BIL 719 - Computer Vision (Spring 2012)

Lectures: Friday 13:30-16:30 @D5


Sailing Island (Courtesy of Rob Gonsalves)

Instructor: Aykut Erdem

e-mail: aykut-at-cs.hacettepe.edu.tr

Office: 111

Tel: 297 7500 / 146

Office hours: Tuesday, 13:00-15:00


Course Description:

This course provides a thorough understanding of the fundamental concepts in 2D and 3D computer vision for graduate students. The main objective is to provide an insight to the general understanding of what does it mean to see, and how this can help us to come up with machine vision systems. In this context, the course provides an introduction to a number of fundamental topics in computer vision, and make the students gain a sense of the accomplishments in the area.


Prerequisites:

Students should have good math background (Calculus, Linear Algebra, Statistical Methods) and programming skills (MATLAB, C/C++)


Course Content:

The topics studied in this course will include:


Course Material:

Grading Policy:

Problem Sets:

There will be at least four assignments related to the topics covered in the class. Each assignment will involve implementing an algorithm, carrying out a set of experiments to evaluate it, and writing up a report on the experimental results. There will also be some warm-up and reading assignments. All assignments have to be done individually, unless stated otherwise.


Project:

In addition to the assignments given throughout the semester, the students taking the course will be required to do a project in computer vision. Students can choose to work individually or in groups of at most 2 people.

This project may be

For a detailed description of the course project, follow this link.

On March 23rd, there will be a special brainstorming session on project previews. For that, each project team should prepare a brief (3-5 min.) presentation on their specific project idea. Each presentation should introduce the study which is expected to form the basis of the project; or should introduce the research topic to be reviewed, including a list of major papers on that specific area.

A project proposal not longer than two pages must be submitted and approved by April 6th.

The final reports must be between 8-10 pages and submitted by May 27th. In preparing your project reports, you should use the provided template and submit them electronically in PDF format.

Course Schedule:


Lecture  

Date  

Topic  

Additional Reading  

Assignments


1

17/02  

Introduction to the course [slides]
Supplemental readings:

­­­­­­

 

2

24/02  

Image formation, the eye, color, linear filters, gradients, edges [slides]  

PSet 0 out
starter code, data

02/03  

No class

3

09/03  

Frequency domain, texture, image pyramids and scale space [slides]  

­­­­­­

PSet 0 due
PSet 1 out
sample images and starter code

4

16/03  

Fitting, RANSAC, the Hough transform [slides]  

5

23/03  

Segmentation I [slides]

PSet 1 due

6

30/03

Segmentation II [slides]

PSet 2 out
starter code

7

06/04

Cameras, projections and calibration [slides]

Project proposals due

8

13/04

Single-view geometry, epipolar geometry, binocular stereo and structure from motion [slides]
Supplemental readings:

20/04  

No class

PSet 2 due

9

27/04

Local image features, optical flow, motion segmentation and tracking [slides]
Supplemental readings:

10

11/05

Introduction to recognition, instance-level recognition, bag of visual words, generic object recognition and classifiers [slides]
Supplemental readings:

11

19/05

Detection with sliding windows and parts-based models, context and spatial layout [slides]
Supplemental readings:



Resources:


Communication:

The course webpage will be updated regularly throughout the semester with lecture notes, programming and reading assignments and important deadlines. All other communications will be carried out through Piazza. Please enroll it by following the link https://piazza.com/hacettepe.edu.tr/spring2012/bil719