Studiewijzer 2022/2023

Globale inhoud

We see in order to move; we move in order to see [William Gibson].  Seeing and perceiving the world is vital for everyday life.  For humans and animals this perceptual capability seems effortless.  However, endowing computers with similar capabilities proves to be hard.  In this course we discuss computational models for computer vision and how these can be implemented as working programs. 

In this direction, we convert digital images based on pixels into "visual features", and then process these features for classifying images into categories, tracking the depicted objects, or reconstructing them in 3D. For converting pixels into features we use mathematical models of the local structure and color of images, ideas from the human visual system, the camera's imaging process, and computationally efficient algorithms.  For computer vision we use classic tools, such as linear algebra and Taylor series of multi-dimensional functions (i.e, images), or more advanced ones, such as convolutional neural networks.  In more detail, we will discuss the following topics:

  • Low-level vision (interpolation, warping, local operators, convolutions).
  • Local structure in images, scale space, feature detection (SIFT).
  • Pinhole camera, camera calibration, stereo vision.
  • Motion, optical flow, tracking (time permitting according to the semester’s schedule).
  • Convolutional Neural Networks (CNNs) for computer vision.

We implement the above models as working programs on computers, apply them on images and get results.

In this course you will use skills acquired through the "Linear Algebra" course and the "Calculus and Optimization” course.  You will also need prior hands-on experience in computer programming.




  • Can explain modern techniques and underlying theories in computer vision.
  • Can apply mathematical techniques from linear algebra (eigenvalues, singular value decomposition) and calculus (differentiation of multivariate functions).
  • Can develop working programs for mathematical models using Python/Numpy/Scipy/OpenCV.
  • Can judge the strengths and limitations of the developed methods and programs.


  • Laptopcollege
  • Werkcollege
  • Hoorcollege

In Hoorcollege (HC) the tutors will introduce some key concepts per week.
In Laptopcollege (LC) the students will work on weekly assignments on the topics discussed in HC, with the help of TAs (1 TA will be helping a group of ~20 students).
The Werkcollege (WC) is the last slot of every week; this is the opportunity for students to ask questions on the week's material.

Verdeling leeractiviteiten















(6 EC x 28 uur)


Aanwezigheidseisen opleiding (OER-B):

  • Voor practica en werkgroepbijeenkomsten met opdrachten geldt een aanwezigheidsplicht. De invulling van deze aanwezigheidsplicht kan per vak verschillen en staat aangegeven in de studiewijzer. Wanneer studenten niet voldoen aan deze aanwezigheidsplicht kan het onderdeel niet met een voldoende worden afgerond.

Aanvullende eisen voor dit vak:

Attendance for the Laptopcollege (LC) is mandatory.
Attendance for the Hoorcollege (HC) is highly encouraged.
Attendance for the Werkcollege (WC) is optional -- this is an opportunity for extra interaction with tutors for Q&A.
For missing a class, the general rules of the BSc program apply; please contact the "study advisor" for questions.
There is no attendance requirement for May 12th, due to the Awesome IT conference by the student association.


Onderdeel en weging Details


0.6 (60%)


Moet ≥ 5 zijn

0.4 (40%)

Weekly assignments

Moet ≥ 5 zijn

To pass the course, both of the following are necessary:
- the partial mark for the final exam must be at least 5, AND
- the partial mark for the weekly assignments must be at least 5.

For the latter, out of N weekly assignments, we will calculate the average of the top N-1 grades (i.e., the worst grade is excused).
Each weekly assignment will have a practical and theoretical part -- the relative weight of these will vary every week.

Students that re-take the course still need to (newly) submit the weekly assignments (irrespective of the last year's grades).

Inzage toetsing

Inspecting the assessed work is possible with the help of the TA of each student group.

All students (in pairs of 2 people) need to submit their solutions for the weekly assignments. 
As a rule of thumbs, the weekly deadline will be on Monday midnight. 
The exact schedule (and any deviations from the rule of thumb due to public holidays) will be announced on Canvas.


Students will be working in pairs of 2 students.
All pairs need to submit their solutions for the weekly assignments.
Students that re-take the course still need to (newly) submit the weekly assignments (irrespective of the last year's grades).
All weekly assignments will be graded; out of the N total assignments we will take into account the top N-1 ones. 
Feedback will be given by the TA of each group; the TAs will be syncing in the background with the tutors and senior-TAs.

Fraude en plagiaat

Dit vak hanteert de algemene 'Fraude- en plagiaatregeling' van de UvA. Hier wordt nauwkeurig op gecontroleerd. Bij verdenking van fraude of plagiaat wordt de examencommissie van de opleiding ingeschakeld. Zie de Fraude- en plagiaatregeling van de UvA:


Will be shortly announced on Canvas.


Het rooster van dit vak is in te zien op DataNose.

Verwerking feedback studenten

A summary of the feedback has been received, and has been integrated in the weekly operations. 
- We will keep the back-to-back HC+LC slots, which worked well.
- We will keep the "bonus" WC slot for Q&A at the end of the week, which worked well.
- We will provide extra intuitions for concepts that have proved to be challenging.
- The LC slots will start with a short summary of the important concepts (brief "take-home message" form) to help students focus their attention on the more important aspects.



  • Dimitris Tzionas


  • Rein van den Boomgaard (co-tutor / co-coordinator)
  • H.F. Willard MSc (Senior TA / Dozent-4)
  • Kyrian Maat MSc (Senior TA / Dozent-4)
  • Ischa Abraham (TA)
  • Maxim van den Berg (TA)
  • Julian Blaauboer (TA)
  • Rens den Braber (TA)
  • Jip Greven (TA)
  • Cristian Jensen (TA)
  • Frederick Kreuk (TA)
  • Mara van der Meulen BSc (TA)
  • Zirk Seljee BSc (TA)
  • I.O. Veken (TA)
  • Romana Wilschut BSc (TA)