— The use of semantic information in robotics is an emergent field of research. As a supplement to other types of information, like geometrical or topological, semantics can improve mobile robot reasoning or knowledge inference, and can also facilitate human-robot communication. These abilities are particularly relevant for robots intended to operate in… (More)
High resolution images provided by latest missions such as QuickBird, Ikonos or OrbView have opened a new and important age in the remote sensing field, mainly in those applications where is crucial to extract detailed information such as buildings, streets, vehicles, etc. The improvement in resolution makes also that something inherent to an image as… (More)
True-orthophotographs are now being widely used in some areas, proving already as very valuable documents even replacing maps being more complete, reliable and objective. But they are still hard to produce with enough quality for other uses and scales, such as in architecture and conservation. Most works in these fields are just approximate… (More)
Foreword There is a growing tendency to introduce high-level semantic information into robotic systems. This tendency is visible in different forms within several areas of robotics. Recent work in mapping and localization tries to extract semantically meaningful structures from sensor data during map building, or to use semantic knowledge in the map… (More)
One of the wordl's major problems is the scarcity of water , due mainly to the unmeasured water consumption and the waste of this vital element. This paper describes a modular water management system, which helps not only in monitoring consumption but also in finding water leaks and water pollution.
In remote sensing, because of the wide diversity of image characteristics (size, spatial and radiometric resolution, terrain relief, observation poses, etc.), image registration methods that may work well on certain satellite images will not produce acceptable results for others, requiring more powerful techniques. A variety of registration techniques for… (More)
When estimating logistic-normal models, the integral appearing in the marginal likelihood is analytically intractable, so that numerical methods such as Gauss-Hermite quadrature (GH) are needed. When the dimensionality increases, the number of quadrature points becomes too high. A possible solution can be found among the Quasi-Monte Carlo (QMC) methods,… (More)