This page contains the details about the first edition of the Course on Computer Vision for Humans and Robots held at Scuola Superiore Sant’Anna in 2017 for PhD and graduate students.
Duration: 20 hours (2 CFU)
- Light and Image Formation
- Multiple Cameras
- Recognition Cases: Face, Objects
- Machine Learning
oral with written exercis, plus scoring from assignments
the reference book is Szeliski 2010 (http://szeliski.org/Book/) that although is not covering the most recent advancements provides a rock solid basis on Computer Vision.
In-class activities and examples are based on OpenCV in Python with the help of the Jupyter framework for presentation. They are available here:
The presentation materials takes advantage of excellent courses available online in particular the recent CSCI 1430 by James Tompkin at Brown University, that in turns used slides from other courses. All original authors have been left in the slides. When none is mentioned they are original.