Download presentation
Presentation is loading. Please wait.
Published byChance Mobley Modified over 9 years ago
2
Sebastian Thrun CS223B Computer Vision, Winter 2005 1 Stanford CS223B Computer Vision, Winter 2005 Lecture 1 Intro and Image Formation Sebastian Thrun, Stanford Rick Szeliski, Microsoft Hendrik Dahlkamp, Stanford
3
Sebastian Thrun CS223B Computer Vision, Winter 2005 2 Today’s Goals Learn about CS223b Get Excited about Computer Vision Learn about Image Formation (tbc)
4
Sebastian Thrun CS223B Computer Vision, Winter 2005 3 Administrativa Time and Location Tue/Thu 1:15-2:35, Gates B03 SCPD Televised (Live on Channel E5) Web site http://cs223b.cs.stanford.edu Class Email list (announcements only) cs223b@cs.stanford.edu Class newsgroup (discussion) su.class.cs223b (server: news.stanford.edu)
5
Sebastian Thrun CS223B Computer Vision, Winter 2005 4 People Involved You! (63 students) Me! Rick Szeliski, Microsoft Hendrik Dahlkamp:
6
Sebastian Thrun CS223B Computer Vision, Winter 2005 5
7
6 The Text
8
Sebastian Thrun CS223B Computer Vision, Winter 2005 7 Course 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
9
Sebastian Thrun CS223B Computer Vision, Winter 2005 8 Course Outline http://cs223b.stanford.edu/schedule.html
10
Sebastian Thrun CS223B Computer Vision, Winter 2005 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!
11
Sebastian Thrun CS223B Computer Vision, Winter 2005 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!
12
Sebastian Thrun CS223B Computer Vision, Winter 2005 11 Grading Criteria 10% Participation 30% Assignments 30% Midterm exam 30% Project (35% of all students received an A in CS223b-04)
13
Sebastian Thrun CS223B Computer Vision, Winter 2005 12 Today’s Goals Learn about CS223b Get Excited about Computer Vision Learn about image formation (tbc)
14
Sebastian Thrun CS223B Computer Vision, Winter 2005 13 Computer Graphics Image Output Model Synthetic Camera (slides courtesy of Michael Cohen)
15
Sebastian Thrun CS223B Computer Vision, Winter 2005 14 Real Scene Computer Vision Real Cameras Model Output (slides courtesy of Michael Cohen)
16
Sebastian Thrun CS223B Computer Vision, Winter 2005 15 Combined Model Real Scene Real Cameras Image Output Synthetic Camera (slides courtesy of Michael Cohen)
17
Sebastian Thrun CS223B Computer Vision, Winter 2005 16 Example 1:Stereo See http://schwehr.org/photoRealVR/example.html
18
Sebastian Thrun CS223B Computer Vision, Winter 2005 17 Example 2: Structure From Motion http://medic.rad.jhmi.edu/pbazin/perso/Research/SfMvideo.html
19
Sebastian Thrun CS223B Computer Vision, Winter 2005 18 Example 3: 3D Modeling http://www.photogrammetry.ethz.ch/research/cause/3dreconstruction3.html
20
Sebastian Thrun CS223B Computer Vision, Winter 2005 19 Example 4: Classification http://elib.cs.berkeley.edu/photos/classify/
21
Sebastian Thrun CS223B Computer Vision, Winter 2005 20 Example 4: Classification http://elib.cs.berkeley.edu/photos/classify/
22
Sebastian Thrun CS223B Computer Vision, Winter 2005 21 Example 5: Detection and Tracking http://www.seeingmachines.com/facelab.htm
23
Sebastian Thrun CS223B Computer Vision, Winter 2005 22 Example 6: Optical Flow David Stavens, Andrew Lookingbill, David Lieb, CS223b Winter 2004
24
Sebastian Thrun CS223B Computer Vision, Winter 2005 23 Example 7: Learning Andrew Lookingbill, David Lieb, CS223b Winter 2004 Demo: Dirt Road
25
Sebastian Thrun CS223B Computer Vision, Winter 2005 24 Example 8: Human Vision
26
Sebastian Thrun CS223B Computer Vision, Winter 2005 25 Example 8: Human Vision
27
Sebastian Thrun CS223B Computer Vision, Winter 2005 26 Excited Yet?
28
Sebastian Thrun CS223B Computer Vision, Winter 2005 27 Computer Vision [ Trucco&Verri’98]
29
Sebastian Thrun CS223B Computer Vision, Winter 2005 28 Today’s Goals Learn about CS223b Get Excited about Computer Vision Learn about image formation (tbc)
30
Sebastian Thrun CS223B Computer Vision, Winter 2005 29 Topics Pinhole Camera Orthographic Projection Perspective Camera Model Weak-Perspective Camera Model
31
Sebastian Thrun CS223B Computer Vision, Winter 2005 30 Pinhole Camera *many slides in this lecture from Marc Pollefeys comp256, Lect 2 -- Brunelleschi, XVth Century
32
Sebastian Thrun CS223B Computer Vision, Winter 2005 31 Perspective Projection A “similar triangle’s” approach to vision. Notes 1.1 Marc Pollefeys
33
Sebastian Thrun CS223B Computer Vision, Winter 2005 32 Perspective Projection x fZ X O -x
34
Sebastian Thrun CS223B Computer Vision, Winter 2005 33 Consequences: Parallel lines meet There exist vanishing points Marc Pollefeys
35
Sebastian Thrun CS223B Computer Vision, Winter 2005 34 Vanishing points VPL VPR H VP 1 VP 2 VP 3 Different directions correspond to different vanishing points Marc Pollefeys
36
Sebastian Thrun CS223B Computer Vision, Winter 2005 35 The Effect of Perspective
37
Sebastian Thrun CS223B Computer Vision, Winter 2005 36 Implications For Perception* * A Cartoon Epistemology: http://cns-alumni.bu.edu/~slehar/cartoonepist/cartoonepist.html Same size things get smaller, we hardly notice… Parallel lines meet at a point…
38
Sebastian Thrun CS223B Computer Vision, Winter 2005 37 Perspective Projection fZ X O -x
39
Sebastian Thrun CS223B Computer Vision, Winter 2005 38 Weak Perspective Projection f Z O -x Z Z
40
Sebastian Thrun CS223B Computer Vision, Winter 2005 39 Generalization of Orthographic Projection When the camera is at a (roughly constant) distance from the scene, take m=1. Marc Pollefeys
41
Sebastian Thrun CS223B Computer Vision, Winter 2005 40 Pictorial Comparison Weak perspective Perspective Marc Pollefeys
42
Sebastian Thrun CS223B Computer Vision, Winter 2005 41 Summary: Perspective Laws 1.Perspective 2.Weak perspective 3.Orthographic
43
Sebastian Thrun CS223B Computer Vision, Winter 2005 42 Limits for pinhole cameras
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.