Courses / Module

On successful completion of the module, students should be able to:

• Mathematically model the image formation process, and calibrate a given camera using this model.
• Describe the different types of image sensors and identify a suitable camera setup based on the requirements of a computer vision system.
• Explain how histograms and kernel density estimation techniques can be used to solve a range of problems in computer vision.
• Implement the 2D convolution and correlation operations and describe the mathematical properties of these operations.
• Describe, compare, and implement approaches to image contour extraction.
• Explain and contrast approaches to interest point extraction, description, and matching.
• Understand the fundamentals of machine learning and deep neural networks and their application in the field of computer vision.

Delivery methods	Hours
Lectures	24
Labs / Practicals	0
Tutorials	0
Planned learning activities	0
Independent student activities	101
Total	125

• Module Graded (numeric value) or Ungraded (Pass/Not Passed): Graded
• Continuous Assessment detail(s): Continuous Assessment: up to 20%.

Assessment type	Options	Weighting	Duration
Continuous Assessment		20%
University scheduled written examination	On-campus	80%	120 minutes
Other		0%
Total		100%	120 minutes

• Pass standard: 40%
• Could the result of this module be capped? No

• Are supplemental/resit registrations permitted? Yes
• University scheduled written examination (Autumn): 120 minutes, On-campus

• MT101SC (or equivalent) and MT113SC (or equivalent)

Computer Vision: Algorithms and Applications 2^nd Edition, Richard Szeliski, Springer; 2nd ed. 2022 edition. ISBN 978-3030343712.

Dive into Deep Learning, Aston Zhang, Zack C. Lipton, Mu Li, Alex J. Smola, ¿ Cambridge University Press. ISBN ¿ 978-1009389433.

Computer Vision: A Modern Approach David A. Forsyth and Jean Ponce, Prentice Hall, 2003. ISBN 0-12-085198-1.

For a full timetable search, go to NUIM Timetable. Venue locations can be found here.