Computer Vision

Fall 2008

 

Please note - specifics of this schedule are subject to change.

 

F&P = Forsyth & Ponce

S&S = Shapiro & Stockman [See Blackboard-> Course Documents]

T&V = Trucco & Verri [See Blackboard-> Course Documents]

 

Dates

Topic

Reading and references

Of related interest

Lectures

Assignments

8/28

 

 

9/2

 

 

 

 

 

 

 

 

9/4

Intro

 

 

Matlab tutorial

 

Image formation

 

 

 

 

 

 

Color

 

 

 

 

 

 

 

 

Matlab intro

 

F&P Chapter 1

 

 

 

 

 

 

F&P Chapter 6

 

 

 

 

 

 

 

Who Invented Ray Tracing? By G. Hofmann

 

Building a camera with a Pringles can

 

The foundations of color measurement and color perception by Brian A. Wandell

 

Lottolab illusions

 

After image effect

 

pdf-handout  ppt

 

 

 

 

pdf-handout  ppt

 

 

 

 

 

 

pdf-handout  ppt

 

misc Matlab notes

Pset 0

Pset 0 images

 

 

 

Pset 0 due 9/4

 

 

 

 

 

 

Pset 1

Pset 1 images

video on seam carving

9/9

 

 

 

 

 

 

 

9/11

 

 

 

9/16

 

 

 

9/18

Features and texture

Linear filters : Part 1

 

F&P Chapter 7 sections 7.1, 7.2, 7.5, 7.6

[T&V Chapter 4]

[S&S Chapter 3]

 

Linear filters : Part 2

Edges :

F&P Chapter 8.

 

Binary image analysis :

 [S&S Chapter 5]

 

Texture : F&P Sections 9.1, 9.3

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Texture Synthesis by Non-parametric Sampling, Efros & Leung, ICCV 1999

 

Filter bank code from Oxford Visual Geometry Group

pdf-handout   ppt

 

 

 

 

 

 

 

pdf-handout   ppt

 

 

 

pdf-handout   ppt

 

 

 

pdf-handout   ppt

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Pset 1 due 9/22

9/23

 

 

9/25

 

 

 

 

 

 

9/30

 

 

 

10/2

 

 

 

 

10/7

 

 

 

 

10/9

 

 

Grouping and fitting

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Fitting & multiple views

Segmentation: F&P Chapter 14

 

Hough Transform: F&P Section 15.1

 

[S&S pp. 304-310]

Excerpt from Ballard & Brown

 

Background models and Bayesian classifiers

 

No class Thursday

 

 

 

 

Deformable contours:

[T&V p. 108-113]

[S&S p. 489-495]

 

 

Alignment & warping

 

RANSAC and robust fitting: F&P Section 15.5, 15.5.2

 

K-means demo

 

 

Hough Transform demo

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Notes on Snakes by Vera Kettnaker

 

pdf-handout   ppt

 

 

pdf-handout   ppt

 

 

 

 

 

 

pdf-handout

 

 

 

 

 

 

 

 

pdf-handout   ppt

 

 

 

 

pdf-handout   ppt

 

 

 

 

 

 

 

 

 

 

 

 

 

Pset 2 out 10/2;

Download Pset 2 images from Blackboardà Assignments

 

 

 

10/14

Midterm

Exam in class

 

 

 

10/16

 

 

10/21

 

 

 

 

 

10/23

 

 

 

 

10/28

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Multiple views

 

Midterm solutions, mosaics review

 

Epipolar geometry and stereo vision

F&P 10.1.1-10.1.2

F&P 11.1-11.3

[T&V Chapter 7]

 

Calibration, weak calibration

F&P 10.1.4-5, 3.2

 

 

Local invariant features: detection and description

 

Distinctive Image Features from Scale-Invariant Keypoints, David Lowe, IJCV 2004.

 

 

 

 

 

 

Applet on epipolar geometry

 

 

 

 

 

 

 

 

 

SIFT demo software from David Lowe

 

Local Invariant Feature Detectors: A Survey, T. Tuytelaars and K. Mikolajczyk, 2008.

 

Oxford group’s software for interest point detection and descriptors

pdf-handout   ppt

 

 

pdf-handout   ppt

 

 

 

pdf-handout   ppt

 

 

 

 

 

 

pdf-handout   ppt

 

 

 

Pset 2 due 10/21

 

 

 

 

 

 

 

 

 

 

Pset 3 out 10/28

*Access data and provided code at /v/filer4b/v26q003/

pset3data.

Note: do not copy or download the data; you can use it directly by pointing to the files in your code.

10/30

 

 

 

 

 

 

 

 

 

 

 

 

 

 

11/4

 

 

 

 

 

 

 

11/6

 

 

 

 

 

 

 

 

 

 


11/11

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

11/13

 

11/18

Recognition and image retrieval

Indexing with bags of words models

 

[Blackboard]: excerpt on information retrieval

 

Video Google: A Text Retrieval Approach to Object Matching in Videos, by J. Sivic and A. Zisserman, 2003.

 

 

Recognition overview,

 

Alignment-based recognition, pose clustering

F&P 18.1, 18.3, 18.5

 

 

Appearance-based recognition and detection

F&P 22.1-22.3, 22.5

 

 

 

 

 

 

 

 

Appearance-based recognition and detection, classifiers

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Part-based models

 

 

Shape matching

Oxford Visual Geometry Group demo of Video Google system

 

 

 

 

 

 

 

 

 

 

 

astrometry.net

 

AAAI 2008 tutorial on recognition

 

 

 

Rapid Object Detection using a Boosted Cascade of Simple Features, by P. Viola and M. Jones, 2001.

 

OpenCV Library, includes code for Viola-Jones face detector

 

Automated Visual Recognition of Individual African Penguins, by Burghardt et al., 2004.

 

LIBSVM: code for support vector machines

 

Learning Gender with Support Faces, by B. Moghaddam and M. Yang.  TPAMI 2002, F&G 2000

 

Histograms of Oriented Gradients for Human Detection, Dalal & Triggs, CVPR 2005

 

 

 

 

Learning Silhouette Features for Control of Human Motion

 

Breaking a Visual Captcha, Mori & Malik.

pdf-handout   ppt

 

 

 

 

 

 

 

 

 

 

 

 

 

 

pdf-handout   ppt

 

 

 

 

 

 

pdf-handout   ppt

 

 

 

 

 

 

 

 

 

 

 

pdf-handout   ppt

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

pdf-handout   ppt

 

 

pdf-handout   ppt

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Pset 3 due 11/11

 

 

 

 

 

 

 

 

11/20

 

 

 

 

11/25

 

 

 

11/27

 

 

12/2

 

 

 

 

 

 

 

 

12/4

Motion & tracking

Motion, optical flow

[Blackboard]: Horn Ch. 12, S&S Ch. 9

 

 

Tracking, linear dynamic models

F&P Chapter 17

 

Thanksgiving

 

 

Tracking continued

 

 

 

 

 

 

 

 

Course review and exam prep.

 

 

 

 

 

 

 

 

 

 

 

 

Infrared thermal video analysis of bats, Betke et al.

 

Tracking People By Learning Their Appearance, Ramanan et al.

 

pdf-handout   ppt

 

 

 

 

pdf-handout   ppt

 

 

 

 

 

 

pdf-handout   ppt

 

 

 

 

 

Pset 4 out 11/25

(100 points for part A alone; part B is extra credit)

 

 

 

 

 

 

 

 

 

 

 

 

Pset 4 due 12/4

with automatic extension to 12/9 if needed.

12/13 Sat

Final exam 7-10 PM