Contributions to 3D Data Registration and Representation

Nowadays, new computers generation provides a high performance that enables to build computationally expensive computer vision applications applied to mobile robotics. Building a map of the environment is a common task of a robot and is an essential part to allow the robots to move through these environments. Traditionally, mobile robots used a combination of several sensors from different technologies. Lasers, sonars and contact sensors have been typically used in any mobile robotic architecture, however color cameras are an important sensor due to we want the robots to use the same information that humans to sense and move through the different environments. Color cameras are cheap and flexible but a lot of work need to be done to give robots enough visual understanding of the scenes. Computer vision algorithms are computational complex problems but nowadays robots have access to different and powerful architectures that can be used for mobile robotics purposes. The advent of low-cost RGB-D sensors like Microsoft Kinect which provide 3D colored point clouds at high frame rates made the computer vision even more relevant in the mobile robotics field. The combination of visual and 3D data allows the systems to use both computer vision and 3D processing and therefore to be aware of more details of the surrounding environment. The research described in this thesis was motivated by the need of scene mapping. Being aware of the surrounding environment is a key feature in many mobile robotics applications from simple robotic navigation to complex surveillance applications. In addition, the acquisition of a 3D model of the scenes is useful in many areas as video games scene modeling where well-known places are reconstructed and added to game systems or advertising where once you get the 3D model of one room the system can add furniture pieces using augmented reality techniques. In this thesis we perform an experimental study of the state-of-the-art registration methods to find which one fits better to our scene mapping purposes. Different methods are tested and analyzed on different scene distributions of visual and geometry appearance. In addition, this thesis proposes two methods for 3d data compression and representation of 3D maps. Our 3D representation proposal is based on the use of Growing Neural Gas (GNG) method. This Self-Organizing Maps (SOMs) has been successfully used for clustering, pattern recognition and topology representation of various kind of data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models without considering time constraints. Self-organising neural models have the ability to provide a good representation of the input space. In particular, the Growing Neural Gas (GNG) is a suitable model because of its flexibility, rapid adaptation and excellent quality of representation. However, this type of learning is time consuming, specially for high-dimensional input data. Since real applications often work under time constraints, it is necessary to adapt the learning process in order to complete it in a predefined time. This thesis proposes a hardware implementation leveraging the computing power of modern GPUs which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). Our proposed geometrical 3D compression method seeks to reduce the 3D information using plane detection as basic structure to compress the data. This is due to our target environments are man-made and therefore there are a lot of points that belong to a plane surface. Our proposed method is able to get good compression results in those man-made scenarios. The detected and compressed planes can be also used in other applications as surface reconstruction or plane-based registration algorithms. Finally, we have also demonstrated the goodness of the GPU technologies getting a high performance implementation of a CAD/CAM common technique called Virtual Digitizing.

Mental evolution and development: Evidence for secondary representation in children, great apes, and other animals

Recent interest in the development and evolution of theory of mind has provided a wealth of information about representational skills in both children and animals, According to J, Perrier (1991), children begin to entertain secondary representations in the 2nd year of life. This advance manifests in their passing hidden displacement tasks, engaging in pretense and means-ends reasoning, interpreting external representations, displaying mirror self-recognition and empathic behavior, and showing an early understanding of mind and imitation. New data show a cluster of mental accomplishments in great apes that is very similar to that observed in 2-year-old humans. It is suggested that it is most parsimonious to assume that this cognitive profile is of homologous origin and that great apes possess secondary representational capacity. Evidence from animals other than apes is scant. This analysis leads to a number of predictions for future research.

Somatotopic organization and cortical projections of the ventrobasal complex of the flying fox: an "inverted" wing representation in the thalamus

The present study investigates the somatotopic representation in the somatosensory thalamus of a megachiropteran bat. Using standard microelectrode mapping techniques, representational maps were generated for the ventrobasal (Vb) and posterior (Po) thalamic complexes of the Grey-headed flying fox. Anatomical tracing from neocortical injections provided additional data confirming the somatotopy found physiologically. A full representation of the body surface innervated by the trigeminal and spinal nerves was found. However, in contrast with other mammals, the representations of the forelimb and adjacent thoracic trunk within the thalamus were inverted. This means that the distal portions of the wing membrane and the tips of the digits were represented dorsally in Vb, and the thoracic trunk was represented ventrally In Po the digit tips were represented in the ventral most portion and the thoracic trunk in the dorsal portion of the nucleus. These results are discussed in relation to similarities of megachiropteran somatosensory thalamic nuclei to those of other mammalian species and in relation to the formation of thalamic somatotopic maps and fiber sorting.

