Description
This course explores the techniques that allow a computer to interpret a scene. A key point is to model the image formation process and the study of the relationship between the 3D environment and its projection in the plane of the image.The extraction of attributes for object recognition and classification is also addressed.
Type Subject
Optativa
Semester
First
Credits
5.00
Objectives

The students of Computer Vision learn the following knowledge and develop the following skills:

1. Acquire the basic knowledge of detection, estimation and interpretation of movement and the structure of a scene, and get to know different methods related to pattern recognition and classification in order to apply them to real problems.
2. Identify, formulate and resolve real situations where computer vision should have an important paper, and to do so in a multidisciplinary environment individually or as a member of a team.
3. Understand the potential impact the algorithms and the learned techniques may have on society.
4. Have a fluent oral communication and a correct writing.
5. Consolidate techniques used in team-working.
6. Understand the importance of having a continuous education and to know English as a fundamental language for knowledge transmission.

Contents

1. Introduction and applications of computer vision
2. Topics and trends in computer vision
3. Digital images
4. Detection and recognition
5. Image features and image matching
6. Architecture of computer vision systems

Methodology

In this subject knowledge is presented through two different kinds of activities: teacher´s lectures and practical lessons.

Teacher lectures offer a solid theoretical framework to allow students to acquire the main ideas, concepts and algorithm foundations in computer vision, in order to give them the ability of using computer vision techniques in practice. These lectures include theoretical explanations, problems, and discussion of practical examples and the program and practical contents of the subject. Teacher´s lectures also include discussions on non solved problems and the difficulty of applying the studied knowledge.

In the practical lessons students must work in groups. These lessons give the student some experience in problem solving and decision-making, abilities extremely related to their future work. A minimum number of hours are necessary for the development of practical exercises and the acquisition of self-learning, self-critic and self-evaluation abilities. Moreover, additional practical hours can be done with the support of the teacher if the student has some questions or he/she can´t reach the desired solution.

Practical exercises in laboratory are suited for students to get to know the main difficulties in real research problems and enhance research abilities.

Evaluation

The evaluation of the Computer Vision subject is based on:

J. Classroom participation
F. Team reports/works
I. Presentations

The evaluation is conducted continuously during the course. The final score is calculated using the following weighting:
- 60% report / work in teams
- 10% participation in class
- 30% presentations

Evaluation Criteria

Objective 1:
- The student must demonstrate their ability to solve problems using machine vision tools [F]
- The student must demonstrate their knowledge on the concepts developed [F]

Objective 2:
- The student must become aware of the validity of the knowledge acquired and how they can become useful future knowledge that he may come to derive [F, J]

Objective 3:
- The student must demonstrate that it has a correct written and oral expression to communicate ideas related to the topic of the subject [J, F, I]

Objective 4:
- The student must demonstrate that he can work with a diverse group of people while maintaining an ethical and tolerant behaviour [J, F, I]

Objective 5:
- The student must demonstrate that he can find solutions to open problems by imposing appropriate restrictions and can check their validity. [F]

Objective 6:
- The student must demonstrate the ability to acquire new knowledge from texts, information and experimentation [F]

Basic Bibliography

David A. Forsyth, Jean Ponce. Computer Vision, A Modern Approach. Prentice Hall, 2003
Arturo de la Escalera, Visión por Computador, Prentice Hall 2001
R. Jain, R. Kasturi, B. Schunck, Machine Vision , Mcgraw-Hill, 1995
B. K. P. Horn, Robot Vision, MIT Press, 1986

Additional Material

M. Tekalp, Digital Video Processing, Prentice Hall, 1995
G. Pajares, J. M. de la Cruz, Visión por Computador. Imágenes digitales y aplicaciones. Editorial Ra-Ma, 2001
Carme Torras (Ed.), Computer Vision. Theory and Industrial Applications, Springer-Verlag, 1992.
R. Boyle, C. Hlavac and M. Sonka, Image Processing, Analysis And Machine Vision , Chapman & Hall, 1994
R. Hartley and A. Zisserman, Multiple View Geometry, Cambridge University Press, 2000
O. Faugeras, Three-Dimensional Computer Vision: A Geometric Viewpoint, Mit Press
C. Brown, D. Terzopoulos, Real-Time Computer Vision, Cambridge University Press, 1994
R. Cipolla, A. Pentland, Computer Vision For Human-Machine Interaction, Cambridge University Press.