Stanford CS223B Computer Vision, Winter 2006 Lecture 1 Intro and Image Formation

1
Stanford CS223B Computer Vision, Winter
2006Lecture 1 Intro and Image Formation

• Professor Sebastian Thrun
• CAs Dan Maynes-Aminzade and Mitul Saha
• Guest lectures Rick Szeliski (Microsoft
  Research)
• and Gary Bradski (Intel Research and Stanford)

2
Todays Goals

• Learn about CS223b
• Get Excited about Computer Vision
• Learn about Image Formation (Part 1)

3
Administrativa

• Time and Location
• Mon/Wed 1100-1220, McCullough 115
• SCPD Televised
• Web site
• http//cs223b.stanford.edu

4
People Involved

• You 90 students signed up
• Me Sebastian Thrun
• Office hours Wed 3-4 with appointment, Gates 154
• CA Mitul Saha
• office hours Tue, Thu 3-5pm, Clark S264
• CA Dan Maynes-Aminzade
• office hours Mon, Wed 3-5pm, Gates 386
• Guest lectureres
• Gary Bradski, Intel Research and Stanford
• Rick Szeliski, Microsoft Research

5
Guest Lecturers
6
Goals

• To familiarize you with basic the techniques and
  jargon in the field
• To enable you to solve computer vision problems
• To let you experience (and appreciate!) the
  difficulties of real-world computer vision
• To get you excited!

7
Course Requirements Criteria

• You have to
• Turn in all assignments (30 of final grade)
• Pass the midterm (30)
• Pass the competition (40)
• Late policy
• Six late days
• Teaming
• Assignments/competition up to three students

8
Course Overview

• Basics
• Image Formation and Camera Calibration
• Image Features
• Calibration
• 3D Reconstruction
• Stereo
• Image Mosaics, Stiching
• Motion
• Optical Flow
• Structure From Motion
• Tracking
• Object detection and recognition
• Grouping
• Detection
• Segmentation
• Classification

9
Course Overview
10
The Text
11
The Class Competition

• No Major Project
• Instead A competition

12
The Competition Motivation
13
Implications

• Why not run a competition in CS223b?

14
The Competition

• March 13, 11-1130am The Competition
• Given a stream of images acquired by a vehicle on
  a highway
• Predict a classification of moving/non moving
  objects 5 seconds ahead
• Same data used in all programming assignments
• HW1 Feature/object detection (due Jan 23)
• HW2 Camera calibration (due Jan 30)
• HW3 Visual odometry (due Feb 13)

15
The Competition, Example
This is not the real data. Well collect the data
with Stanley
16
Todays Goals

• Learn about CS223b
• Get Excited about Computer Vision
• Learn about image formation (Part 1)

17
Computer Graphics
Output
Image
Model
Synthetic Camera
(slides courtesy of Michael Cohen)
18
Computer Vision
Output
Model
Real Scene
Real Cameras
(slides courtesy of Michael Cohen)
19
Combined
Output
Image
Real Scene
Model
Synthetic Camera
Real Cameras
(slides courtesy of Michael Cohen)
20
Example 1Stereo
See http//schwehr.org/photoRealVR/example.html
21
Example 2 Structure From Motion
http//medic.rad.jhmi.edu/pbazin/perso/Research/Sf
Mvideo.html
22
Example 3 3D Modeling
http//www.photogrammetry.ethz.ch/research/cause/3
dreconstruction3.html
23
Example 4 3D Modeling
Drago Anguelov
24
Example 4 3D Modeling
25
Example 4 3D Modeling
26
Example 5 Segmentation
http//elib.cs.berkeley.edu/photos/classify/
27
Example 6 Classification
28
Example 6 Classification
29
Example 7 Optical Flow
Demo Dirt Road
Andrew Lookingbill, David Lieb, CS223b Winter 2004
30
Example 8 Detection
David Stavens, Andrew Lookingbill, David Lieb,
CS223b Winter 2004
31
Example 9 Tracking
http//www.seeingmachines.com/facelab.htm
32
Example 10 Human Vision
33
Example 9 Human Vision
34
Excited Yet?
35
Todays Goals

• Learn about CS223b
• Get Excited about Computer Vision
• Learn about image formation (Part 1)

36
Topics

• Pinhole Camera
• Orthographic Projection
• Perspective Camera Model
• Weak-Perspective Camera Model

37
Pinhole Camera
-- Brunelleschi, XVth Century
many slides in this lecture from Marc Pollefeys
comp256, Lect 2
38
Perspective Projection
A similar triangles approach to vision.
Marc Pollefeys
39
Perspective Projection
O
X
-x
f
f
Z
40
Consequences Parallel lines meet

• There exist vanishing points

Marc Pollefeys
41
The Effect of Perspective
42
Vanishing points
VPL
H
VPR
VP2
VP1
Different directions correspond to different
vanishing points
VP3
Marc Pollefeys
43
Implications For Perception
Same size things get smaller, we hardly notice
Parallel lines meet at a point
A Cartoon Epistemology http//cns-alumni.bu.edu
/slehar/cartoonepist/cartoonepist.html
44
Perspective Projection
O
X
-x
f
Z
45
Weak Perspective Projection
Z
O
-x
Z
f
Z
46
Generalization of Orthographic Projection
When the camera is at a (roughly constant)
distance from the scene, take m1.
Marc Pollefeys
47
Pictorial Comparison
Weak perspective
Perspective
?
Marc Pollefeys
48
Summary Perspective Laws

1. Perspective
2. Weak perspective
3. Orthographic

49
Limits for pinhole cameras