KIUA2002 Computer Vision

    • Number of credits
      10
    • Teaching semester
      2026 Spring
    • Language of instruction
      Norwegian/English
    • Campus
      Hamar
    • Required prerequisite knowledge

      Recommended: KIUA1002 Programming I, KIUA1005 Programming II and KIUA1000 Introduction to AI, Law and Ethics

Course content

Computer vision provides computer programs with the ability to interpret and understand visual information from images and videos and recognise and interpret objects and patterns. The course addresses fundamental principles, concepts and challenges in computer vision and covers topics such as image formation, representation, colour space and image processing. Students will also gain knowledge of different computer vision algorithms and deep learning architectures tailored for computer vision tasks. Students develop skills in image processing and object recognition and will gain practical experience of data vision applications and libraries. The course will also promote critical thinking, problem solving and collaboration, as well as addressing ethical and societal implications associated with computer vision technologies.

Learning Outcome

Upon successfully passing the course, students will have achieved the following learning outcomes:

Knowledge

The student will have

  • knowledge of basic principles, concepts and challenges in computer vision in order to develop knowledge of image formation, representation, colour space and common imaging techniques
  • knowledge of various computer vision algorithms and techniques
  • knowledge of deep learning architectures designed specifically for computer vision and an understanding of the principles behind such models and their applications in computer vision tasks
Skills

The student will be able to

  • perform image processing and practice improvement techniques to use different filters
  • perform object recognition and tracing using different methods and algorithms
  • perform image classification and object recognition and use different computer vision applications
  • apply different methods and libraries used in computer vision
General competence

The student will be able to

  • enhance their critical thinking and problem-solving skills using data vision techniques to analyse and solve real world problems
  • present findings and solutions and efficiently communicate complex computer vision concepts and techniques to a technical and non-technical audience
  • assess ethical and societal implications of computer vision technologies to gain awareness of privacy considerations, bias and fairness in computer vision applications and responsible use of computer vision technologies in different domains
  • promote a research-oriented mindset, explore and evaluate ground-breaking advances in computer vision, read and understand research articles, experiment with new techniques and contribute to the field through innovative ideas and implementations
Teaching and working methods

The course comprises a combination of lectures, practical exercises, independent study and academic supervision.

Required coursework
  • 2 individual assignments

Compulsory coursework requirements that have been passed are valid for 12 months only. Students wishing to take examinations after 12 months must pass the compulsory coursework requirements again in connection with the next scheduled delivery of the course.

Form of assessment
  • 1 project-based group assignment

When taking part in group assignments, all participants in the group are responsible for all content of the task/product/work.

The assignment is assessed using a grading scale from A-F, where E is the lowest passing grade.

Students are able to choose which language to use for their examination. The available options are Norwegian Bokmål, Nynorsk and English.

 

Permitted aids:

  • Literature
  • All printed and written resources
  • Any use of AI-generated text and content must be clarified with the lecturer, clearly labelled and academically justified in the submission
Assessments
Form of assessmentGrading scaleGroupingDuration of assessmentSupport materialsProportionComment
Written assignment
ECTS - A-F
Group
  • All
100
Faculty
Faculty of Audiovisual Media and Creative Technologies
Department
Department of Game Development - The Game School