Göm meny

TSBB15 Computer Vision VT2016 (last year's course)

This course is worth 12 ECTS credits, which corresponds to approximately 320h of work per student. The time is divided among the following activities:

The course is given during the VT1 and VT2 periods. Note that not all the time slots in the course schedule will be used. A few spare slots have been reserved in case a lecture has to be moved. The actually planned lectures are listed below on this page, and any changes to this plan will be announced during the lectures, and on this page.

People

We all have our offices in the B-building, ground floor, corridor A, between entrances 27 and 29.

Documents

Literature

Other topics covered in the course, such as background models are missing from these two. For side reading on other topics, we have collected pointers to relevant literature in the column "Material" in the "Lecture and Lab schedule" below.

Registration

If you intend to take the course but are not registered, make sure to register ASAP, using the Student portal. You need to be registered on the course to receive course email, and to have results input to Ladok. If you take the course but are not registered to any program at Linköping University, please contact the course examiner in order to make sure that you receive email about the course.

Examination

The course has a written examination which is offered at three occations during 2016:
  • 2016-03-23, 14-18: Re-examination opportunity for last year's students, and voluntary mid-term examination for this years's students.
  • 2016-06-01, 14-18: Examination at end of course.
  • 2016-08-16, 14-18: Re-examination opportunity.

Old exams

The exams from 2012 and 2013 in TSBB15 can be found here. Still older exams from the courses TS1017 and TSBB12 can be found here. These two courses covered similar theory as this course.
We recommend that you use these exams as pointers into the literature ("instuderingsfrågor"). To answer the exam, read corresponding discussions in your notes, the course book, and the lecture slides. While it is faster to look at other people's exam answers, this merely gives you answers, while reading and thinking also results in understanding.

Grades

How to pass the course, and the grading criteria are described here.

Lecture and lab schedule VT1 2016 (last year's course)

These are the dates and slides from 2016.

Date,Time,Room Activity Teacher Material
Jan 19: 10.15-12
BL34
 Lecture 1
What is Computer Vision?
 Per-Erik
Jan 20: 8.15-10
BL34
 Lecture 2
Image Representations
 Klas
Jan 21: 13.15-17
OLYM
Computer lessons 1&2
Images in Matlab 		Kristoffer
Jan 26: 10.15-12
BL33
 Lecture 3
Orientation 		Klas
Jan 27: 8.15-10
BL34
 Lecture 4
Motion estimation, optical flow, 3D structure tensor 		Klas
  • CVAA: 8.1 Alignment
Jan 28: 13.15-15
P34
 Lecture 5
Optical flow, tracking 		Klas
Feb 2: 10.15-12
BL33 		Lecture 6
Clustering and learning 		Per-Erik
Feb 3: 8.15-10
BL33
 Lecture 7
Overview of project 1: Tracking
 Klas
Feb 4: 13.15-17
OLYM
 Computer exercise 1
Tracking 		Martin, Tommaso
Feb 10: 8.15-10
BL33 		Lecture 8
Invariant Features 		Per-Erik
Feb 11: 13.15-17
OLYM 		Computer exercise 2
Motion 		Martin, Tommaso
Feb 16: 10.15-12
BL34
 Lecture 9
Biological Vision 		Per-Erik

Lecture and lab schedule VT2 2016 (last year's course)

These are the dates and slides from 2016.

Date,Time,Room Activity Teacher Material
Apr 5: 13.15-17
P18
 Seminar 1
Presentation of project 1 		Per-Erik Forssén
Apr 6: 10.15-12
P18
 Lecture 10
Gold Standard, PnP, Calibrated epipolar geometry. 		Klas Nordberg
  • IREG: 8.2.7 (cameras from F)
  • IREG: 10.6 (ML-estimation)
  • IREG: 14.1.3 (opt. triangulation)
  • IREG: 14.2.4 (gold standard est. of F)
  • CVAA: 6.1.4
  • HZ: 4.7, 11.4
Apr 8: 8.15-10
BL33
 Lecture 11
Robust estimation and RANSAC 		Klas Nordberg
  • IREG: 8.5 including at least 8.5.4. (calib. epip. geom.)
  • IREG: 13.4 (PnP)
  • IREG: 14.3 (est. of E)
  • IREG: Chapter 15, in particular 15.3, 15.4 and 15.5.2. (robust est. and RANSAC)
  • CVAA: 7.2, 7.2.1
  • HZ: 9.6
Apr 12: 13.15-15
BL31
 Lecture 12
SfM, BA, Proj. 2
Klas Nordberg
  • IREG: Chapter 18 (SfM)
  • CVAA: 7.4
Apr 13: 10.15-12
BL31
 Lecture 13
Optimization 		Michael Felsberg
Apr 19: 13.15-17
OLYM
 Computer Exercise 3
Optimisation 		Hannes, Giulia
Apr 20: 10.15-12
P34
 Lecture 14
Image Enhancement 		Klas Nordberg
Apr 22: 8.15-10
BL31
 Lecture 15
Variational Methods 		Michael Felsberg
Apr 26: 13.15-17
OLYM
 Computer Exercise 4
Image Restoration 		Martin, Tommaso
May 11: 10.15-12
BL33
moved from May 4 		Guest Lecture 1
Leif Haglund, Vricon
May 24: 13.15-17
P30
 Seminar 2
Presentation of project 2 		Per-Erik Forssén
May 25: 10.15-12
BL33
 Guest Lecture 2
Ola Friman, SICK-IVP

Projects

List of project groups VT2016

The projects are conducted in groups of 4,5 or 3 students (in order of preference).

  • Project 1: Tracking
    Introductory lecture on Feb 3
    Design plan due Feb 12
    Report due Mar 22
    Presentation seminar on Apr 5
  • Project 2: 3D Reconstruction
    Introductory lecture on April 12
    Design plan due April 19
    Report due May 20
    Presentation seminar on May 24

General resources

We suggest and allow you to use the following software:

  • OpenCV (Open Source Computer Vision). Version 2.4.2 will be installed on the department's Linux computers. See also the minimal example OpenCV progam (contributed by Gustav Häger).
    Read the section on OpenCV in the hints and pitfalls page. There is a cheat sheet for OpenCV. An important exception is the Background modelling with mixtures of Gaussians, which you are NOT allowed to use (as you're supposed to learn this in the course).
  • David Lowe's SIFT implementation for Matlab. This includes binary executables that are compiled into mex-code that runs from Matlab. If you don't know about Matlab mex-files ask your guide.
  • VLFeat has a a useful code library, both for Matlab and C/C++.  For example, there is an alternative implementation of SIFT here, and also an implementation of MSER here. Both are made by Andrea Vedaldi.
  • The Visual Geometry Group at Oxford University maintains code for affine invariant region detectors, produced in cooperation with other groups.
  • The Computer Vision Laboratory at ETH provides an implementation of SURF.

Subversion

Each project group will have access to a part of a Subversion repository, with individual login by each project member.

Documentation for Subversion can be found here:

If you are using a Windows based computer, we recommend that you use the Tortoise client for Subversion. We also recommend that you look at the section on Subversion in the hints and pitfalls page.

Hints and pitfalls

Based on experience from previous year's projects, we have accumulated a list of hints and pitfalls for the projects. Read them carefully before starting your project work.


Senast uppdaterad: 2016-12-23