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.

Body image perception in adolescents and concern with weight

In a holistic conception of health, youth health is moderated by their self image and the perception that adolescents have of themselves is conditioned by social and cultural pressure, and low selfesteem is often observed, possibly caused by the way they perceive their own body, having as a consequence, an health proile with morbidities. Recognize the level of youth heath assessing Body Image perception and their concern with weight. It is a descriptive, quantitative and transversal study. Based on a sampling error lower than 5% and a conidence level of 95%, the study was carried out on a sample of 600 adolescents aged between 12 and 18. A self-ad-ministered questionnaire validated for adolescents was conducted by Di Pietro (2002). The sample is composed of 44% male and 56% female adolescents, with an age mean of 15.54. 61.2% of the boys and 83.6% of the girls stated to be concerned with their weight. The main reasons given for this concern were health associated with aesthetics (29.1% of boys and 38.5% of girls). The results show that 12.8% of boys and 23.5% of girls are dissatisied with their body image. The study revealed that the variable gender is statistically moderating in relation to the variables: body image perception and concern with weight: female adolescents show a higher dissatisfaction with their body image (0.003) and a bigger concern with weight (0.000). The results point out towards the need for assessment/ intervention in this population as body image represents a paramount issue in adolescence, with the body image self-perception being strongly associated with the biopsychosocial maturing process, which interferes with their level of health and personal and social development.

DORIS: Processing and management of Sound Velocity Profiles for echosounding applications

If a bathymetric echosounder is the essential device to carry on hydrographic surveys, other external sensors are absolutely also necessary (positioning system, motion unit or sound velocity profiler). And because sound doesn‛t go straight away into the whole bathymetric swath its measurement and processing are very sensitive for all the water column. DORIS is the very answer for an operational sound velocity profile processing.

Parcellation of fMRI datasets with ICA and PLS: a data driven approach

Inter-subject parcellation of functional Magnetic Resonance Imaging (fMRI) data based on a standard General Linear Model (GLM) and spectral clustering was recently proposed as a means to alleviate the issues associated with spatial normalization in fMRI. However, for all its appeal, a GLM-based parcellation approach introduces its own biases, in the form of a priori knowledge about the shape of Hemodynamic Response Function (HRF) and task-related signal changes, or about the subject behaviour during the task. In this paper, we introduce a data-driven version of the spectral clustering parcellation, based on Independent Component Analysis (ICA) and Partial Least Squares (PLS) instead of the GLM. First, a number of independent components are automatically selected. Seed voxels are then obtained from the associated ICA maps and we compute the PLS latent variables between the fMRI signal of the seed voxels (which covers regional variations of the HRF) and the principal components of the signal across all voxels. Finally, we parcellate all subjects data with a spectral clustering of the PLS latent variables. We present results of the application of the proposed method on both single-subject and multi-subject fMRI datasets. Preliminary experimental results, evaluated with intra-parcel variance of GLM t-values and PLS derived t-values, indicate that this data-driven approach offers improvement in terms of parcellation accuracy over GLM based techniques.

Image summarisation: human action description from static images

Dissertação de Mestrado, Processamento de Linguagem Natural e Indústrias da Língua, Faculdade de Ciências Humanas e Sociais, Universidade do Algarve, 2014

Acoustic and device feature fusion for load recognition

Appliance-specific Load Monitoring (LM) provides a possible solution to the problem of energy conservation which is becoming increasingly challenging, due to growing energy demands within offices and residential spaces. It is essential to perform automatic appliance recognition and monitoring for optimal resource utilization. In this paper, we study the use of non-intrusive LM methods that rely on steady-state appliance signatures for classifying most commonly used office appliances, while demonstrating their limitation in terms of accurately discerning the low-power devices due to overlapping load signatures. We propose a multi-layer decision architecture that makes use of audio features derived from device sounds and fuse it with load signatures acquired from energy meter. For the recognition of device sounds, we perform feature set selection by evaluating the combination of time-domain and FFT-based audio features on the state of the art machine learning algorithms. Further, we demonstrate that our proposed feature set which is a concatenation of device audio feature and load signature significantly improves the device recognition accuracy in comparison to the use of steady-state load signatures only.

