This is a tentative schedule and subject to change.

Date Lecture Description Readings Assignments Materials
9/9 Introduction.      Lecture 1 slides
9/11 Introduction continues.

What is vision good for? Why is it hard?  Why is it interesting? How do you pose the problem computationally?

 

 Reading: Ch 1.1

Lecture 2 slides

 

9/14 Continuing Introduction.  

Reading: Ch 3.2.1 (linear filtering).

Background: 2.3.1, 3.3

Assignment 1 p1 p2 out

Lecture 3 slides

Ball and Shadow movie

Illusory motion from shadows

9/16

Case study - object recognition.

 

Reading: 3.4.1, 3.4.2

Lecture 4 slides

9/18

Finish intro and case study.

Start linear filtering.

 

Lecture 5 slides

Linear algebra tutorial slides

Matlab tutorial code

9/21

Convolution and linear filtering.

    Lecture 6 slides
9/23

Filtering and Gaussian pyramids

 

Lecture 7 slides

Matlab code - Gaussian smoothing

 

9/25

Edges, derivatives and Laplacian pyramid

 

Asgn1 all out

Lecture 8 slides

Matlab code - edges

Matlabcode - derivatives of Gaussians

9/28

Deqing Sun: Gradients, filtering and features (needed for Assignment 1)

 

Asgn1 - p1 and p2 Due

Handin name:

asgn1_p1_p2
Lecture 9 slides
9/30

Tim St Claire: data collection for assignment 2 - please attend. If you miss this, assignment 2 won't be as fun.

     
10/2

Guest Lecture: Silvia Zuffi, Color constancy and the Retinex Model

     
10/5 Images as vectors.  Appearance-based models

Asgn1 all Due (You can only handin p3 and p4)

Hand-in name: asgn1all

 

Lecture 10 slides

 

10/7 Covariance and PCA  

 

Lecture 11 slides

 

10/9 PCA and SVD Lecture 12 slides
10/12 Columbus Day, No class      
10/14 PCA and faces.    Asgn2 p1 p2 out

 

Lecture 13 slides

 

10/16

Finish PCA applications.

Review of basic probability.

Multivariate Gaussians, covariance, probability.

 

 

Lecture 14 slides
10/19

 

Finish multivariate Gaussians and PCA

 

Moghaddam and Pentland Lecture 15 slides
10/21

Finish covariance, start motion

 Lecture 16 slides

 

Asgn2 p1, p2 due

Hand-in name:

asgn2_p1_p2

10/23

Motion intro. Assumptions, formalization, Sum of Squared Differences.

 

 

Lecture 17 slides

 

10/26

 

Motion estimation. Aperture problem, optical flow constraint equation, optimization, least squares.

 

 

 

 

Lecture 18 slides
10/28

 

Motion illusions and affine motion

  Asgn3 out Lecture 19 slides
10/30

Computing affine motion

Incremental warping and coarse to fine.

 

Lecture 20 slides 
11/2

 

Cameras and projection

 

   

Lecture 21 slides
11/3    

Assignment 3, p1 and p2 due 11am

Hand-in name:

asgn3_p1_p2

 
11/4

Robust estimation,

Non-linear optimization

Initial project discussion

 

Lecture 22 slides

11/6

More on projects

Non-linear optimiation

Robust regularization

 

Project handout

Bring project ideas to class

Project ideas slides

11/9

 

Regularization and Dense optical flow

 

 

Assignment 3, All problems due 11am

Hand-in name: asgn3all  

Assignment 4 out

Lecture 23 slides

11/11 Dense flow  

 

Lecture 24 slides
11/13

 

Start Tracking

 

 

Project proposals Due

Hand-in name: proposal

Lecture 25 slides
11/16

 

Particle filtering

 

 

Assignment 4, problem 1 due

Hand-in name:

asgn4_p1

Lecture 26 slides
11/18

 

Stereo

 

 

 

Lecture 27 slides
11/20

 

Finish stereo and start object recognition

 

  Lecture 28 slides
11/23

 

Object recognition

 

Assignment 4, all problems due

Hand-in name:

asgn4_all

Lecture 29 slides
11/25

 

Thanksgiving recess. No class

 

   
11/27

 

Thanksgiving recess. No class

 

   
11/30 Object recognition     Lecture 30 slides
12/2 Finish object recognition and concusions     Lecture 31 slides
12/4

No class

That there are known knowns,
There are things we know that we know,
There are known unknowns,
That is to say there are things that we now know, we don't know
But there are also unknown unknowns,
There are things we do not know we don't know
And each year we discover a few more
Of those unknown unknowns.

D. Rumsfeld.

     
12/7 Reading week. No class.      
12/9 Reading week. No class      
12/11 Reading week. No class      
12/16 note new date  

Projects due.
Hand-in name: proj