Eigenvalue computations in the context of data-sparse approximations of integral operators

In this work, we consider the numerical solution of a large eigenvalue problem resulting from a finite rank discretization of an integral operator. We are interested in computing a few eigenpairs, with an iterative method, so a matrix representation that allows for fast matrix-vector products is required. Hierarchical matrices are appropriate for this setting, and also provide cheap LU decompositions required in the spectral transformation technique. We illustrate the use of freely available software tools to address the problem, in particular SLEPc for the eigensolvers and HLib for the construction of H-matrices. The numerical tests are performed using an astrophysics application. Results show the benefits of the data-sparse representation compared to standard storage schemes, in terms of computational cost as well as memory requirements.

Semi-automatic 3D Segmentation Of Costal Cartilage In CT Data From Pectus Excavatum Patients

One of the current frontiers in the clinical management of Pectus Excavatum (PE) patients is the prediction of the surgical outcome prior to the intervention. This can be done through computerized simulation of the Nuss procedure, which requires an anatomically correct representation of the costal cartilage. To this end, we take advantage of the costal cartilage tubular structure to detect it through multi-scale vesselness filtering. This information is then used in an interactive 2D initialization procedure which uses anatomical maximum intensity projections of 3D vesselness feature images to efficiently initialize the 3D segmentation process. We identify the cartilage tissue centerlines in these projected 2D images using a livewire approach. We finally refine the 3D cartilage surface through region-based sparse field level-sets. We have tested the proposed algorithm in 6 noncontrast CT datasets from PE patients. A good segmentation performance was found against reference manual contouring, with an average Dice coefficient of 0.75±0.04 and an average mean surface distance of 1.69±0.30mm. The proposed method requires roughly 1 minute for the interactive initialization step, which can positively contribute to an extended use of this tool in clinical practice, since current manual delineation of the costal cartilage can take up to an hour.

Grid structure impact in sparse point representation of derivatives

In the Sparse Point Representation (SPR) method the principle is to retain the function data indicated by significant interpolatory wavelet coefficients, which are defined as interpolation errors by means of an interpolating subdivision scheme. Typically, a SPR grid is coarse in smooth regions, and refined close to irregularities. Furthermore, the computation of partial derivatives of a function from the information of its SPR content is performed in two steps. The first one is a refinement procedure to extend the SPR by the inclusion of new interpolated point values in a security zone. Then, for points in the refined grid, such derivatives are approximated by uniform finite differences, using a step size proportional to each point local scale. If required neighboring stencils are not present in the grid, the corresponding missing point values are approximated from coarser scales using the interpolating subdivision scheme. Using the cubic interpolation subdivision scheme, we demonstrate that such adaptive finite differences can be formulated in terms of a collocation scheme based on the wavelet expansion associated to the SPR. For this purpose, we prove some results concerning the local behavior of such wavelet reconstruction operators, which stand for SPR grids having appropriate structures. This statement implies that the adaptive finite difference scheme and the one using the step size of the finest level produce the same result at SPR grid points. Consequently, in addition to the refinement strategy, our analysis indicates that some care must be taken concerning the grid structure, in order to keep the truncation error under a certain accuracy limit. Illustrating results are presented for 2D Maxwell's equation numerical solutions.

Analysis and visualization of seismic data using mutual information

Seismic data is difficult to analyze and classical mathematical tools reveal strong limitations in exposing hidden relationships between earthquakes. In this paper, we study earthquake phenomena in the perspective of complex systems. Global seismic data, covering the period from 1962 up to 2011 is analyzed. The events, characterized by their magnitude, geographic location and time of occurrence, are divided into groups, either according to the Flinn-Engdahl (F-E) seismic regions of Earth or using a rectangular grid based in latitude and longitude coordinates. Two methods of analysis are considered and compared in this study. In a first method, the distributions of magnitudes are approximated by Gutenberg-Richter (G-R) distributions and the parameters used to reveal the relationships among regions. In the second method, the mutual information is calculated and adopted as a measure of similarity between regions. In both cases, using clustering analysis, visualization maps are generated, providing an intuitive and useful representation of the complex relationships that are present among seismic data. Such relationships might not be perceived on classical geographic maps. Therefore, the generated charts are a valid alternative to other visualization tools, for understanding the global behavior of earthquakes.

Data gathering approach in dense sensor networks

Sensor/actuator networks promised to extend automated monitoring and control into industrial processes. Avionic system is one of the prominent technologies that can highly gain from dense sensor/actuator deployments. An aircraft with smart sensing skin would fulfill the vision of affordability and environmental friendliness properties by reducing the fuel consumption. Achieving these properties is possible by providing an approximate representation of the air flow across the body of the aircraft and suppressing the detected aerodynamic drags. To the best of our knowledge, getting an accurate representation of the physical entity is one of the most significant challenges that still exists with dense sensor/actuator network. This paper offers an efficient way to acquire sensor readings from very large sensor/actuator network that are located in a small area (dense network). It presents LIA algorithm, a Linear Interpolation Algorithm that provides two important contributions. First, it demonstrates the effectiveness of employing a transformation matrix to mimic the environmental behavior. Second, it renders a smart solution for updating the previously defined matrix through a procedure called learning phase. Simulation results reveal that the average relative error in LIA algorithm can be reduced by as much as 60% by exploiting transformation matrix.

