Computer Vision (2016/2017)

Course code
Name of lecturer
Umberto Castellani
Umberto Castellani
Number of ECTS credits allocated
Academic sector
Language of instruction
I sem. dal Oct 3, 2016 al Jan 31, 2017.

Lesson timetable

I sem.
Day Time Type Place Note
Monday 10:30 AM - 11:30 AM lesson Laboratory Gamma  
Monday 11:30 AM - 1:30 PM laboratorio Laboratory Gamma  
Tuesday 8:30 AM - 10:30 AM lesson Lecture Hall I  

Learning outcomes

This course is aimed at providing the student with the practical and theoretical tools that enables the recovery of the three-dimensional structure of a scene starting from its two-dimensional projections, the images. The process of image acquisition will be introduced describing several 3D to 2D projection models and focusing on the relations between the involved cameras. In the context of the CdS, the course provides the knowledge for the extraction of 3D information form 2D sources that are important for the automatic recognition of image content.
At the end of the course, the student will be able to address methodological and practical aspects of different computer vision problems. The student will be able to generalize the acquired knowledge for the design, implementation and documentation of new projects on innovative applications.


- Geometry of the pinhole camera
- Calibration
- Epipolar geometry
- Triangulation
- Planes and homographies
- Structure and motion from images
- Autocalibration
- Dealing with noise and outliers
- Image matching
- Laboratory exercise

Reference books
Author Title Publisher Year ISBN Note
E. Trucco, A. Verri Introductory techniques for 3D Computer Vision (Edizione 1) Prentice-Hall 1998 0132611082
R. Hartley, A. Zisserman Multiple View Geometry in Computer Vision (Edizione 2) Cambridge University Press 2004
Andrea Fusiello Visione Computazionale 2008

Assessment methods and criteria

The exam can be obtained with three different options:
A) Oral with discussion on lab exercise (max 28/30, average between the two modalities).
B) Project with discussion on lab exercise (max 28/30, average between the two modalities).
C) Oral+Project (average between the two modalities).
Oral is a discussion on the program. The aim is to verify the knowledge of theoretical and practical aspects of involved topics.
The discussion of lab exercise consists of the delivering of an archive with the scripts that implement the vision algorithms described in the program. The discussion aims at verifying the correct practical implementation of the theoretical aspects addressed during the course.
The project is focused on a specific and innovative topic that is identified with the teacher. The topic can be an open issue of the state of the art or a specific applicative theme. The student will be able to generalize the knowledge acquired during the course for the solution of new computer vision problems.