On the Exploitation of 3D Straight Lines forActive Mapping and Camera Localization

By |

Human-made environments tend to be structured, i.e., composed mainly of planar surfaces, whose majority are either parallel or perpendicular to each other. Furthermore, those environments lack texture. Traditional methods for Mapping and Localization rely on point features. However, when applying those methods to structured environments, the density of point features may be insufficient for the

Comments Off on On the Exploitation of 3D Straight Lines forActive Mapping and Camera Localization

Application-friendly methods for distributed optimization

By |

With the rise of big data, and of the internet of things, distributed applications are becoming increasingly more popular. Distributed optimization focuses on finding the minimizer of a cost which is the sum of several functions. Each of these functions is stored within an agent that is physically separated from the others. Because no agent

Comments Off on Application-friendly methods for distributed optimization

Learning Object Affordances via Interaction and Observation

By |

Affordances are defined as action opportunities that an environment offers an agent. This concept, introduced by American psychologist J. J. Gibson in the 70s, provides a non-reductionist explanation regarding visual perception in animals by placing their motor capabilities as the backbone of perceptual faculties. In addition to its profound impact in psychology and neuroscience, action-derived

Comments Off on Learning Object Affordances via Interaction and Observation

Vision with Plenoptic Cameras

By |

Vision is one of the most important sensing modalities in nature because of the valuable, thorough information it can provide about the environment. Vision sensing can come in different flavors ranging from human vision, where images are perspective views that follow the pinhole model, to insect vision where compound eyes with ommatidia design enable the

Comments Off on Vision with Plenoptic Cameras

Classification of Visual Data with Unreliable Annotations: a Real Case in the Fashion Domain

By |

Image classification is a fundamental Computer Vision task that has become more relevant in our current information-driven society. Despite the recent leap forward in the field brought by deep learning approaches, we identify two main challenging problems that are still unresolved and are currently active research topics: multi-label image classification and classifying in the presence

Comments Off on Classification of Visual Data with Unreliable Annotations: a Real Case in the Fashion Domain

Vision-based control of Unmanned Aerial Vehicles

By |

This thesis proposes novel vision-based controllers for the guidance of Unmanned Aerial Vehicles (UAVs). It considers scenarios involving both single and multiple vehicles. For the case of a single-vehicle, novel Image-based visual servo control (IBVS) approaches are proposed for both fixed-wing and vertical take-off and landing (VTOL) UAVs operating in urban or congested environments. Navigation

Comments Off on Vision-based control of Unmanned Aerial Vehicles