Artificial Vision | Università degli Studi di Milano Statale

A.Y. 2024/2025

Max ECTS

Overall hours

SSD

INF/01

Language

Italian

Included in the following degree programmes

Computer Science (Classe LM-18)-Enrolled from 2014/2015 Until 2024/2025 Academic Year

Learning objectives

Aim of the course is to give elements which allow to infer knowledge about the real world from digital images or videos. These skills mainly concern the 3D reconstruction of real objects, and the processing and recognition of elements and actions in a scene.

Expected learning outcomes

- Learn the image formation principles
- Learn the techniques to obtai 3D object reconstruction
- Learn machine learning techniques aimed at the identification and recognition of objects and actions in images or videos

Lesson period: Second semester

Lessons timetable

Assessment methods: Esame
Assessment result: voto verbalizzato in trentesimi

Exams calendar

Single course

This course can be attended as a single course.

Take a single course

Course syllabus and organization

Single session

Responsible

Lanzarotti Raffaella

Lesson period

Second semester

Syllabus
(active tab)
Course structure

Course syllabus

Aim of this course is to examine the fundamental concepts in the field of computer vision, with special focus on the following topics:

* Image formation
- Geometric camera models
- Camera Calibration
- Brightness models
- Color models
* "Early" vision
- Linear Filtering
- Feature extraction
- Stereopsis (binocular vision)
- Structure from Motion (multi-view)
- 3D Registration
* Machine learning
- Linear Neural Networks
- Multilayer perceptrons
- Deep Learning Computation
- Convolutional Neural Networks
- Transformers
- Recurrent Neural networks
- Graph Neural Networks
- Generative models

Prerequisites for admission

A good knowledge of the fundamentals of:
- probability and statistics
- signal and image processing
as taught in scientific undergraduate courses.

Teaching methods

Lectures and demo in python

Teaching Resources

Web site:
https://github.com/lanzarotti/

Class material:
- Lecture slides
- Software code for exercises

Books:
- D.A. Forsyth, J. Ponce - Computer Vision - A Modern Approach - Pearson, 2nd edition
- C.M. Bishop, H. Bishop - Deep Learning - Foundations and Concepts - Springer
- A. Zhang, Z.C. Lipton, M. Li, A.J. Smola - Dive into Deep Learning

Assessment methods and Criteria

The exam consists of a written test with open-ended questions or a project, which involves submitting a report and the produced code, as well as presenting the project itself.
The evaluation is expressed on a thirty-point scale.

INF/01 - INFORMATICS - University credits: 6

Lessons: 48 hours

Professor: Lanzarotti Raffaella

Shifts:

Turno

Professor: Lanzarotti Raffaella

Educational website(s)

Visione artificiale (a.a. 2024/25)

Professor(s)

Lanzarotti Raffaella

Web site

We use a selection of our own and third-party cookies on the pages of this website: Essential cookies, which are required in order to use the website; functional cookies, which provide better easy of use when using the website; performance cookies, which we use to generate aggregated data on website use and statistics; and marketing cookies, which are used to display relevant content and advertising. If you choose "ACCEPT ALL", you consent to the use of all cookies. You can accept and reject individual cookie types and revoke your consent for the future at any time at "Settings".