Computational Vision

Code:

PDEEC0090

Acronym:

VC

Keywords
Classification	Keyword
OFICIAL	Electrical and Computer Engineering

Instance: 2023/2024 - 2S

Active?	Yes
Responsible unit:	Department of Electrical and Computer Engineering
Course/CS Responsible:	Doctoral Program in Electrical and Computer Engineering

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
PDEEC	13	Syllabus	1	-	6	42	162

Teaching language

Suitable for English-speaking students

Objectives

Computer vision focuses on extracting "useful information" from images and videos. Examples of "useful information" include, for example, detection and identification of human faces and gestures, and tracking moving people or vehicles in a video sequence. Computer vision algorithms have found a wide range of applications in the industrial, military and medical fields. Upon completion of this course, students will:

-understand and be able to explain the basic concepts of computer vision and the fundamental algorithms for manipulation of images and video sequences;

- have described the foundation of image formation, measurement, and analysis;

- have knowledge of existing methods for visual data analysis and be able to apply them in practical situations;

- understand the geometric relationships between 2D images and the 3D world;

- have gained exposure to object and scene recognition and categorization from images;

- grasp the principles of state-of-the-art deep neural networks;

- developed the practical skills (e.g., OpenCV or Pytorch) necessary to build computer vision applications;

- be able to analyze and understand selected scientific papers in computer vision.

 

Learning outcomes and competences

Teaching and learning methods aim the knowledge of the contents referred to in the syllabus, reaching the targeted goals and competencies.

The diversity of proposed methodologies aims at enhancing the skills and competencies established, seeking to evidence different levels of analysis, fostering the integration of knowledge. The proposed methods and strategies aim to develop students' knowledge, understanding and skills in computer vision techniques.

The generic skills of teamwork, organization, etc. will be worked on in the group project. Likewise, the ability to develop computer vision according to existing needs and to apply the most appropriate technological tools, to know, apply and evaluate computer vision will be worked out in the weekly exercises and group project.

Technical skills in computer vision and scientific dissemination in this research field will be worked during the semester in theoretical-practical classes.

Working method

Presencial

Pre-requirements (prior knowledge) and co-requirements (common knowledge)

No prior experience with computer vision is mandatory, although previous knowledge of visual computing or signal processing will be helpful. The following skills are necessary for this class:

Math: Linear algebra, vector calculus, and probability.

Data structures: code that represents images as feature and geometric constructions.

Programming: all lecture code and homework starter code will be Python (but you can also use C/C++).

Program

Introduction to computer vision

Acquisition of digital images

     Intensity (2D) and distance/position (3D) images

     Geometric and radiometric model of a camera

Image processing and analysis

     Filtering (in time and frequency domain)

     Rejection of Outliers

Image processing and analysis for 3D

    Multiple Image Geometry

    Use of Deep Learning techniques to calculate the disparity

    Use of Deep Learning techniques for fusion of 3D information

Movement and tracking

     Motion estimation

     Tracking of linear models

Object recognition

    Detection and location of objects in images

    3D object detection and recognition

Case Studies

Mandatory literature

Richard Szeliski; Computer vision. ISBN: 978-1-84882-935-0

Teaching methods and learning activities

Lectures: Presentation and discussion of the course topics, and resolution of exercises.

Practical assignments: Development of projects where the studied computer vision methods must be applied.

Two projects will be developed during the semester; these projects must be developed both during classes and at home. For the last project a report will be written and an oral presentation will be required.

The final exam is worth 30% of the final grade. The projects account for the remaining 70%.

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation	Weight (%)
Apresentação/discussão de um trabalho científico	30,00
Exame	30,00
Trabalho prático ou de projeto	40,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Apresentação/discussão de um trabalho científico	20,00
Elaboração de projeto	100,00
Estudo autónomo	10,00
Frequência das aulas	36,00
Total:	166,00

Eligibility for exams

-- University of Porto regulations.
-- Completion of the practical work.
-- Minimum grade of 8.00 (eight).

Calculation formula of final grade

Grade (100%) = 30%Assignment_1 + 40% Assignment_2 + 30% Exam

Examinations or Special Assignments

Students who have not carried out the practical component during the academic period will have to carry out an equivalent work.

Special assessment (TE, DA, ...)

UP regulations.

Classification improvement

Assignments are not possible to be enhanced in the same year.