TSBB15 Computer Vision

TSBB15 Computer Vision VT2017 (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:

Lectures	32h (16x2h)
Computer lessons	4h (2x2h)
Computer exercises	16h (4x4h)
Written examination	4h
Seminars	8h (2x4h)
Own studies	106h (approx.)
Project work	150h (approx.)

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

Per-Erik Forssén, lectures, examiner
Klas Nordberg, lectures
Michael Felsberg, lectures

Martin Danelljan, computer exercises, project guide (VT1&VT2)
Marcus Wallenberg, computer exercises (VT1)
Hannes Ovrén, computer exercises, project guide (VT2)
Gustav Häger, computer lessons, computer exercise (VT2), project guide (VT1)

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

Documents

Course description in Studiehandboken (the LiTH study guide)
Course schedule for VT1 and VT2 is available in TimeEdit.

Literature

Klas Nordberg, Introduction to Representations and Estimation in Geometry (IREG).
This compendium covers only the 3D geometry part of the course.
Richard Szeliski, Computer Vision: Algorithms and Applications, Springer Verlag (2011).
This book covers topics such as tracking, optical flow and image features.
The book is available as an on campus e-book via the LiU library. See also Book webpage.

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 2017:

2017-03-15, 14-18: Re-examination opportunity for last year's students, and voluntary mid-term examination for this years's students.
2017-06-03, 14-18: Examination at end of course.
2017-08-15, 14-18: Re-examination opportunity.

Old exams

The exams from 2012, 2013 and 2014 in TSBB15 can be found here.

How to use the old exams: 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

The course content is similar to last year's course, so you may want to look there for details (e.g. slides). Updated slides for this year will be added to the table below, after each lecture.

Date,Time,Room	Activity	Teacher	Material
Jan 18: 10.15-12 P30	Lecture 1 What is Computer Vision?	Per-Erik	Slides for Lecture 1 Edupack - orientation, section 1
Jan 19: 13.15-17 OLYM	Computer lessons 1&2 Images in Matlab and Python	Gustav	Matlab lesson Python lesson
Jan 20: 10.15-12 R18	Lecture 2 Image Representations	Klas	Slides for Lecture 2 Videos: Scale Space 1 - Introduction and Scale Space 2 - Linear Scale Space in the CVL Video Channel. Wikipedia: scale space RNDF up to section 3.3 CVAA: 3.5 Pyramids and wavelets (optional) or GW: sec 7.1.1 p463 (optional) Groups and semi-groups are described in PRE, section 1.3 SLIC: a method for super-pixel formation
Jan 25: 10.15-12 R23	Lecture 3 Orientation	Klas	Slides for Lecture 3 Videos: The Structure Tensor in the CVL Video Channel. EDUPACK - orientation Bigün & Granlund, Optimal orientation detection of linear symmetry, ICCV 1987 (optional)
Jan 26: 13.15-15 BL34	Lecture 4 Motion estimation, optical flow	Klas	CVAA: 8.1 Alignment Videos: Motion Analysis - Introduction in the CVL Video Channel.
Jan 27: 10.15-12 P30	Lecture 5 Optical flow, tracking	Klas	CVAA: 8.4 Optical Flow Summary on Lucas-Kanade tracking Horn & Schunck's paper on optical flow (optional) Shi & Tomasi's paper on tracking (optional)
Feb 1: 10.15-12 BL34	Lecture 6 Clustering and learning	Per-Erik	Slides for Lecture 6 CVAA: 5.3 Mean shift and mode finding CVAA 4.3.2: Hough Transforms SHB: 16.5.1 Background modelling
Feb 2: 13.15-17 OLYM	Computer exercise 1 Tracking	Martin, Marcus	CE1: The Harris operator and LK Tracking Derivation of LK tracking
Feb 3: 10.15-12 BL33	Lecture 7 Overview of project 1: Tracking	Klas	Slides for Lecture 7
Feb 10: 10.15-12 P36	Lecture 8 Local Features	Per-Erik	Slides for Lecture 8 CVAA: 4.1 Points and Patches Background geometry: IREG ch. 7-9,13
Feb 9: 13.15-17 OLYM	Computer exercise 2 Motion	Martin, Marcus	CE2: Motion Estimation ForwardL SCcar4
Feb 15: 10.15-12 R19	Lecture 9 Biological Vision	Per-Erik	Slides for Lecture 9