Scalable data acquisition for densely instrumented cyber-physical systems

Consider the problem of designing an algorithm for acquiring sensor readings. Consider specifically the problem of obtaining an approximate representation of sensor readings where (i) sensor readings originate from different sensor nodes, (ii) the number of sensor nodes is very large, (iii) all sensor nodes are deployed in a small area (dense network) and (iv) all sensor nodes communicate over a communication medium where at most one node can transmit at a time (a single broadcast domain). We present an efficient algorithm for this problem, and our novel algorithm has two desired properties: (i) it obtains an interpolation based on all sensor readings and (ii) it is scalable, that is, its time-complexity is independent of the number of sensor nodes. Achieving these two properties is possible thanks to the close interlinking of the information processing algorithm, the communication system and a model of the physical world.

Assessment of the ensembles regional climate models in the representation of precipitation variability and extremes over Portugal

A new data set of daily gridded observations of precipitation, computed from over 400 stations in Portugal, is used to assess the performance of 12 regional climate models at 25 km resolution, from the ENSEMBLES set, all forced by ERA-40 boundary conditions, for the 1961-2000 period. Standard point error statistics, calculated from grid point and basin aggregated data, and precipitation related climate indices are used to analyze the performance of the different models in representing the main spatial and temporal features of the regional climate, and its extreme events. As a whole, the ENSEMBLES models are found to achieve a good representation of those features, with good spatial correlations with observations. There is a small but relevant negative bias in precipitation, especially in the driest months, leading to systematic errors in related climate indices. The underprediction of precipitation occurs in most percentiles, although this deficiency is partially corrected at the basin level. Interestingly, some of the conclusions concerning the performance of the models are different of what has been found for the contiguous territory of Spain; in particular, ENSEMBLES models appear too dry over Portugal and too wet over Spain. Finally, models behave quite differently in the simulation of some important aspects of local climate, from the mean climatology to high precipitation regimes in localized mountain ranges and in the subsequent drier regions.

Visualization of clusters in geo-referenced data using three-dimensional self-organizing maps

Dissertação apresentada como requisito parcial para obtenção do grau de Mestre em Estatística e Gestão de Informação

Scenarios Generation for Multi-Agent simulation of Electricity Markets based on Intelligent Data Analysis

This document presents a tool able to automatically gather data provided by real energy markets and to generate scenarios, capture and improve market players’ profiles and strategies by using knowledge discovery processes in databases supported by artificial intelligence techniques, data mining algorithms and machine learning methods. It provides the means for generating scenarios with different dimensions and characteristics, ensuring the representation of real and adapted markets, and their participating entities. The scenarios generator module enhances the MASCEM (Multi-Agent Simulator of Competitive Electricity Markets) simulator, endowing a more effective tool for decision support. The achievements from the implementation of the proposed module enables researchers and electricity markets’ participating entities to analyze data, create real scenarios and make experiments with them. On the other hand, applying knowledge discovery techniques to real data also allows the improvement of MASCEM agents’ profiles and strategies resulting in a better representation of real market players’ behavior. This work aims to improve the comprehension of electricity markets and the interactions among the involved entities through adequate multi-agent simulation.

Data Mining Approach to support the Generation of Realistic Scenarios for Multi-Agent simulation of Electricity Markets

This paper presents the Realistic Scenarios Generator (RealScen), a tool that processes data from real electricity markets to generate realistic scenarios that enable the modeling of electricity market players’ characteristics and strategic behavior. The proposed tool provides significant advantages to the decision making process in an electricity market environment, especially when coupled with a multi-agent electricity markets simulator. The generation of realistic scenarios is performed using mechanisms for intelligent data analysis, which are based on artificial intelligence and data mining algorithms. These techniques allow the study of realistic scenarios, adapted to the existing markets, and improve the representation of market entities as software agents, enabling a detailed modeling of their profiles and strategies. This work contributes significantly to the understanding of the interactions between the entities acting in electricity markets by increasing the capability and realism of market simulations.

A framework for supporting knowledge representation – an ontological based approach

Dissertação para obtenção do Grau de Mestre em Engenharia Electrotécnica e de Computadores

Cartographic representation of spatiotemporal phenomena

Dissertação para obtenção do Grau de Mestre em Engenharia Informática