Checking date: 24/04/2024


Course: 2024/2025

Computer Vision
(19286)
Master in Machine Learning for Health (Plan: 480 - Estudio: 359)
EPI


Coordinating teacher: GONZALEZ DIAZ, IVAN

Department assigned to the subject: Signal and Communications Theory Department

Type: Electives
ECTS Credits: 6.0 ECTS

Course:
Semester:




Requirements (Subjects that are assumed to be known)
Machine Learning Statistical Signal Processing Biomedical Image Processing Deep learning
Objectives
Students are expected to achieve the following goals: - Learn how images are formed both in the human visual system and in digital cameras, attending both to photometric and geometric dimensions. - Know well-known algorithms that implement processes of human vision: extraction of visual features, motion estimation, stereopsis (2-view geometry), structure from motion (n-view geometry) image registration, object tracking, visual recognition. - Apply the knowledge acquired in previous related subjects (e.g. machine learning, deep learning) to the field of computer vision. - Solve practical problems related to computer vision - Design and develop a scientific-technical project that involves the use of computer vision techniques.
Skills and learning outcomes
Description of contents: programme
Block 1: image Formation - Topic 1: Light, shading and color. - Topic 2: Geometric Camera Models and Camera Calibration Block 2: Early Vision - Topic 3: Local Invariant Features - Topic 4: Motion Estimation and Optical Flow - Topic 5: Stereopsis and Structure from Motion Block 3: Mid-level Vision - Topic 6: Object Tracking - Topic 7: Image Registration: rigid and deformable Block 4: High-level Vision - Topic 8: Object Recognition & Image Classification with Convolutional Neural Networks - Topic 9: Other applications of Deep Learning in images: object detection, segmentation, image matching, image generation, video analysis, etc.
Learning activities and methodology
LEARNING ACTIVITIES We will consider the following learning activities: AF3 Theoretical practical classes AF4 Laboratory practices AF5 Tutorials AF6 Team work AF7 Student individual work AF8 Partial and final exams METHODOLOGIES MD1: Class lectures by the professor with the support of computer and audiovisual media, in which the main concepts of the course are developed and complemented with bibliography. MD2: Critical reading of texts recommended by the professor of the course. MD3: Resolution of practical cases, problems, etc. .... posed by the teacher individually or in groups. MD4: Presentation and discussion in class, under the moderation of the professor, of topics related to the content of the course, as well as case studies. MD5: Elaboration of works and reports individually or in groups. TUTORING REGIME There will be 2 hours a week of tutorials for students where the teacher will be available in his office.
Assessment System
  • % end-of-term-examination 0
  • % of continuous assessment (assigments, laboratory, practicals...) 100

Calendar of Continuous assessment


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 may change due academic events or other reasons.