Robustness comparison of clustering - based vs. non-clustering multi-label classifications for image and video annotations

This paper reports robustness comparison of clustering-based multi-label classification methods versus nonclustering counterparts for multi-concept associated image and video annotations. In the experimental setting of this paper, we adopted six popular multi-label classification Algorithms, two different base classifiers for problem transformation based multilabel classifications, and three different clustering algorithms for pre-clustering of the training data. We conducted experimental evaluation on two multi-label benchmark datasets: scene image data and mediamill video data. We also employed two multi-label classification evaluation metrics, namely, micro F1-measure and Hamming-loss to present the predictive performance of the classifications. The results reveal that different base classifiers and clustering methods contribute differently to the performance of the multi-label classifications. Overall, the pre-clustering methods improve the effectiveness of multi-label classifications in certain experimental settings. This provides vital information to users when deciding which multi-label classification method to choose for multiple-concept associated image and video annotations.

Edge centrality via the Holevo quantity

In the study of complex networks, vertex centrality measures are used to identify the most important vertices within a graph. A related problem is that of measuring the centrality of an edge. In this paper, we propose a novel edge centrality index rooted in quantum information. More specifically, we measure the importance of an edge in terms of the contribution that it gives to the Von Neumann entropy of the graph. We show that this can be computed in terms of the Holevo quantity, a well known quantum information theoretical measure. While computing the Von Neumann entropy and hence the Holevo quantity requires computing the spectrum of the graph Laplacian, we show how to obtain a simplified measure through a quadratic approximation of the Shannon entropy. This in turns shows that the proposed centrality measure is strongly correlated with the negative degree centrality on the line graph. We evaluate our centrality measure through an extensive set of experiments on real-world as well as synthetic networks, and we compare it against commonly used alternative measures.

The average mixing matrix signature

Laplacian-based descriptors, such as the Heat Kernel Signature and the Wave Kernel Signature, allow one to embed the vertices of a graph onto a vectorial space, and have been successfully used to find the optimal matching between a pair of input graphs. While the HKS uses a heat di↵usion process to probe the local structure of a graph, the WKS attempts to do the same through wave propagation. In this paper, we propose an alternative structural descriptor that is based on continuoustime quantum walks. More specifically, we characterise the structure of a graph using its average mixing matrix. The average mixing matrix is a doubly-stochastic matrix that encodes the time-averaged behaviour of a continuous-time quantum walk on the graph. We propose to use the rows of the average mixing matrix for increasing stopping times to develop a novel signature, the Average Mixing Matrix Signature (AMMS). We perform an extensive range of experiments and we show that the proposed signature is robust under structural perturbations of the original graphs and it outperforms both the HKS and WKS when used as a node descriptor in a graph matching task.

Singularity and multifractal characterization of signals with wavelets. Application to clay soil images

In the field of multiscale analysis of signals, including images, the wavelet transform is one of the most attractive and powerful tool due to its ability to focus on signals structures at different scales. Wavelet Transform at different scales is successfully applied to image characterization (which can be applied to a watermarking scheme) and multiscale singularity detection and processing. In this work we show further research of computation of multifractals properties such as the multifractal spectrum (D(alpha)) applied to dye stained images of natural terrain. This can be useful for statically describing preferential flow path geometry.

Into the looking glass: Literacy acquisition and mirror invariance in preschool and first-grade children

At what point in reading development does literacy impact object recognition and orientation processing? Is it specific to mirror images? To answer these questions, forty-six 5- to 7-year-old preschoolers and first graders performed two same–different tasks differing in the matching criterion-orientation-based versus shape-based (orientation independent)-on geometric shapes and letters. On orientation-based judgments, first graders out- performed preschoolers who had the strongest difficulty with mirrored pairs. On shape-based judgments, first graders were slower for mirrored than identical pairs, and even slower than preschoolers. This mirror cost emerged with letter knowledge. Only first graders presented worse shape-based judgments for mirrored and rotated pairs of reversible (e.g., b-d; b-q) than nonreversible (e.g., e-ә) letters, indicating readers’ difficulty in ignoring orientation contrasts relevant to letters.