Title: Stanford CS223B Computer Vision, Winter 2005 Lecture 1 Intro and Image Formation
1Stanford CS223B Computer Vision, Winter
2005Lecture 1 Intro and Image Formation
- Sebastian Thrun, Stanford
- Rick Szeliski, Microsoft
- Hendrik Dahlkamp, Stanford
2Todays Goals
- Learn about CS223b
- Get Excited about Computer Vision
- Learn about Image Formation (tbc)
3Administrativa
- Time and Location
- Tue/Thu 115-235, Gates B03
- SCPD Televised (Live on Channel E5)
- Web site
- http//cs223b.cs.stanford.edu
- Class Email list (announcements only)
- cs223b_at_cs.stanford.edu
- Class newsgroup (discussion)
- su.class.cs223b (server news.stanford.edu)
4People Involved
- You! (63 students)
- Me!
- Rick Szeliski, Microsoft
- Hendrik Dahlkamp
5(No Transcript)
6The Text
7Course Overview
- Basics
- Image Formation and Camera Calibration
- Image Features
- 3D Reconstruction
- Stereo
- Image Mosaics
- Motion
- Optical Flow
- Structure From Motion
- Tracking
- Object detection and recognition
- Grouping
- Detection
- Segmentaiton
- Classification
8Course Outline
- http//cs223b.stanford.edu/schedule.html
9Goals
- 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!
10Requirements
- Attend participate in all classes except at
most two - Turn in all assignments (even if for zero credit)
- Pass the midterm exam
- Successfully carry out research project
- Jan 31 selection
- Feb 14 Interim report
- March 8/10 Class presentation
- March 15 Final report
- No exceptions!
11Grading Criteria
- 10 Participation
- 30 Assignments
- 30 Midterm exam
- 30 Project
- (35 of all students received an A in CS223b-04)
12Todays Goals
- Learn about CS223b
- Get Excited about Computer Vision
- Learn about image formation (tbc)
13Computer Graphics
Output
Image
Model
Synthetic Camera
(slides courtesy of Michael Cohen)
14Computer Vision
Output
Model
Real Scene
Real Cameras
(slides courtesy of Michael Cohen)
15Combined
Output
Image
Real Scene
Model
Synthetic Camera
Real Cameras
(slides courtesy of Michael Cohen)
16Example 1Stereo
See http//schwehr.org/photoRealVR/example.html
17Example 2 Structure From Motion
http//medic.rad.jhmi.edu/pbazin/perso/Research/Sf
Mvideo.html
18Example 3 3D Modeling
http//www.photogrammetry.ethz.ch/research/cause/3
dreconstruction3.html
19Example 4 Classification
http//elib.cs.berkeley.edu/photos/classify/
20Example 4 Classification
http//elib.cs.berkeley.edu/photos/classify/
21Example 5 Detection and Tracking
http//www.seeingmachines.com/facelab.htm
22Example 6 Optical Flow
David Stavens, Andrew Lookingbill, David Lieb,
CS223b Winter 2004
23Example 7 Learning
Demo Dirt Road
Andrew Lookingbill, David Lieb, CS223b Winter 2004
24Example 8 Human Vision
25Example 8 Human Vision
26Excited Yet?
27Computer Vision TruccoVerri98
28Todays Goals
- Learn about CS223b
- Get Excited about Computer Vision
- Learn about image formation (tbc)
29Topics
- Pinhole Camera
- Orthographic Projection
- Perspective Camera Model
- Weak-Perspective Camera Model
30Pinhole Camera
-- Brunelleschi, XVth Century
many slides in this lecture from Marc Pollefeys
comp256, Lect 2
31Perspective Projection
A similar triangles approach to vision. Notes
1.1
Marc Pollefeys
32Perspective Projection
O
X
-x
f
Z
33Consequences Parallel lines meet
- There exist vanishing points
Marc Pollefeys
34Vanishing points
VPL
H
VPR
VP2
VP1
Different directions correspond to different
vanishing points
VP3
Marc Pollefeys
35The Effect of Perspective
36Implications 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
37Perspective Projection
O
X
-x
f
Z
38Weak Perspective Projection
Z
O
-x
Z
f
Z
39Generalization of Orthographic Projection
When the camera is at a (roughly constant)
distance from the scene, take m1.
Marc Pollefeys
40Pictorial Comparison
Weak perspective
Perspective
?
Marc Pollefeys
41Summary Perspective Laws
- Perspective
- Weak perspective
- Orthographic
42Limits for pinhole cameras