Displaying 204 resources
Structure from Motion
Image-based 3D Shape Reconstruction, Stereo and multiview imaging principles will be overviewed. The following topics will be covered: Feature extraction and matching. Triangulation and Bundle Adjustment. Mathematics of structure from motion.
Lecture notes on reinforcement learning
Reinforcement learning is an appealing subject. Firstly, it is a very general concept: an agent interacts with an environment with the goal to maximize
the rewards it receives from the environment.
AI, Large Language Models and University Education
This lecture overviews the impact of AI, and Large Language Models, particularly of ChatGPT language model in Education, e.g., in Universities. First it present the ChatGPT transformer structure and ChatGPT training.
A Survey of Large Language Models
This survey highlights the complexity of language and the challenge of developing AI algorithms capable of understanding and generating language.
Real-World Learning
In the past decade, artificial intelligence has made remarkable progress, achieving feats like self-driving cars, defeating go-masters, and precise image categorisation through supervised deep learning with labelled data.
Digital Image Filtering
This lecture overviews Image Filtering, which is very important to ensure high image quality and image denoising. It covers the following topics in detail: Image noise. 2D FIR filters, including Moving average filters.
3D Road Surface Reconstruction
This lecture overviews 3D Road Surface Reconstruction that has many applications in autonomous car vision and smart city infrastructure inspection.
3D Image and Shape Compression
This lecture overviews 3D Image and Shape Compression hat has many applications in stereo imaging, cinema and 3D TV.
Stereotypes in Language & Computational Language Models
Combined knowledge from linguistics, psychology, and natural language processing.
3D Image Registration
This lecture overviews 3D Image Registration that has many applications in computer vision, and 3D medical imaging. It covers the following topics in detail: 2D and 3D rotations and translations, ICP algorithm, SVD 3D Point Cloud Registration.
Attention and Transformers Networks
In this lecture, the limitations of Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs) in effectively processing sequences are emphasized.
Drone Vision for Infrastructure Inspection
This lecture overviews the use of drones for infrastructure inspection and maintenance. Various types of inspection, e.g., using visual cameras, LIDAR or thermal cameras are reviewed. Primary application area is electric line inspection.