Vision-Based Systems

Code:

EEC0100

Acronym:

SBVI

Keywords
Classification	Keyword
OFICIAL	Automation, Control & Manufacturing Syst.
OFICIAL	Basic Sciences for Electrotechnology

Instance: 2020/2021 - 1S

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

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
MIEEC	81	Syllabus	4	-	6	56	162

Teaching language

Portuguese

Objectives

The main objectives to attain are the acquisition of knowledge on automatic vision systems, not only on the elements that constitute their modular structure, but also on the technology used in their implementation.

Learning outcomes and competences

1. Acquisition of knowledge on automatic vision systems, not only on the elements that constitute their modular structure, but also on the technology used in their implementation (CDIO Syllabus 1.3, 1.4, 2.1, 2.3).
2. Demonstration of skills on the design, projection and implementation of automatic vision systems (CDIO Syllabus 4.2, 4.3, 4.4, 4.5).
3. Development of organisational skills, as well as autonomous work and bibliography research (CDIO Syllabus 2.4, 2.5, 3.3).
4. Demonstration of skills on teamwork (CDIO Syllabus 2.5, 3.1).
5. Development and demonstration of skills on written and oral communication (CDIO Syllabus 3.2)

Working method

Presencial

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

Knowledge of Signal Processing and software MatLab.

Program

1. Introduction. General structure of a vision-based system.
2. Acquisition and formation of digital images.
3. Preprocessing. Image operators and their application in image enhancement.
4. Mathematical morphology.
5. Image segmentation.
6. Image analysis.
7. Image recognition and classification.

Mandatory literature

Rafael C. Gonzalez, Richard E. Woods; Digital Image Processing, Pearson, 2018. ISBN: 1-292-22304-9
Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins; Digital image processing using Matlab. ISBN: 0-13-008519-7
E.R. Davies; Computer Vision. Principles, Algorithms, Applications, Learning, Elsevier, 2018. ISBN: 978-0-12-809284-2

Complementary Bibliography

Steger C., Ulrich M. Wiedemann C; Machine Vision Algorithms and Applications, Wiley, 2008. ISBN: 978-3-527-40734-7
Milan Sonka, Vaclav Hlavac, Roger Boyle; Image processing, analysis and machine vision. ISBN: 978-0-495-24428-7

Teaching methods and learning activities

Theoretical classes: presentation of themes, practical demonstration and case studies.

Theoretical-practical classes:
Problem solving, experimentation and testing using Matlab (Image Processing Toolbox), development of solutions in Matlab.

Distributed evaluation components (for realization outside the classes) 
A. Individual responses to a set of 4/5 quizzes available using the Moodle platform.
B. Autonomous project work by groups of 3/4 students on a topic suggested by the teachers. Elaboration of a written report. Public oral presentation of the work done.

Software

MatLab - The Mathworks

keywords

Technological sciences > Engineering > Electrical engineering

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation	Weight (%)
Exame	60,00
Trabalho prático ou de projeto	30,00
Teste	10,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Elaboração de projeto	40,00
Estudo autónomo	61,00
Frequência das aulas	56,00
Trabalho escrito	5,00
Total:	162,00

Eligibility for exams

The components of the evaluation are:
- questionnaires (Q)
- group project (3/4 students) and respective written report (P);
- oral presentation of practical work (AP)
- final exam (EF)

Students have to do the group project, as well as the oral presentation and report, to be admitted to exams.
The frequency grade (distributed evaluation) is obtained by combining the grade obtained in the questionnaires and the group work grade, considering the execution aspects, achieved results, division of tasks among the group members, quality of the written report and of the public presentation.
Students without a frequency grade are not admitted to the exam. Students with a countinuous assignment grade obtained in a previous year should contact the teacher in order to be admitted to the final exam.


Practical assignment – CDIO Syllabus assessed: 1.3, 1.4, 2.1, 2.3, 2.4, 2.5, 3.1, 3.3, 4.2, 4.3, 4.4, 4.5.
Oral Presentation – CDIO Syllabus assessed: 3.1, 3.3, 4.2, 4.3, 4.4, 4.5.
Final Exam and quizzes - CDIO Syllabus assessed: 1.3, 1.4, 2.1, 2.3, 4.2, 4.3, 4.4, 4.5.

Calculation formula of final grade

The final grade is the result of the combination of the frequency evaluation grade (AF) and the final exam grade (EF). 
The same formula apply for recurso season and classification improvement.

Final grade=0.4*AD + 0.6*EF

Examinations or Special Assignments

Quizzes and the above mentioned project.

Internship work/project

The theme of the group project will be defined before FEUP week.
The project report and the developed code must be submitted until December 12th.
The presentation of the work will be carried out during the periods of the PL classes of the last week of the semester, with a calendar to be defined. Presentation slides must be submitted by the end of the 14th of December.

 

Special assessment (TE, DA, ...)

The only special case considered is that of working-students. These students must qualify for the final exam by performing a practical assignment whose nature is similar to that of ordinary students. This work can be done individually or in groups, depending on the student's choice, but approved by the responsible of the course.

Classification improvement

Students cannot improve the frequency grade
However, students can improve the grade of the exam.