Computer Vision

Recommended Prerequisites

Differential and Integral Calculus, Linear Algebra, Optimization. Programming in Matlab and/or Pyton. Working knowledge of English. 

Teaching Methods

Teaching will be essentially experimental with the development of Computer Vision applications. The lectures will consist in the description and analysis of the methods, techniques and algorithms that will be used in each of the experimental examples.

Learning Outcomes

The objectives include the acquisition of knowledge related to the execution of Computer Vision applications using Deep Learning tools. Upon completion of this curricular unit the student will acquire skills that will allow him/her to apply machine learning techniques, in particular, deep learning, to  computer vision applications that require entity/object detection and recognition, semantic segmentation, motion and optical flow analysis, pose estimation and SfM-Structure from Motion.

Work Placement(s)

No

Syllabus

Introduction to Computer Vision. Review of the fundamentals of Deep Learning. Image classification. Object detection and recognition. Optical flow. Visual Object tracking. Pose estimation. "SfM-Structure from Motion". 

Assessment Methods

Assessment
Laboratory work or Field work: 50.0%
Project: 50.0%

Bibliography

“Computer Vision: Algorithms and Applications”, 2nd ed, Szeliski.

“Deep Learning”, Ian Goodfellow, Yoshua Bengio, Aaron Courville

"Deep Learning for Computer Vision - Image classification, object detection and face recognition in Python", Jason Brownlee, Machine Learning Mastery, 2019.