Eduardo Zalama Casanova

Obtaining 3D models of indoor environments with a mobile robot by estimating local surface directions

Abstract In this paper a method for obtaining the location, size and shape of main surfaces in an environment, from points measured by a laser scanner on board a mobile robot, is presented. The most likely orientation of the surface normal is first calculated at every point, from points in an adaptive-radius neighboring region. Then, similar planes are merged under orientation and distance criteria. Finally, points are projected onto the planes they belong to, and the corresponding boundaries are obtained from Voronoi’s diagram. A simple representation of the environment is thus obtained, which matches the real topology thanks to the detailed prior analysis of the local geometry at every point.

Hand Gesture Recognition for Deaf People Interfacing

In this paper, an approach for deaf-people interfacing using computer vision is presented. The recognition of alphabetic static signs of the Spanish sign language is addressed. The proposed approach combines a number of norms to evaluate the distance of the current sign, to the sign models stored in a database (a dictionary). This solution leads to a largely selective criterion. The method is simple enough to provide real-time recognition, and works suitably for most letters

Moisture detection in heritage buildings by 3D laser scanning

Moisture is one of the main factors in the deterioration of heritage buildings, causing mould, unwanted parasites, and the decanting of salts, which, in turn, aggravate such degradation. The existence of moisture not only affects the building aesthetically, but is also evidence of bad conservation conditions. It is thus extremely important to verify and assess the extent of the moisture, even though it may not be confirmed by mere visual inspection. This article describes an innovative and straightforward procedure to automatically show where moisture appears, as well as the affected area. The procedure is based on the use of 3D laser scanner surveying data for documentation purposes of historic buildings. Data are processed off-line in order to analyse the laser reflectivity level. The method is not intrusive, allows large areas to be covered in a short time, and does not interact with the materials, which makes it optimal for application to these special buildings. Hence, professionals of the conservation sector will have objective and comprehensive information on moisture damage, helping them to take decisions on the action to be undertaken. The results achieved in the Cathedral of Ciudad Rodrigo (Spain) are shown to demonstrate the utility of the proposed method.

Using the Big Data generated by the Smart Home to improve energy efficiency management

A Smart Home is able to generate energy-related values such as electricity consumption, temperature, or luminosity without higher infrastructure requirements. The main aim of this research is to extract information from that raw data that could contribute to improving the energy efficiency management. This paper presents a system which, using different Machine Learning approaches to learn about the users’ consumption habits, is able to generate collaborative recommendations and consumption predictions that help the user to consume better, which will in turn improve the demand curve. Moreover, from consumption values, the system learns to identify devices, enabling the demand to be anticipated. Taking into account the fact that the amount of energy data is increasing in real-time, the use of Big Data techniques will be the key to handling all the operations and one of the more innovative features of the system.

Supporting the Automatic Extraction of HBIM Elements from Point Clouds

The purpose of this paper is just detailing a state-of-the-art procedure for the automatic recognition of specific 3D shapes from point clouds of immovable heritage assets supported on a tailored tool using PLY, PTX and PTS formats as input files. To make this tool functional and widely used, it is currently developed as a plug-in for the well-known and representative REVIT BIM software package.