IREG = Introduction to Representations and Estimation in Geometry, version 0.32, LiU compendium, Klas Nordberg
PRE = Prerequisites for studies at advanced level in Image Science at Linköping University, LiU compendium, Klas Nordberg
CVAA = Richard Szeliski, "Computer Vision: Algorithms and Applications" (2011). The book is available as an on campus e-book via the LiU library. See also Book webpage.
SHB = Sonka, Hlavac and Boyle "Image Processing, Analysis, and Machine Vision" (Old course book)
GW = Gonzalez and Woods, "Digital Image Processing"
HZ = Hartley and Zisserman, "Multiple View Geometry in Computer Vision" (2nd edition 2003). Available as e-book from LiU library
Wikipedia = Search wikipedia for the listed term
Mathworld = Search http://mathworld.wolfram.com/ for the listed term.
Edupack - orientation is a tutorial found here
EDUPACK2 = orientation2.pdf
RNDF = J. Weickert: A Review of Nonlinear Diffusion filtering, Scale-Space 1997

Lecture and lab schedule VT2

Date,Time,Room	Activity	Teacher	Material
Mar 20: 10.15-12 E328	Lecture 10 Recap from previous courses, ML-estimation, Gold Standard	Klas Nordberg	IREG: 8.2.7, 10.6, 14.1.3 SHB: 10.2 HZ: 4.7, 11.4
Mar 21: 13.15-15 BL33	Lecture 11 Calibrated geometry, PnP and the essential matrix, Robust estimation	Klas Nordberg	IREG: 8.5, 13.4, 14.3 SHB: 11.5 HZ: 9.6
Mar 27: 10.15-12 Moved to Mar 30	Lecture 12 RANSAC, Structure from motion, Bundle adjustment, Project 2	Klas Nordberg	Slides for lecture 12 IREG: 15, 18 CVAA: 6.1.4, 6.1.5 (also in IREG)
Mar 28: 13.15-17 E330	Seminar 1 Presentation of project 1	Per-Erik Forssén
Mar 30: 8.15-10 BL34	Lecture 12 RANSAC, Structure from motion, Bundle adjustment, Project 2	Klas Nordberg	IREG: 15, 18 CVAA: 6.1.4, 6.1.5 (also in IREG)
Apr 4: 13.15-17 OLYM	Computer Exercise 3 Optimisation	Martin, Hannes	CE3: Optimisation
Apr 6: 8.15-10 BL33 NB! moved here	Lecture 13 Optimization	Per-Erik Forssén	Slides for Lecture 13 CVAA: 3.7.2, 5.5 Survey article on DP and Graph Algorithms
Apr 10: 10.15-12 E330	Lecture 14 Image Enhancement	Klas Nordberg	Slides for Lecture 14 Videos: Scale Space 3 - The Diffusion Equation in the CVL Video Channel. Edupack - orientation RNDF: Pages 1-9,15-16
Apr 24: 10.15-12 E330	Lecture 15 Variational Methods	Michael Felsberg	Slides for Lecture 15 Excerpt handed out during the lecture CVAA: 5.1 CVonline
Apr 25: 13.15-17 OLYM	Computer Exercise 4 Image Restoration	Martin, Gustav	CE4: Image Restoration
May 8: 10.15-12 BL34	Guest Lectures	Leif Haglund, Vricon Gunnar Farnebäck, Context Vision
May 23: 13.15-17 BL33	Seminar 2 Presentation of project 2	Per-Erik Forssén

Projects

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

List of project groups VT2017

Project 1: Tracking
Introductory lecture on February 3
Design plan due February 13
Report due March 16
Presentation seminar on March 28

Project 2: 3D Reconstruction
Introductory lecture on March 27
Design plan due April 10
Report due May 16
Presentation seminar on May 23

General resources

We suggest and allow you to use the following software:

OpenCV (Open Source Computer Vision). Version 3.1.0 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.

Project repositories

Project code should be developed under versioning control, with changes tracked according to LiU-ID of the participating group members.

Option A: Project groups get their repositories from GITLab at IDA Note: this is not GitHub, and GitHub should not be used.
Option B: On request each project group can get access to a Subversion repository, with individual login by each project member.
Documentation for Subversion can be found here:
- https://svn.isy.liu.se
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: 2017-12-04

Datorseende (CVL)