CMPSCI 670: Computer Vision, Fall 2014
 Key to Dreams, René Magritte |
Instructor: Subhransu Maji Graders: Ryan Szeto, Tung (Steven) Pham |
Overview
This course will explore current techniques for the analysis of visual data (primarily color images). In the first part of the course we will examine the physics and geometry of image formation, including the design of cameras and the study of color sensing in the human eye. In each case we will look at the underlying mathematical models for these phenomena. In the second part of the course we will focus on algorithms to extract useful information from images. This includes detection of reliable interest points for applications such as image alignment, stereo and instance recognition; robust representations of images for recognition; and principles for grouping and segmentation. Time permitting we will look at some additional topics at the end of the course.
Course assignments will highlight several computer vision tasks and methods. For each task you will construct a basic system, then improve it through a cycle of error analysis and model redesign. There will also be a final project, which will investigate a single topic or application in greater depth. This course assumes a good background in basic probability, linear algebra, and ability to program in MATLAB. Prior experience in signal/image processing is useful but not required.
Textbooks (recommended)
- Computer Vision: A Modern Approach by David Forsyth and Jean Ponce (2nd ed.)
- Computer Vision: Algorithms and Applications by Richard Szeliski (pdf available online)
Announcements
- 12/22/14 Grades posted.
- 12/10/14 Final report due at 11:55 pm, Monday (December 15) via email.
- 12/02/14 We will meet on Thursday (12/4) at 5:30pm, CS 142 to wrap up the project presentations. There will be pizza!
- 12/01/14 Slides for 11/26 lecture on optical flow posted (class was cancelled due to snow storm)
- 11/17/14 Guest lecture by Aditya Khosla on Wednesday on "Crafting the Perfect Selfie using Computer Vision"
- 11/17/14 Homework 4 grades posted.
- 11/11/14 Office hours this week are at Thursday 3:45-4:35, CS 274
- 11/05/14 Homework 3 grades posted.
- 11/05/14 Homework 5 posted.
- 11/03/14 Office hours this week are at Monday 3:45-4:35, CS 274
- 10/22/14 Homework 4 posted.
- 10/22/14 Office hours this week are at Thursday 2:30-3:30, CS 274
- 10/19/14 Homework 2 grades posted.
- 10/19/14 Homework 3 deadline extended to Wednesday, Oct 22.
- 10/14/14 Final project guidelines posted.
- 10/08/14 Office hours this week are at Thursday 3:45-4:35, CS 274
- 10/07/14 Homework 1 grades posted.
- 10/06/14 Homework 3 posted.
- 09/28/14 There was a bug in the initial code for HW2. Download the latest code.zip from the homework page.
- 09/24/14 Homework 2 posted.
- 09/24/14 Office hours this week are at Thursday 3:45-4:35, CS 274
- 09/17/14 Instructions for HW1 submission posted on the homework page.
- 09/11/14 Make sure you can log in to your edLab accounts. Homeworks will be collected and tested via edLab.
- 09/11/14 Further readings for each lecture can be found in the last slide of each lecture.
- 09/08/14 Homework 1 posted.
- 09/03/14 Office hours this week are at Thursday 3:45-4:35, CS 274
- 08/21/14 Tentative course outline posted.
Schedule
| Week | Date | Topic | Links | Homework (out) | Homework (due) |
| 1 | Sep 3 | Course introduction [pdf, key] | MATLAB tutorial and setup | ||
| 2 | Sep 8 | Image formation [pdf, key] | Edlab resources | HW1: Color images | |
| Sep 10 | Cameras [pdf, key] | ||||
| 3 | Sep 15 | Color [pdf, key] | |||
| Sep 17 | Light and shading [pdf, key] | ||||
| 4 | Sep 22 | Linear filtering [pdf, key] | |||
| Sep 24 | Edge detection [pdf, key] | HW2: Photometric stereo | HW1 due | ||
| 5 | Sep 29 | Corner detection [pdf, key] | |||
| Oct 1 | Blob detection [pdf, key] | ||||
| 6 | Oct 6 | Texture [pdf, key] | HW3: Blob detection | HW2 due | |
| Oct 8 | Texture continued [pdf, key] | ||||
| 7 | Oct 13 | No class (Columbus day) | |||
| Oct 14 | Grouping [pdf, key] | FP guidelines | |||
| Oct 15 | Grouping continued [pdf, key] | ||||
| 8 | Oct 20 | Alignment [pdf, key] | |||
| Oct 22 | Alignment continued [pdf, key] | HW4: Grouping | HW3 due | ||
| 9 | Oct 27 | Recognition introduction [pdf, key] | Abstracts due | ||
| Oct 29 | Machine learning introduction [pdf, key] | ||||
| 10 | Nov 3 | Image representation [pdf, key] | |||
| Nov 5 | Object detection [pdf, key] | HW5: Recognition | HW4 due | ||
| 11 | Nov 10 | Object detection continued [pdf, key] | |||
| Nov 12 | No class (post Veteran's day. Tuesday class schedule will be followed) | ||||
| 12 | Nov 17 | Deep learning [pdf,key] | |||
| Nov 19 | Guest lecture: Aditya Khosla, MIT | Title: Crafting the Perfect Selfie using Computer Vision [pdf,pptx] | HW5 due | ||
| 13 | Nov 24 | Human-centric computer vision [pdf,key] | |||
| Nov 26 | Optical flow and tracking [pdf,key] | Class cancelled due to snow | |||
| 14 | Dec 1 | Project presentations | |||
| Dec 3 | Project presentations continued | ||||
| Dec |
Final report due | ||||