Teaching plan for the course unit

 

 
Close imatge de maquetació

 

Print

 

General information

 

Course unit name: Computational Vision

Course unit code: 569392

Academic year: 2021-2022

Coordinator: Petia Ivanova Radeva

Department: Department of Mathematics and Computer Science

Credits: 5

Single program: S

More information enllaç

 

 

Estimated learning time

Total number of hours 125

 

Face-to-face and/or online activities

45

(Due to the Covid-19 restrictions, we expect to have 50%-75% of in-person activities)

Independent learning

80

 

 

Competences to be gained during study

 

Competències relacionades


  • CT3 - Ser capaz de trabajar como miembro de un equipo interdisciplinar ya sea como un miembro mas, o realizando tareas de direccion con la finalidad de contribuir a desarrollar proyectos con pragmatismo y sentido de la responsabilidad, asumiendo compromisos teniendo en cuenta los recursos disponibles.
  • CT4 - Gestionar la adquisicion, la estructuracion, el analisis y la visualizacion de datos e informacion en el ambito de la especialidad y valorar de forma critica los resultados de esta gestion.
  • CT6 - Capacidad de evaluar y analizar de manera razonada y critica sobre situaciones, proyectos, propuestas, informes y estudios de caracter cientifico-tecnico. Capacidad de argumentar las razones que explican o justifican tales situaciones, propuestas, etc.
  • CEP3 - Capacidad de aplicacion de las tecnicas de Inteligencia Artificial en entornos tecnologicos e industriales para la mejora de la calidad y la productividad.
  • CEP5 - Capacidad de disenar nuevas herramientas informaticas y nuevas tecnicas de Inteligencia Artificial en el ejercicio profesional.

 

Competències relacionades


  • CT7 - Capacidad de analisis y resolucion de problemas tecnicos complejos.
  • CEA6 - Capacidad de comprender los principios básicos de funcionamiento de las técnicas de Visión Computacional, y saber utilizarlas en el entorno de un sistema o servicio inteligente.
  • CEA7 - Capacidad de comprender la problemática, y las soluciones a los problemas en la práctica profesional de la aplicación de la Inteligencia Artificial en el entorno empresarial e industrial.
  • CG1 - Capacitat per a projectar, dissenyar i implantar productes, processos, serveis i instal·lacions en tots els àmbits de la Intel·ligència Artificial.
  • CG3 - Capacitat per a la modelització, càlcul, simulació, desenvolupament i implantació en centres tecnològics i d’enginyeria d’empresa, particularment en tasques de recerca, desenvolupament i innovació en tots els àmbits relacionats amb la Intel·ligència Artificial.

 

 

 

 

Learning objectives

 

Referring to knowledge

This course introduces the main aspects of computational vision, from fundamentals on image formation and basic image operations until scene recognition, going through the main problems in computer vision: segmentation, motion estimation, pattern recognition and object tracking. The latest state-of-the-art methods will be revised for the computer vision problems and methods will be developed to solve some of these problems.

 

 

Teaching blocks

 

1. Fundamentals of Computer Vision

1.1. Filters and linear operations

2. Image segmentation (kmeans and meanshift).

3. Object/face recognition by eigenfaces.

4. Object detection by Adaboost.

5. Deep learning: fundamentals

6. Image classification by Convolutional Neural Networks

7. Object detection: Yolo, RCNN, etc.

8. Image segemntation by Unet

 

 

Teaching methods and general organization

 

The course will be divided in a series of theory and practical sessions: 

- Participatory theory sessions in which new concepts are introduced and discussed between students. Group discussion is strongly encouraged. Textbook chapters and research papers will be provided to facilitate debate and exchange of ideas. 

- Practical sessions are devoted to solve problems, designing methods and developing prototypes. These sessions allow students to put into practice previously introduced concepts to gain further insight. 

 

 Teaching will follow a face-to-face (in-person), virtual (online) or mixed model according to the instructions of the competent authorities. In principle, we expect to follow the mixed teaching model for the 2020-21 academic year.

 * In case of in-person teaching:

The weekly schedule of in-person activities is distributed in three hours of theory class that includes practice.

* In case of mixed teaching required by the health situation (this is the expected model):

If the health situation allows it and the necessary conditions are met, we expect to have between 50% and 70% of in-person activities. In general, when having an occupancy rate of 50%, students will attend in-person for a week and will follow class on streaming for the following week.

In case on-line teaching is required by the health situation: The time ranges of mixed teaching are maintained but all teaching will be carried out in an online format, prioritizing synchronous sessions for the subject dynamization.

As far as possible, the gender perspective will be incorporated in the development of the subject. In addition, teachers will be attentive to those specific gender needs that students may raise, such as being able to choose a partner of the same gender if group work is carried out or being able to pose challenges against the gender gap.

 

 

Official assessment of learning outcomes

 

Students will be assessed on final exam, in-class oral presentations (if it is planned for the academic year) and their work in practical assignments. Typically, marks for final exam and oral presentations will be awarded on an individual basis, whereas marks for practical assignments will be based on an assessment of the whole group (2 persons per grup). The weighting of the final grade will be proportional to the respective workloads of the two tasks and a final exam.

Depending on the health situation, the evaluable activities can be: face-to-face tests, synchronous online tests or work delivery.