ETH Zurich - D-INFK - IVC - CVG - Lectures - Computer Vision

Computer Vision


Instructors: Marc Pollefeys, Luc Van Gool
Teaching assistants: Marc Pollefeys's part:
Federico Camposeco, Pablo Speciale, Nikolay Savinov.

Luc Van Gool's part:
Assignment 7: Corin Otesteanu
Assignment 8: Firat Oezdemir
Assignment 9: Yuhua Chen
Assignment 10: Taha Sabri Koltukluoglu
Lectures: Wednesdays from 13:15-16:00 in CHN C 14
Exercises: Thursdays from 14:15-15:00 in NO D 11
Exercises: Thursdays from 15:15-16:00 in HG G 26.1

Computer Vision (following Tomaso Poggio, MIT): Computer Vision, formerly an almost esoteric corner of research and regarded as a field of research still in its infancy, has emerged to a key discipline in computer science. Vision companies have emerged and commercial applications become available, ranging from industrial inspection and measurements to security database search, surveillance, multimedia and computer interfaces. Computer Vision is still far from being a solved problem, and most exciting developments, discoveries and applications still lie ahead of us. Understanding the principles of vision has implications far beyond engineering, since visual perception is one of the key modules of human intelligence.

Course Objectives

The objectives of this course are:
1.To introduce the fundamental problems of computer vision.
2.To introduce the main concepts and techniques used to solve those.
3.To enable participants to implement solutions for reasonably complex problems.
4.To enable participants to make sense of the computer vision literature.

Course Topics

Camera models and calibration, invariant features, Multiple-view geometry, Model fitting, Stereo Matching, Segmentation, 2D Shape matching, Shape from Silhouettes, Optical flow, Structure from motion, Tracking, Object recognition, Object category recognition

Target Audience

The target audience of this course are Master students, that are interested to get a basic understanding of computer vision.

Requirements

Fundamentals of calculus and linear algebra, basic concepts of algorithms and data structures, basic programming skills in Matlab and C.

Some useful links

The Computer Vision Homepage
CVonline
Middlebury Stereo Vision Page
VLFeat SIFT package for MATLAB
STUD-IDES
Course Notes
Computer Vision: Algorithms and Applications

Lecture Slides

Introduction and geometry[pdf]
Camera models and calibration[pdf]
Feature extraction[pdf]
Multiple view geometry[pdf]
Model fitting[pdf]
Stereo Matching[pdf]
Image Segmentation[pdf]
Specific object recognition[pdf]
Object category recognition[pdf]
Motion extraction[pdf]
Tracking[pdf]
SfM and SfS[pdf]

Exercises

Assignment 1[pdf][slides][code]
Assignment 2[pdf][slides][code]
Assignment 3[pdf][slides][code]
Assignment 4[pdf][slides][code]
Assignment 5[pdf][slides][code]
Assignment 6[pdf][slides][code]
Assignment 7 (labeled 10 in the pdf)[pdf][slides][code][data]
Assignment 8[pdf][slides][code][data][paper]
Assignment 9[pdf][slides][code][data]
Assignment 10[pdf][slides][code][data]

Important: how to submit exercises

Put all your files (report, code, images) in a zip named "CV15_ETHID_LastName.zip".
Where ETHID is your student id found on your student card (eg. 14-999-999).
Then email it to the Teaching Assistant with subject "[CV15] Assignment 37" (replace "37" with the actual assignment number).


FAQ:


Q0: I cannot send the assignment by email (files are too large/eth email client does not work). Can I use a file-sharing service Dropbox/eth box/anything else?
A: Of course. Just make sure your assignment stays there until the end of the term. The only requirement would be to use a service which has a "last modified" time stamp. Dropbox has such a time stamp, for example.
Q1: I am re-taking Computer Vision class. Can you transfer exercise grades from the previous time?
A: Please write directly to the TA responsible for the particular assignment INSTEAD of sending the assignment one more time. If the exercises did not change, the score will be transferred.
Q2: My code is correct, it just happens it does not run. Can you grade it?
A: No, please make sure it runs in other environment before sending. We will only grade working code.
Q3: My code is correct, but I did not write the report. Can you grade the assignment?
A: No, you should write the report.


© CVG, ETH Zürich lm@inf.ethz.ch