17634 - Computer Vision

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, 2nd ed., 2022

Teaching methods

• Lectures
• Guided exercises at the PC

Assessment methods

Assessment is carried out through a 90-minute written examination, during which the use of books, notes, calculators, or electronic devices is not permitted.

The exam aims to verify the achievement of the following learning objectives:

1. In-depth knowledge of the algorithms and techniques illustrated during the course;
2. Ability to implement these algorithms and apply them within programs that process images and videos;Understanding of the basic functioning of the software libraries used during laboratory exercises.

To this end, the written exam consists of both theoretical questions and practical exercises, in which the student is asked to implement algorithms or portions of algorithms, potentially utilizing some functionalities of the software libraries used during the laboratory exercises. The grade assigned to the exam is determined by the sum of the total score obtained in the theoretical questions (which can range between 0 and 15) and the total score obtained in the practical exercises (which can range between 0 and 17); if the value is greater than 30, "30 e Lode" is assigned.

Attendance of the lessons (including laboratory sessions) is not mandatory and does not contribute to the final grade, which is solely determined by the written examination.

Teaching tools

Lecture notes

Office hours

See the website of Raffaele Cappelli