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 |
||
9/16 | Case study - object recognition. |
Reading: 3.4.1, 3.4.2 |
||
9/18 | Finish intro and case study. Start linear filtering. |
|||
9/21 | Convolution and linear filtering. |
Lecture 6 slides | ||
9/23 | Filtering and Gaussian pyramids |
Matlab code - Gaussian smoothing
|
||
9/25 | Edges, derivatives and Laplacian pyramid |
|||
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 |
|
|
10/7 | Covariance and PCA |
|
||
10/9 | PCA and SVD | Lecture 12 slides | ||
10/12 | Columbus Day, No class | |||
10/14 | PCA and faces. | Asgn2 p1 p2 out |
|
|
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 |
|||
Asgn2 p1, p2 due
Hand-in name: asgn2_p1_p2 |
||||
10/23 | Motion intro. Assumptions, formalization, Sum of Squared Differences. |
|
||
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 |
|
||
11/6 | More on projects Non-linear optimiation Robust regularization |
Bring project ideas to class |
||
11/9 |
Regularization and Dense optical flow
|
Assignment 3, All problems due 11am Hand-in name: asgn3all |
||
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, 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. |