Target

Duration

20 hours

Instructors

Francesca Odone
UniGe | MaLGa & DIBRIS francesca.odone@unige.it

When

Jul 5 2021 , Jul 9 2021

Where

Live streaming on Microsoft Teams

Important Dates

Application deadline: May 16
Notifications of acceptance have been sent out
The school will be held online on Microsoft Teams
We sent the invitations to join the CVCC team on Microsoft Teams. If you have not received the invitation, please reach out at malga.unige@gmail.com

Abstract

Visual perception, as a key element of Artificial Intelligence, allows us to build smart systems sensitive to surrounding environments, interactive robots, video-cameras with real time algorithms running on board. With similar algorithms our smart-phones can log us in by recognizing our face, read text automatically, improve the quality of the photos we shoot.
At the core of these applications are computer vision models, often boosted by machine learning algorithms.
This crash course will present the basic principles of computer vision and visual perception in artificial agents. It will include theoretical classes, application examples, hand-on activities.
Students will be provided with an overview of state-of-the-art methods for modelling and understanding the surrounding scene or an image content. In the first part we will present elements of classical computer vision (feature detection, depth estimation, motion analysis). In a second part, students will get acquainted with the problem of representing and understanding the image content adaptively by means of shallow or deep machine learning algorithms.

A certificate of attendance (2 credits suggested according to the ECTS grading scale) will be sent to all participants.

An exam certificate (no grade, 6 credits suggested according to the ECTS grading scale) will be issued to those who will take and pass the exam

CVCC is a 20 hours crash course on computer vision, including principles and algorithms and hands-on activities. The course is linked to DL. The two courses are self-contained and can be taken independently, with very little overlap, but students interested in both will be provided extra information to better relate the two subjects.

Mon 9.00-11:00-Class : Introduction to computer vision and its applications
Mon 11.00-13.00 Class : Image formation; image processing basics
Tue 9.000-11.00 Class : Image filtering: noise reduction and edge enhancement. Introduction to features detection
Tue 11.00-13.00 Lab
Wed 9.000-13.00 INTERLUDE: A practical wider scope activity on image analysis
Thu 9.00-11.00 Class : Dealing with more than one image: motion analysis and depth estimation
Thu 11.00-13.00 Lab : -
Fri 9.00-11:00 Class : Computer Vision in the Deep Learning era
Fri 11.00-13.00 **Lab **

Once accepted, each candidate has to follow the instructions in the acceptance email and proceed with the payment. The registration fee is non-refundable.

Fees
students and postdocs: waived
professors: waived
professionals: EUR 150
UniGe students and IIT affiliates: no fee

To apply, complete the application form

Issa Mouawad
UniGe | MaLGa & DIBRIS issa.mouawad@dibris.unige.it
Modiana Pasquinelli UniGe | MaLGa & DIBRIS modiana@unige.it

Slides and readings will be provided.

Some reference books:
E. Trucco, A. Verri Introductory Techniques for 3-D Computer Vision Prenctice Hall 1998
R. Szeliski Computer Vision: Algorithms and Applications https://szeliski.org/Book/
I. Goodfellow, Y. Bengio, A. Courville Deep Learning https://www.deeplearningbook.org/
The course is linked to the course Deep Learning: hands on introduction. The two courses are self-contained and can be taken independently, but students interested in both will be provided extra information to better relate the two subjects.