Checking date: 09/05/2018


Course: 2019/2020

Computer Vision
(12995)
Study: Master in Advanced Communications Technologies (278)
EPI


Coordinating teacher: GONZALEZ DIAZ, IVAN

Department assigned to the subject: Department of Signal and Communications Theory

Type: Electives
ECTS Credits: 6.0 ECTS

Course:
Semester:




Students are expected to have completed
Digital Image Processing, Video Processing or similar.
Competences and skills that will be acquired and learning results.
In this course students will acquire knowledge about Computer Vision (Computer Vision), a subfield of artificial intelligence that combines techniques from various fields such as image processing, pattern recognition and statistical learning . To this end, the course will begin revisiting the traditional field of image processing, to then study modern methods for automatic image acquisition, processing , analysis and understanding. Therefore, taking the Human Visual System (HVS) as reference , the processing pipeline is organized into three levels: 1. Low Vision : working with pixels 2. Vision average : from pixels to segments, from motion vectors to object trajectories . 3. High Level Vision : understanding the content of images.
Description of contents: programme
The course consists of the following chapters: 1.- Introduction to Computer Vision 2.- Image Formation and Image Models 3.- Basic Image Processing 4.- Feature Detection and Matching (I) 5.- Dense Motion Estimation and Parameterization 6.- Geometric Camera Models and Stereoscopic Vision 7.- Image Segmentation 8.- Object Tracking 9.- Image Retrieval 10.- Image Classification & Object Detection
Learning activities and methodology
The course will combine lectures with lab sessions where students will experiment with the techniques seen in theory, as well as apply them to problems of interest.
Assessment System
  • % end-of-term-examination 0
  • % of continuous assessment (assigments, laboratory, practicals...) 100
Basic Bibliography
  • Forsyth, Ponce. Computer Vision: A Modern Approach. Pearson. 2012
  • Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning. The MIT Press, Cambrigde, Massachussetts, London, England. 2016
  • Richard Hartley & Andrew Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press. 2003
  • Richard Szeliski. Computer Vision: Algorithms and Applications. Springer-Verlag. 2011

The course syllabus and the academic weekly planning may change due academic events or other reasons.