Course syllabus

Jump to today

Course-PM

EEN020 Computer vision lp2 HT19 (7.5 hp)

Course is offered by the department of Electrical Engineering

Essential information

  • For every lecture, there are some mandatory preparations, typically involving viewing a few videos. See Schedule and preparations.
  • There are five mandatory assignments. After completing an assignment, you submit a report in pdf together with your code in Canvas. Deadlines below.
  • There is a mandatory project. More details about possible projects later.
  • There is no written exam in the course. For a passing grade (3), all assignments and the project should be completed in time. In addition, for higher grades (4 or 5), optional exercises in the assigments should be completed, and an oral exam should be taken. The quality of the project will also influence the final grade.
  • We recommend that you do the computer exercises in pairs, but it is also ok do them individually. Groups larger than two persons are not allowed.
  • Reports to assignments should be done invidually.
  • Projects should be done individually.

Contact details

Course purpose

The course aims to provide an overview of theory and practical useful methods in computer vision, with applications such as seeing systems, non-destructive measurements and augmented reality. The aim is also to enable the student to develop his / her ability to solve problems, both with and without computer, using tools derived from many different sciences, especially geometry, optimization, statistics and computer science.

Schedule

Please see Schedule and preparations.

You can also see the schedule and lecture room in TimeEdit.

Course literature

The necessary course material will be provided during the course. This includes lecture notes, assignments and research articles.
If you like to read more about computer vision, you can use Szeliski's book which is available online.

  • Richard Szeliski, Computer Vision: Algorithms and Applications, available at Cremona or as a free pdf.

For pointers to relevant chapters, see Schedule.

For more in-depth reading, the Hartley-Zisserman book also known as the Bible is recommended.

  • Richard Hartley and Andrew Zisserman, Multiple View Geometry, Cambridge University Press, 2004.

Deadlines

You need to submit your code and reports for your assignments before the following dates in Canvas. If there are minor errors on the mandatory exercises, you will be given a chance to correct them later. If you submit solutions to optional exercises, you will be given feedback, but no need to submit corrections.

  1. Assignment 1: Thursday, November 21, 23:59
  2. Assignment 2: Thursday, November 28, 23:59
  3. Assignment 3: Thursday, December 5, 23:59
  4. Assignment 4: Thursday, December 12, 23:59
  5. Assignment 5: Thursday, December 19, 23:59
  6. Project: Wednesday, January 8, 2020.

Deadline for all revisions of assignments: Friday, January 10, 2020.

Note that if you are not approved on all assignments by the January 10, 2020, you will fail the course. We recommend that you do all revisions before Christmas, since correcting assignments will be done at a slower pace after that.

Learning objectives and syllabus

Learning objectives:

Knowledge and understanding
For a passing grade the student must:

  • be able to clearly explain and use basic concepts in computer vision, in particular regarding projective geometry, camera modelling, stereo vision, recognition, and structure and motion problems.
  • be able to describe and give an informal explanation of the mathematical theory behind some central algorithms in computer vision (the least squares method and Newton based optimization).

Competence and skills
For a passing grade the student must:

  • in an engineering manner be able to use computer packages to independently solve problems in computer vision.
  • be able to show good ability to independently identify problems which can be solved with methods from computer vision, and be able to choose an appropriate method.
  • be able to independently apply basic methods in computer vision to problems which are relevant in industrial applications or research.
  • with proper terminology, in a well-structured way and with clear logic, be able to explain the solution to a problem in computer vision.

Link to the syllabus on Studieportalen.

Study plan

Course summary:

Date Details Due