17634 - Computer Vision

Course Unit Page

SDGs

This teaching activity contributes to the achievement of the Sustainable Development Goals of the UN 2030 Agenda.

Quality education Industry, innovation and infrastructure

Academic Year 2021/2022

Learning outcomes

At the end of the course, the student knows the main application areas of computer vision and the basic algorithms for image analysis and object recognition.

Course contents

  • Basic image processing tools (color models, convolution, digital topology and mathematical morphology
  • Techniques for object detection and segmentation from images
  • Video object detection and tracking
  • Object recognition from images and videos

Readings/Bibliography

Richard Szeliski, Computer Vision: Algorithms and Applications, 2010

Teaching methods

  • Lectures
  • Guided exercises at the PC

Assessment methods

Learning results are assessed through a written test of 90 minutes, during which it is not allowed to use books, notes, or any electronic device. The examination aims to assess the achievement of the following learning objectives: 1) detailed knowledge of the algorithms and techniques discussed during the course; 2) ability to implement such algorithms and apply them in software programs; 3) understanding of the main functionalities of the class libraries used during the lab exercises. To this end, the written test contains both theoretical questions and practical exercises, which ask the student to implement algorithms or portions of algorithms, exploiting also some functionalities of the class libraries used during the lab exercises.

In case of remote assessment due to the COVID-19 emergency, the written exam is replaced by an oral exam on the same topics/exercises.

Teaching tools

Lecture notes

Office hours

See the website of Raffaele Cappelli