Title: Stanford CS223B Computer Vision, Winter 2006 Lecture 1 Intro and Image Formation
1Stanford 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)
2Todays Goals
- Learn about CS223b
- Get Excited about Computer Vision
- Learn about Image Formation (Part 1)
3Administrativa
- Time and Location
- Mon/Wed 1100-1220, McCullough 115
- SCPD Televised
- Web site
- http//cs223b.stanford.edu
4People 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
5Guest Lecturers
6Goals
- 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!
7Course 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
8Course 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
9Course Overview
10The Text
11The Class Competition
- No Major Project
- Instead A competition
12The Competition Motivation
13Implications
- Why not run a competition in CS223b?
14The 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)
15The Competition, Example
This is not the real data. Well collect the data
with Stanley
16Todays Goals
- Learn about CS223b
- Get Excited about Computer Vision
- Learn about image formation (Part 1)
17Computer Graphics
Output
Image
Model
Synthetic Camera
(slides courtesy of Michael Cohen)
18Computer Vision
Output
Model
Real Scene
Real Cameras
(slides courtesy of Michael Cohen)
19Combined
Output
Image
Real Scene
Model
Synthetic Camera
Real Cameras
(slides courtesy of Michael Cohen)
20Example 1Stereo
See http//schwehr.org/photoRealVR/example.html
21Example 2 Structure From Motion
http//medic.rad.jhmi.edu/pbazin/perso/Research/Sf
Mvideo.html
22Example 3 3D Modeling
http//www.photogrammetry.ethz.ch/research/cause/3
dreconstruction3.html
23Example 4 3D Modeling
Drago Anguelov
24Example 4 3D Modeling
25Example 4 3D Modeling
26Example 5 Segmentation
http//elib.cs.berkeley.edu/photos/classify/
27Example 6 Classification
28Example 6 Classification
29Example 7 Optical Flow
Demo Dirt Road
Andrew Lookingbill, David Lieb, CS223b Winter 2004
30Example 8 Detection
David Stavens, Andrew Lookingbill, David Lieb,
CS223b Winter 2004
31Example 9 Tracking
http//www.seeingmachines.com/facelab.htm
32Example 10 Human Vision
33Example 9 Human Vision
34Excited Yet?
35Todays Goals
- Learn about CS223b
- Get Excited about Computer Vision
- Learn about image formation (Part 1)
36Topics
- Pinhole Camera
- Orthographic Projection
- Perspective Camera Model
- Weak-Perspective Camera Model
37Pinhole Camera
-- Brunelleschi, XVth Century
many slides in this lecture from Marc Pollefeys
comp256, Lect 2
38Perspective Projection
A similar triangles approach to vision.
Marc Pollefeys
39Perspective Projection
O
X
-x
f
f
Z
40Consequences Parallel lines meet
- There exist vanishing points
Marc Pollefeys
41The Effect of Perspective
42Vanishing points
VPL
H
VPR
VP2
VP1
Different directions correspond to different
vanishing points
VP3
Marc Pollefeys
43Implications 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
44Perspective Projection
O
X
-x
f
Z
45Weak Perspective Projection
Z
O
-x
Z
f
Z
46Generalization of Orthographic Projection
When the camera is at a (roughly constant)
distance from the scene, take m1.
Marc Pollefeys
47Pictorial Comparison
Weak perspective
Perspective
?
Marc Pollefeys
48Summary Perspective Laws
- Perspective
- Weak perspective
- Orthographic
49Limits for pinhole cameras