Course content

Review of vision systems

• Image formation (light, colour, optics, cameras)
• Digital images (sampling, quantisation, colour spaces)

Visual data processing

• Transformations, filtering and feature extraction
• Feature visualisation techniques
• Density estimation, clustering and classification

Optimisation

• Optimisation basics

Computer vision

• Modeling and optimisation basics
• Object detection/recognition
• Tracking
• Video understanding
• Imaging with multiple cameras
• Illuminant invariance

Deep learning for computer vision

• Overview of state-of-the-art machine learning techniques
• Explainable AI basics for Computer Vision

Learning outcome

At the end of the semester, a successful student will have knowledge of:

• Vision systems (basics)
• Feature extraction and analysis for images and videos
• Optimisation techniques for model training
• Classical computer vision techniques for object detection, recognition, tracking and scene understanding.
• Deep learning for computer vision (basics)

Students will have developed the skills required to design simple machine/robot vision systems and to extract basic knowledge from digital images and videos. Students will also develop Python programming skills through assignments and project work.

Learning methods and activities

Learning activities will be in the form of interactive lectures, programming assignments and project work.

Compulsory assignments

• Compulsory assignment

Specific conditions

Recommended previous knowledge

Basic knowledge of image processing and/or computer vision