ECTS credits ECTS credits: 6
ECTS Hours Rules/Memories Hours of tutorials: 1 Expository Class: 21 Interactive Classroom: 21 Total: 43
Use languages English
Type: Ordinary subject Master’s Degree RD 1393/2007 - 822/2021
Departments: External department linked to the degrees
Areas: Área externa M.U en Intelixencia Artificial
Center Higher Technical Engineering School
Call: Second Semester
Teaching: With teaching
Enrolment: Enrollable | 1st year (Yes)
The main objective of this subject is to deepen the techniques of computer vision, advancing in the advanced techniques for segmentation, classification, detection, and tracking of objects, as well as in the applications of AI in the field of vision. In addition to the study of advanced techniques in image processing and analysis, applications in this area will be studied to solve real problems. This subject provides the necessary tools to apply the algorithms studied in practical cases as well as to develop new algorithms.
Learning outcomes:
- Know and know how to apply advanced digital image processing techniques.
- Know and know how to apply advanced digital image analysis techniques.
- Know how to analyze, design, and develop solutions based on advanced image processing and analysis technologies.
- Know how to evaluate the adequacy of the methodologies applied in specific problems.
-Image classification
-Image segmentation
-Object detection
-Visual search
-Video processing
Optical flow
Object tracking
-Aspects of 3D
Skeletonization
Symmetry
-Structure from motion
3D depth estimation
SLAM
Basic bibliography:
Gonzalez & Woods. Digital image processing. ISBN: 0-20-118075-8.
Complementary bibliography:
D.A. Forsyth y J. Ponce. Computer Vision. ISBN 0-13-085198-1.
Steger & Wiedemann. Machine Vision Algorithms and Applications. ISBN 978-3-527-4073.
CB6. Possess and understand knowledge that provides a foundation or opportunity to be original in the development and/or application of ideas, often in a research context.
CB7. That students know how to apply the knowledge acquired and their ability to solve problems in new or little-known environments within broader (or multidisciplinary) contexts related to their area of study.
CB10. That students have the learning skills that allow them to continue studying in a way that will be largely self-directed or autonomous.
CG1. Maintain and extend grounded theoretical approaches to allow the introduction and exploitation of new and advanced technologies in the field of Artificial Intelligence.
CG3. Search and select the useful information necessary to solve complex problems, managing with ease the bibliographic sources of the field.
CG5. Work in a team, especially of a multidisciplinary nature, and be skilled in managing time, people, and decision-making.
CT3. Use the basic tools of information and communication technologies (ICT) necessary for the exercise of their profession and for learning throughout their lives.
CT4. Develop for the exercise of a respectful citizenship with the democratic culture, human rights, and the gender perspective.
CT8. Assess the importance of research, innovation, and technological development in the socioeconomic and cultural progress of society.
CE23. Understanding and mastery of the basic concepts and techniques of digital image processing.
CE24. Ability to apply different techniques to computer vision problems.
CE25. Knowledge and skills to design systems for detection, classification, and monitoring of objects in images and video.
CE26. Understanding and mastery over the forms of representation of signals and images based on their data, as well as its fundamental characteristics and its forms of representation.
The methodology uses the Virtual Campus of the three universities as a basic platform. In the virtual classroom of the subject, the students will have all the information (theory material, class slides, practice scripts, etc.)
*Master sessions: oral exposition (UDC/UVIGO) (common for all students). They mainly develop the skills CB6, CB10, CG1, CT3, CT4, CT8, CE23, CD25, and CE26.
*Laboratory practices (specific presential group in USC): Practical resolution of different image problems through the application of image processing techniques introduced during the master sessions. They mainly develop the skills CB7, CG3, CG5, and CE24.
The assessment of the course consists of two parts:
- Laboratory practicals (40%): Resolution of practical exercises related to the lecture sessions. The adequacy of the proposed solutions to the problems, the quality of the results obtained and the understanding of the techniques used will be evaluated.
- Research (Research project, 60%): Resolution of practical cases. The adequacy of the solutions
proposed to the problems, the quality of the results obtained and the understanding of the techniques used will be assessed.
- Mixed test (Replaces laboratory practices, 40%): Written test with theoretical questions and practical problems to be solved.
The delivery of laboratory practices throughout the course represents 40% of the final grade. Alternatively, 40% of the final grade can be reached by taking a mixed test. The presentation of the laboratory practices exempts from the performance of the mixed test. If the student submits the laboratory practicals and then takes the mixed exam, the grade obtained in the mixed exam will prevail. Students who do not submit any of the tests will be considered as not submitted.
Second opportunity
In case of a no-show in the first opportunity, the evaluation will be based on the research project (up to 60% of the total grade) and the mixed test (up to 40% of the total grade). If the student handed in the laboratory practices and/or the research projects but did not achieve a passing grade in the first round, the grade obtained for the second round in each of the parts will be kept. In order to achieve the grade required to pass, the student must submit the projects not submitted/approved and/or take the mixed test.
The condition of Not Submitted will only apply to those who do not participate in any of the evaluation tests.
In application of the Regulamento da ETSE sobre plaxio (approved by the Xunta ETSE on 19/12/2019), the total or partial copy of any exercise of practice or theory will mean a failure on both occasions of the course, with a qualification of 0.0 in both cases.
Second and subsequent enrollments
The evaluation criteria will be the same as for first registration students.
Class attendance
Attendance is not evaluable.
This subject has 6 ECTS credits, corresponding to a total workload of 150h (presence of 7h/credit). This time can be broken down into the following sections:
PRESENTIAL WORK IN CLASSROOM:
* Master classes: 21 hours
* Laboratory practices: 14 hours
* Problem-based learning, seminars, case studies and projects: 7 hours
Total hours of classroom work in the classroom: 42 hours
PERSONAL WORK OF THE STUDENTS:
* Autonomous study: 21 hours
* Laboratory practices: 48 hours
* Problem-based learning, seminars, case studies and projects: 39 hours
Total: 108 hours
It is recommended to have completed the subject Computer Vision I. It is recommended to bring the subject up to date and to use tuition sessions to clarify doubts and advise on its development.
The teaching of this subject will be in English.
The expository teaching (21 hours) will be given between the UDC and the UVIGO and will be broadcast for all students.
There will be a specific interactive teaching group at USC (21 hours).
| Wednesday | |||
|---|---|---|---|
| 17:00-18:30 | Grupo /CLE_01 | - | IA.02 |
| 18:30-20:00 | Grupo /CLIL_01 | - | IA.02 |
| 06.15.2026 16:00-20:00 | Grupo /CLIL_01 | IA.02 |
| 06.15.2026 16:00-20:00 | Grupo /CLE_01 | IA.02 |
| 07.08.2026 16:00-20:00 | Grupo /CLE_01 | IA.02 |
| 07.08.2026 16:00-20:00 | Grupo /CLIL_01 | IA.02 |