1. Stanford CS223B Computer Vision, Winter 2005 Lecture 1 Intro and Image Formation
Sebastian Thrun, Stanford
Rick Szeliski, Microsoft
Hendrik Dahlkamp, Stanford

2. Today’s Goals Learn about CS223b Get Excited about Computer Vision
Learn about Image Formation (tbc)

3. Administrativa Time and Location Web site Class newsgroup (discussion)
Tue/Thu 1:15-2:35, Gates B03
SCPD Televised (Live on Channel E5)
Web site
Class list (announcements only)
Class newsgroup (discussion)
su.class.cs223b (server: news.stanford.edu)

4. People Involved You! (63 students) Me! Rick Szeliski, Microsoft
Hendrik Dahlkamp:

6. The Text

7. Course Overview Basics 3D Reconstruction Motion
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

8. Course Outline

9. 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!

10. Requirements 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!

11. Grading Criteria 10% Participation 30% Assignments 30% Midterm exam
30% Project
(35% of all students received an A in CS223b-04)

12. Today’s Goals Learn about CS223b Get Excited about Computer Vision
Learn about image formation (tbc)

13. Computer Graphics Output Image Model Synthetic Camera
(slides courtesy of Michael Cohen)

14. Computer Vision Output Model Real Scene Real Cameras
(slides courtesy of Michael Cohen)

15. Combined Output Image Model Real Scene Synthetic Camera Real Cameras
(slides courtesy of Michael Cohen)

16. Example 1:Stereo
See

17. Example 2: Structure From Motion

18. Example 3: 3D Modeling

19. Example 4: Classification

20. Example 4: Classification

21. Example 5: Detection and Tracking

22. Example 6: Optical Flow
David Stavens, Andrew Lookingbill, David Lieb, CS223b Winter 2004

23. Example 7: Learning Demo: Dirt Road
Andrew Lookingbill, David Lieb, CS223b Winter 2004

24. Example 8: Human Vision

25. Example 8: Human Vision

26. Excited Yet?

27. Computer Vision [Trucco&Verri’98]

28. Today’s Goals Learn about CS223b Get Excited about Computer Vision
Learn about image formation (tbc)

29. Topics Pinhole Camera Orthographic Projection Perspective Camera Model
Weak-Perspective Camera Model

30. Pinhole Camera -- Brunelleschi, XVth Century
“shards of diamond” – those little pieces of beautiful truth scattered about.
-- Brunelleschi, XVth Century
*many slides in this lecture from Marc Pollefeys comp256, Lect 2

31. Perspective Projection
Derive the perspective equations on notes page 1.1
A “similar triangle’s” approach to vision. Notes 1.1
Marc Pollefeys

32. Perspective ProjectionX x -x Z f

33. Consequences: Parallel lines meet
There exist vanishing points
Marc Pollefeys

34. Vanishing points Different directions correspond
VPL
VPR
VP1
VP2
Different directions correspond
to different vanishing points
VP3
Marc Pollefeys

35. The Effect of Perspective

36. Implications For Perception*
Same size things get smaller, we hardly notice…
Parallel lines meet at a point…
* A Cartoon Epistemology:

37. Perspective ProjectionX -x Z f

38. Weak Perspective ProjectionZ O -x Z Z f

39. Generalization of Orthographic Projection
When the camera is at a
(roughly constant) distance
from the scene, take m=1.
Marc Pollefeys

40. Pictorial Comparison
Weak perspective
Perspective 
Marc Pollefeys

41. Summary: Perspective Laws
Weak perspective
Orthographic

42. Limits for pinhole cameras