Autonomous Systems Sensors
This lecture overviews Autonomous Systems Sensors that has many applications in Autonomous robots, cars, vessels and drones. It covers the following topics in detail: GPS, RTK-GPS, IMU, RFID Sensors, mono/stereo and event cameras, lidars, inductive/capacitance proximity sensors, Ultrasonic sensors.
Should you require access to the resource, please contact the author directly.
Attention and Transformers Networks in Computer Vision
In this lecture focused on Transformers in the field of computer vision, the limitations of Convolutional Neural Networks (CNNs) are emphasized. While CNNs have been the dominant architecture for visual tasks, they face challenges in capturing long-range dependencies and handling variable-sized inputs. However, recent research has shown promising results by combining convolutional layers with attention mechanisms. Specifically, attention mechanisms allow the model to focus on relevant regions of the image, enabling better contextual understanding. Notably, specific transformer architectures designed for computer vision tasks are introduced, including the Vision Transformer (VIT), which replaces the traditional convolutional layers with self-attention mechanisms, facilitating better global information integration. Furthermore, the Detection Transformer (DETR) introduces transformers to object detection, achieving impressive results by utilizing a set-based representation of objects. Similarly, the Segmentation Transformer (SETR) leverages transformer architectures for semantic segmentation tasks, demonstrating improved performance in capturing fine-grained details. The lecture also explores unsupervised transformers such as the self-distilling DinO, which leverage self-supervision to learn representations without the need for explicit labels. Finally, the Video Vision Transformer (ViViT) extends the transformer architecture to video understanding, capturing spatiotemporal dependencies and achieving state-of-the-art performance. Overall, this lecture showcases the limitations of CNNs in computer vision and explores various transformer-based approaches that have emerged as powerful alternatives in the field, revolutionizing the way visual information is processed and understood.
Should you require access to the resource, please contact the author directly.
Introduction to Autonomous Systems
A fully autonomous system can: a) gain information about the environment, b) work for an extended period without human intervention, c) move either all or part of itself throughout its operating environment without human assistance and d) avoid situations that are harmful to people, property, or itself unless those are part of its design specifications.
Key technologies of autonomous systems are overviewed, notably: mission planning and control, perception and intelligence, embedded computing, swarm systems, communications and societal technologies. Several autonomous system applications are presented, notably a) autonomous cars, b) drones and drone swarms, c) autonomous underwater vehicles d) autonomous marine vessels and e) autonomous robots.
Should you require access to the resource, please contact the author directly.
AI, System Complexity, Life, Intelligence and Environment
This lecture overviews the relation between matter and system complexity on one hand and Life, Intelligence and Environment on the other one. First the theoretical tools (systems, graph and network theory) are overviewed. Then their relation to: a) life structure, c) biological neural networks, c) AI and artificial neural networks, d) social structure and evolution and e) environment is presented. System and matter complexity measures are investigated and the Law of Complexity is presented. Finally, philosophical issues related to life evolution-by-design are introduced.
Should you require access to the resource, please contact the author directly.
What is AI?
The stakes of this lecture are as follows: Can an ordinary person having a high school education and genuine interest understand the basic principles of Artificial Intelligence in just an one-hour lecture? If so, there is hope that she/he can comprehend the current AI Science advances and become an informed citizen that can form her/his opinion about the AI impact in her/his profession (whether they are a taxi driver, artist, manager, or anything else) and even at more broad level. If not, people have to rely on various AI “gurus” and try to sense where AI Science and Engineering is heading. Even worse, they might become technophobic: history has shown that when a society relies on fear and prejudice, it is inevitably doomed (as seen in the Middle Ages and more recently in fascist regimes).
Should you require access to the resource, please contact the author directly.
Digital Painting Analysis and Conservation
This lecture overviews an important topic of Digital Humanities, namely digital painting analysis that has many applications in painting conservation and in the history of arts. It covers the following topics in detail: Structure from Motion (SfM) in 3D monument and painting reconstruction, fragmented artefact re-assembly, IR reflectography and mosaicking, image registration, crack restoration, color restoration. Finally, stylistic painting analysis and computational aesthetics will be overviewed.
Should you require access to the resource, please contact the author directly.