Computer Vision

Target audience

Participants interested in understanding and applying core computer vision and deep learning methods to analyse, interpret, and generate visual content. The course is particularly suited to those who want to develop practical skills in Python and PyTorch for tasks such as image classification, segmentation, object detection, anomaly detection, and generative AI.

Intended Learning Outcomes

At the end of the course, participants will be able to:

• Understand digital images and 3D sensing: explain how images are represented as numerical data, including RGB channels, depth images, point clouds, and common 3D sensing technologies.

• Apply image-processing techniques in Python and analyse colour channels and histograms, manage noise, image compositing, and metadata.

• Develop deep-learning models for visual recognition, training and evaluating convolutional neural networks for image classification, semantic segmentation, object detection, and anomaly detection using Python and PyTorch.

• Recognise overfitting, apply data augmentation and appropriate evaluation metrics, and use visualisation techniques to interpret model predictions.

• Explore generative and vision–language AI

Estimated Time for Completion

12 hours

Level

Level 6: Bachelor’s degree (first cycle)

Type of the assessment

Quizzes and project evaluation

Form of participation in the learning activity

Asynchronous learning (videos, quizzes, exercises)
Live training workshop 
Project work in groups

Pre-requisites

Basic knowledge of Python programming, including data structures, functions, and the use of libraries.
Basic familiarity with mathematics and linear algebra, including vectors, matrices, and basic probability.
No previous experience in computer vision or deep learning is required.