygons go to Polygons

28
Perspective Projection
29
Weak Perspective Projection
P
Q
Reference point
30
Orthographic Projection
31
Why Lenses
32
Why Lenses
33
Issues with Lenses
34
Refraction
35
Thin Lens Model
36
Thick Lens
37
Spherical Aberration
38
Distortions
39
Chromatic Aberration
40
Compound Lenses
41
Vignetting
42
Suggested Reading

• Chapter 1, David A. Forsyth and Jean Ponce,
  "Computer Vision A Modern Approach",