Computer Vision

Code:

M.IA005

Acronym:

VC

Keywords
Classification	Keyword
OFICIAL	Computer Science
OFICIAL	Informatics Engineering

Instance: 2025/2026 - 2S

Active?	Yes
Responsible unit:	Department of Informatics Engineering
Course/CS Responsible:	Master in Artificial Intelligence

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
M.IA	56	Syllabus	1	-	6	42	162

Teaching language

English

Objectives

A definir pelo docente.

Learning outcomes and competences

The aim is that students understand and are able to explain the basic concepts of computer vision and the fundamental algorithms for manipulation of images and video sequences.
Upon completion of the course, students shall be able to:
1 - analyze a specific problem of computer vision and identify the different fundamental technological challenges;
2 - understand and explain the basic concepts of computer vision and the fundamental algorithms for manipulation of images and video sequences;
3 - identify, discuss, evaluate and apply in practical situations processing, analysis and recognition techniques;
4 - use libraries that implement some of the analyzed algorithms (eg. OpenCV, Keras), and to implement novel algorithms described in the literature;
5 - analyze and understand selected scientific papers in the fields of image processing and analysis, and computer vision.

Working method

Presencial

Program

Introduction to Computer Vision
Image acquisition
- intensity images (2D) and distance/position images (3D)
- geometric and radiometric model of a camera
Processing and analysis of intensity images
- filtering
- feature extraction
- segmentation
Geometric calibration of a camera
- calibration methods
Stereo
- epipolar geometry
- matching
Recognition
- feature selection
- description using local invariant features
- matching of features
Machine Learning
- clustering
- classification
- model generalization
Deep learning
- neural networks
- convolutional neural networks (CNNs)
- detection and segmentation (R-CNN models)
Motion and tracking
- motion estimation
- tracking using linear models
Case studies

Mandatory literature

Szeliski , Richard; Computer vision : algorithms and applications. ISBN: 978-3-030-34371-2
Gonzalez , Rafael C.; Digital image processing. ISBN: 0-13-335672-8

Complementary Bibliography

Goodfellow, I. , Bengio, Y. & Courville, A.; Deep Learning, 2016
Forsyth, D. A. & Ponce, J.; Computer Vision: A Modern Approach, 2011

Teaching methods and learning activities

Classes consisting of presentation and discussion of the course topics, and resolution of exercises. Also, projects are developed, where the studied computer vision methods are applied.

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation	Weight (%)
Teste	50,00
Trabalho prático ou de projeto	50,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Apresentação/discussão de um trabalho científico	81,00
Elaboração de projeto	81,00
Total:	162,00

Eligibility for exams

1- A minimum of 40% on the ExEv and DEv evaluation components are required to be approved in the course. 2- If the teaching team decides not to propose one of the projects, its weight will be redistributed to the other evaluation components.

Calculation formula of final grade

Final Classification = DEv * 0.5 + ExEv * 0.5