Instrumentation and processing for machine vision

Code:

MVCOMP05

Acronym:

IPVA

Keywords
Classification	Keyword
CNAEF	Engineering and related techniques

Instance: 2024/2025 - 1S

Active?	Yes
Responsible unit:	Department of Informatics Engineering
Course/CS Responsible:	Master in Computer Vision

Cycles of Study/Courses

Acronym	No. of Students	Study Plan	Curricular Years	Credits UCN	Credits ECTS	Contact hours	Total Time
MVCOMP	5	Syllabus	1	-	6	42	162

Teaching language

English

Objectives

This curricular unit goes through the aspects of image acquisition and image processing. From the viewpoint of industrial application, the course also elucidates topics like illumination and camera calibration. Attention is paid to the hardware aspects, from lenses and camera systems to camera-computer interfaces. Besides the hardware analysis, the necessary software is discussed with equal depth. This includes connections to digital image basics, image analysis, and processing (discussed in other curricular units). Finally, the student is introduced to general aspects of industrial applications of machine vision, such as case studies and strategies for the conception of complete machine vision systems. The student will be enabled not only to understand up-to-date systems for machine vision but also to be qualified for the planning and evaluation of such technology.

Learning outcomes and competences

Basic Skills
CB7- Students have to be capable of applying the knowledge learned throughout the course and problem-solving abilities in new scenarios related to their field of study.

Transversal Skills
CT2- Teamwork capacity, organization and planning.
CT5- Green and sustainability plans in their professional careers. Equity, responsibility and efficiency with the resources available.

Generic Skills
CG3- Ability to design and deploy computer vision systems meeting existing needs and ability to run the most suitable tools.
CG4- To be critical and to make strict and thoughtful assessments of technologies and methodologies.

Specific Skills
CE6- To be knowledgeable and apply the fundamentals of image acquisition and computer vision.

Working method

Presencial

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

Knowledge of a programming language, preferably Python or C++, and basic algebra concepts are recommended.

Program

1. Image and video acquisition: lighting, lenses, sensors and interfaces.


2. Smart image sensors.


3. Machine vision algorithms.


4. Geometric camera calibration.


5. 3D data acquisition.


6. Industrial machine vision systems and applications.

Mandatory literature

Alexander Hornberg; Handbook of Machine and Computer Vision: The Guide for Developers and Users
E. R. Davies; Machine Vision, Theory, Algorithms, Practicalities
Adrian Kaehler; Learning OpenCV 3. ISBN: 978-1-491-93799-0
Laurent Berger; Traitement d'images et de vidéos avec OpenCV 4 en Python (Windows, Linux, Raspberry)

Complementary Bibliography

Junichi Nakamura; Image Sensors & Signal Processing for Digital Still Cameras
Jun Ohta; Smart Image Sensors and Applications
Richard Szeliski; Computer vision. ISBN: 978-1-84882-935-0
Rafael C. González, Richard E. Woods; Digital Image Processing, 2007

Teaching methods and learning activities

Face-to-face lectures by the teacher on the topics of each chapter. Examples of use cases of every chapter will be given. Some concepts will be completed with talks. Students will attend lab lessons, conduct their experiments, and do their own homework to elaborate on the contents.

This curricular unit requires face-to-face participation of all students at the University of Santiago de Compostela to carry out part of their laboratory practices.

Software

OpenCV library

Evaluation Type

Distributed evaluation with final exam

Assessment Components

Designation	Weight (%)
Exame	40,00
Trabalho laboratorial	60,00
Total:	100,00

Amount of time allocated to each course unit

Designation	Time (hours)
Estudo autónomo	55,00
Frequência das aulas	42,00
Trabalho laboratorial	65,00
Total:	162,00

Eligibility for exams

Submitting and presenting the practical assignments is mandatory.

Calculation formula of final grade

Final_grade = Exam_grade*40% + Distributed_grade*60%

Special assessment (TE, DA, ...)

Students with specific statuses will be assessed like regular students: they must do all the assignments and lab work during the semester and submit them on the scheduled dates.

Classification improvement

The grade on the final exam can be improved in the next exam season, according to FEUP rules. The distributed evaluation grade is the one obtained at the end of classes, and it can only be improved by enrolling again in a future occurrence of this course.