Computer Vision

This teaching unit will be held online.

An image is worth thousand words. That is to say: Images are very rich of information and this course aims to provide the basic understanding and algorithms to automatically extract it. The ultimate objective of computer vision is to design machine vision systems (e.g., camera sensors, computers, algorithms and robotic actuators) that can assist humans with applications to science (e.g., medicine), safety (e.g., traffic monitoring), consumer products (e.g., consumer cameras), entertainment (e.g., Microsoft Kinect, cell-phone apps), and manufacturing. This course covers the following fundamental topics in computer vision: introduction to image formation, image processing, feature detection, segmentation, multiple view geometry and 3D reconstruction, motion, face detection, object recognition and classification. Students will implement algorithms that are presented in the class and have a chance to test them first hand on images.


Code 31062
Type Course
Site Bern
Track(s) T3 – Advanced Information Processing
T6 – Data Science
Semester A2020


Learning Outcomes

Upon successful completion of this class, you will be able to:

  • Understand how cameras capture images of a scene
  • Implement and use: algorithms for image processing such as image filtering and image segmentation; algorithms for object detection (such as faces) and recognition; algorithms for 3D reconstruction (e.g., from stereo systems)
  • Describe the mathematics underpinning each method and know how to adapt it to other scenarios.
Lecturer(s) Paolo Favaro
Language english
Course Page

The course page in ILIAS can be found at

Schedules and Rooms

Period Weekly
Schedule Tuesday, 14:15 - 17:00
Location online

Additional information


First Lecture
The first lecture will take place online on Tuesday, 15.09.2020 at 14:15.