|Module Name||Computer Vision|
|ECTS Weighting ||5 ECTS|
|Semester Taught||Semester 1|
|Module Coordinator/s||Prof. Martin Alain|
Module Learning Outcomes
On successful completion of this module, students will be able to:
- Explain Perception, describe low to high level features;
- Understand and apply the mathematics involved in Computer Vision;
- Use programming languages (e.g. Matlab/Octave, Python) for developing applications with Computer Vision libraries and deep learning;
- Design Computer Vision modules as part of Intelligent Systems;
- Discuss critically (with a report, a demo and a presentation) a Computer Vision project.
- Image processing, feature detection and matching, image registration, recognition and segmentation;
- Motion flow and object tracking in video;
- Mathematics for Computer Vision.
Teaching and Learning Methods
Lectures, laboratories (programming) and online (e.g. discussion board).
|Assessment Component||Brief Description||Learning Outcomes Addressed||% of Total||Week Set||Week Due|
|A||Weekly Short Quizzes for Week k=1 (first teaching week) to k=11 (except reading week k=7).||L01/LO2/LO3/L|
|5% for each (x10 = 50%)||k||k+1|
|B||Computer Vision without deep|
|LO2/LO3/LO4||20%||Week 3||5/11 (week k=8)|
|C||Computer Vision with deep|
Contact Hours and Indicative Student Workload
|Contact Hours (scheduled hours per student over full module), broken down by:||22 hours|
|Independent Study (outside scheduled contact hours), broken down by:||94 hours|
|Preparation for classes and review of material (including preparation for examination, if applicable)||42 hours|
|Completion of assessments (including examination, if applicable)||52 hours|
|Total Hours||116 hours|
Recommended Reading List
- Computer Vision: Algorithms and Applications, Richard Szeliski, 2021.
- Stanford CS class CS231n: Convolutional Neural Networks for Visual Recognition with a Youtube playlist.
- Computer Vision: Models, Learning, and Inference , Simon J.D. Prince, Cambridge University Press 2012.
- Computer Vision: A Modern Approach, Forsyth and Ponce, Pearson 2012 (available in TCD library).
- Programming Computer Vision with Python, Jan Erik Solem.
- Deep Learning, I. Goodfellow et al., MIT 2016 press.
Prerequisite modules: Mathematics (e.g. Linear algebra, Optimisation), statistics, machine learning, programming (e.g. Python), signal processing.
Other/alternative non-module prerequisites: Some computer programming experience.