The course aims at providing the student with a holistic vision of the state of the art and the modern methodologies on automatic perception, i.e. the ability of a system to interpret data in a way similar to the way in which human beings use their senses to relate to the world around them. In particular, the main focus of the course is oriented towards the description of the methodologies for automatic vision and listening. The student will learn to develop applications for the high-level understanding of images and sounds in order to make appropriate decisions automatically. The course is completed by a detailed discussion of some complex applications, such as: virtual assistants, healthcare, scene analysis, safety systems, and autonomous driving.
Knowledge and understanding: at the end of the course the student will be able to learn about modern methodologies for the design of automatic vision and listening applications.
Applying knowledge and understanding: the student will be able to independently develop automatic vision and listening applications and to describe the implemented solutions and their limitations.
Making judgements: the student will be able to integrate the knowledge acquired during the course with that of the information generally transmitted within the Master Degree Course.
Communication skills: the student will be able to transmit the knowledge acquired and to illustrate the processes that led to it.
Learning skills: individual study will adequately train the capacity for autonomous and independent study, and the ability to continue future studies regarding advanced topics of multimedia processing.
IIET-01/A (Electrical Engineering)
Telecommunication Engineering; Second year; Second semester. 6 CFUs.
Students are expected to have the following background:
Basic of computer programming
Basic of Digital Signal Processing
Basic of Machine and Deep Learning
Project. Students are requested to develop a practical project assignment on one of the course topics. The discussion of the project can be carried out at students’ early convenience. The formal exam registration on Infostud system will take place on the dates indicated below.
Course overview
Deep learning reminders
Part I: Machine Vision
Introduction to Machine Vision
Deep learning for vision
Object detection
Image segmentation
Pre-processing and training strategies
Explainability
Advanced topics (measurement, counting, etc.)
Image generation
Part II Machine Listening
Introduction to Machine Listening
Audio representations
Feature engineering
Deep learning for audio
Environmental sound analysis
Music Information Retrieval (MIR)
Advanced topics (BSS, chord recognition, etc.)
Sound generation
Fusing Vision and Listening (Multimodal Learning)
Concluding remarks
Detailed contents.
Valliappa Lakshmanan, Martin Görner, Ryan Gillard, Practical Machine Learning for Computer Vision: End-to-End Machine Learning for Images, O'Reilly Media, 2021. [For the machine vision part]
Lecture slides, 2027. [For the machine listening part]
Richard Szeliski, Computer Vision: Algorithms and Applications, Springer, 2022.
Rajalingappaa Shanmugamani, Deep Learning for Computer Vision, Packt, 2018.
V Kishore Ayyadevara and Yeshwanth Reddy, Modern Computer Vision with PyTorch, Packt, 2024.
Tuomas Virtanen, Mark. D. Plumbley, and Dan Ellis, Computational Analysis of Sound Scenes and Events, Springer, 2018.
Meinard Müller, Fundamentals of Music Processing - Using Python and Jupyter Notebooks, Springer, 2021.
Alexander Lerch, An Introduction to Audio Content Analysis, John Wiley & Sons, 2012.
Naomi Ceder, The Quick Python Book, 3rd Edition, Manning, 2018.
Naomi Ceder, Python - Guida alla sintassi, alle funzionalità avanzate e all'analisi dei dati, Apogeo, 2019. (in Italian)
Sebastian Raschka, Vahid Mirjalili, Python Machine Learning - Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2, Third Edition, Packt Publishing, 2019.
Sebastian Raschka, Vahid Mirjalili, Machine Learning con Python - Costruire algoritmi per generare conoscenza, Seconda edizione, Apogeo, 2020. (in Italian)
Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, O'Reilly Media, 2nd edition, 2019.
The course will start on February 22 2027, with the following schedule:
Day, hh:00- hh:00, Room xx
Day, hh:00 - hh:00, Room xx
Every day by appointment.
News, updates, and communications about the course will be available on Google Classroom, with the code: .
Lecture Slides:
Overview
Deep learning reminders
Introduction to Machine Vision
Deep learning for vision
Object detection
Image segmentation
Pre-processing and training strategies
Explainability
Advanced topics (measurement, counting, etc.)
Image generation
Introduction to Machine Listening
Audio representations
Feature engineering
Deep learning for audio
Environmental sound analysis
Music Information Retrieval (MIR)
Advanced topics (BSS, chord recognition, etc.)
Sound generation
Fusing Vision and Listening (Multimodal Learning)
Concluding remarks
Python Source Codes:
Example source code
Lecture Notes:
Note 1
Note 2
The discussion of the project can be held at any time, by appointment. The formal verbalization takes place on the dates indicated below:
I round: 16 June 2027 at 11:00 (Exam reservation date ends on 15 June 2027).
II round: 15 July 2027 at 11:00 (Exam reservation date ends on 14 July 2027).
III round: 16 September 2027, at 11:00 (Exam reservation date ends on 15 September 2027).
Special round: 28 October 2027, at 11:00 (Exam reservation date ends on 27 October 2027). Please note that this round is reserved only for part-time, off-course, repeating and graduating students.
IV round: 20 January 2028, at 11:00 (Exam reservation date ends on 19 January 2028).
V round: 17 February 2028, at 11:00 (Exam reservation date ends on 16 February 2028).
Special round: 06 April 2028, at 11:00 (Exam reservation date ends on 05 April 2028). Please note that this round is reserved only for part-time, off-course, repeating and graduating students.
Please, note that the exam is reserved electronically via the INFOSTUD system.