Ir a cuerpo Ir a Estudios, Gobernanza y organización
Logo UA
Realizar búsqueda
Course description
  ADVANCED ARTIFICIAL VISION

Competencies and objectives

 

Course context for academic year 2020-21

The subject Advanced Computer Vision deals with methods of artificial intelligence applied to automation and robotics. These methods, mainly of deep learning, will allow to be able to recognize objects and to extract information about them.

The subject is optional and it is recommended to have taken another optional subject, Machine learning

 

 

Course content (verified by ANECA in official undergraduate and Master’s degrees)

General Competences:>>Instrumental

  • CG1 : Advise on the choice, acquisition, and implementation of robotic and/or automated systems for different applications.
  • CG2 : Make decisions in the design and planning of a robotics and/or automation project, taking into account quality and environmental criteria.
  • CG3 : Implement and maintain robotics and/or automation projects that satisfy the requirements of industrial or service applications.
  • CG6 : Analyse, synthesise problems and make decisions.

 

General Competences:>>Interpersonal

  • CG10 : Critical reasoning.

 

General Competences:>>Systematic

  • CG12 : Capacity to apply the knowledge acquired to real situations.
  • CG13 : Capacity to work and learn autonomously.
  • CG14 : Capacity to adapt to new situations, promoting creativity and an entrepreneurial spirit.

 

Specific Competences:>>Robotics

  • CER010 : Conocer y saber aplicar las principales técnicas de aprendizaje y Deep learning en sistemas robóticos.

 

Specific Competences:>>Vision

  • CEVI1 : Analyse and know how to apply tools and techniques that allow visual information to be gathered and processed and know which are the best for the particular field of application and context.
  • CEVI4 : Apply specific methods, techniques and instruments for the acquisition and formation of images.
  • CEVI5 : Conocer y aplicar métodos, técnicas e instrumentos de aprendizaje automático y Deep learning en visión artificial.

 

Specific Competences:>>Sensory

  • CESE1 : Be able to select the best characteristics for perception systems, according to application in different contexts and areas of industrial or service automation.
  • CESE2 : Analyse and understand the importance and applicability of perception systems in sensorisation processes for robotic and automatic systems.
  • CESE3 : Be able to configure sensors, hardware and software, as well as all the elements making up perception systems.
  • CESE4 : Analyse and optimise the design of a measurement acquisition system to obtain the required precision and accuracy.
  • CESE5 : Evaluate the importance of sensorial system measurement limits on the significance of the results obtained.

 

 

 

Learning outcomes (Training objectives)

No data

 

 

Specific objectives stated by the academic staff for academic year 2020-21

  • To know the different schemes used in artificial vision for object recognition.
  • To know how to develop schemes that allow the automatic labelling of objects in an image.
  • To know the different techniques that allow depth estimation from a 2D image.
  • To be able to distinguish the movement of a human with vision, so that it can be tracked in the image.
  • To know how to define artificial intelligence schemes based on antagonistic generative networks.
  • Knowing different advanced artificial vision applications in the industry and being able to propose similar applications.

 

 

 

General

Code: 37817
Lecturer responsible:
CAZORLA QUEVEDO, MIGUEL ANGEL
Credits ECTS: 3,00
Theoretical credits: 0,44
Practical credits: 0,76
Distance-base hours: 1,80

Departments involved

  • Dept: SCIENCE OF COMPUTING AND ARTIFICIAL INTELLIGENCE
    Area: SCIENCE OF COMPUTING AND ARTIFICIAL INTELLIGENCE
    Theoretical credits: 0,44
    Practical credits: 0,76
    This Dept. is responsible for the course.
    This Dept. is responsible for the final mark record.

Study programmes where this course is taught