Parallel Computational Intelligence-Based Multi-Camera Surveillance System

In this work, we present a multi-camera surveillance system based on the use of self-organizing neural networks to represent events on video. The system processes several tasks in parallel using GPUs (graphic processor units). It addresses multiple vision tasks at various levels, such as segmentation, representation or characterization, analysis and monitoring of the movement. These features allow the construction of a robust representation of the environment and interpret the behavior of mobile agents in the scene. It is also necessary to integrate the vision module into a global system that operates in a complex environment by receiving images from multiple acquisition devices at video frequency. Offering relevant information to higher level systems, monitoring and making decisions in real time, it must accomplish a set of requirements, such as: time constraints, high availability, robustness, high processing speed and re-configurability. We have built a system able to represent and analyze the motion in video acquired by a multi-camera network and to process multi-source data in parallel on a multi-GPU architecture.

Combining visual features and Growing Neural Gas networks for robotic 3D SLAM

The use of 3D data in mobile robotics provides valuable information about the robot’s environment. Traditionally, stereo cameras have been used as a low-cost 3D sensor. However, the lack of precision and texture for some surfaces suggests that the use of other 3D sensors could be more suitable. In this work, we examine the use of two sensors: an infrared SR4000 and a Kinect camera. We use a combination of 3D data obtained by these cameras, along with features obtained from 2D images acquired from these cameras, using a Growing Neural Gas (GNG) network applied to the 3D data. The goal is to obtain a robust egomotion technique. The GNG network is used to reduce the camera error. To calculate the egomotion, we test two methods for 3D registration. One is based on an iterative closest points algorithm, and the other employs random sample consensus. Finally, a simultaneous localization and mapping method is applied to the complete sequence to reduce the global error. The error from each sensor and the mapping results from the proposed method are examined.

A GIS-based methodology to quantitatively define an Adjacent Protected Area in a shallow karst cavity: The case of Altamira cave

Different types of land use are usually present in the areas adjacent to many shallow karst cavities. Over time, the increasing amount of potentially harmful matter and energy, of mainly anthropic origin or influence, that reaches the interior of a shallow karst cavity can modify the hypogeal ecosystem and increase the risk of damage to the Palaeolithic rock art often preserved within the cavity. This study proposes a new Protected Area status based on the geological processes that control these matter and energy fluxes into the Altamira cave karst system. Analysis of the geological characteristics of the shallow karst system shows that direct and lateral infiltration, internal water circulation, ventilation, gas exchange and transmission of vibrations are the processes that control these matter and energy fluxes into the cave. This study applies a comprehensive methodological approach based on Geographic Information Systems (GIS) to establish the area of influence of each transfer process. The stratigraphic and structural characteristics of the interior of the cave were determined using 3D Laser Scanning topography combined with classical field work, data gathering, cartography and a porosity–permeability analysis of host rock samples. As a result, it was possible to determine the hydrogeological behavior of the cave. In addition, by mapping and modeling the surface parameters it was possible to identify the main features restricting hydrological behavior and hence direct and lateral infiltration into the cave. These surface parameters included the shape of the drainage network and a geomorphological and structural characterization via digital terrain models. Geological and geomorphological maps and models integrated into the GIS environment defined the areas involved in gas exchange and ventilation processes. Likewise, areas that could potentially transmit vibrations directly into the cave were identified. This study shows that it is possible to define a Protected Area by quantifying the area of influence related to each transfer process. The combined maximum area of influence of all the processes will result in the new Protected Area. This area will thus encompass all the processes that account for most of the matter and energy carried into the cave and will fulfill the criteria used to define the Protected Area. This methodology is based on the spatial quantification of processes and entities of geological origin and can therefore be applied to any shallow karst system that requires protection.

Spectral features in isolated neutron stars induced by inhomogeneous surface temperatures

The thermal X-ray spectra of several isolated neutron stars display deviations from a pure blackbody. The accurate physical interpretation of these spectral features bears profound implications for our understanding of the atmospheric composition, magnetic field strength and topology, and equation of state of dense matter. With specific details varying from source to source, common explanations for the features have ranged from atomic transitions in the magnetized atmospheres or condensed surface, to cyclotron lines generated in a hot ionized layer near the surface. Here, we quantitatively evaluate the X-ray spectral distortions induced by inhomogeneous temperature distributions of the neutron star surface. To this aim, we explore several surface temperature distributions, we simulate their corresponding general relativistic X-ray spectra (assuming an isotropic, blackbody emission), and fit the latter with a single blackbody model. We find that, in some cases, the presence of a spurious ‘spectral line’ is required at a high significance level in order to obtain statistically acceptable fits, with central energy and equivalent width similar to the values typically observed. We also perform a fit to a specific object, RX J0806.4−4123, finding several surface temperature distributions able to model the observed spectrum. The explored effect is unlikely to work in all sources with detected lines, but in some cases it can indeed be responsible for the appearance of such lines. Our results enforce the idea that surface temperature anisotropy can be an important factor that should be considered and explored also in combination with more sophisticated emission models like atmospheres.

Learning Probabilistic Features for Robotic Navigation Using Laser Sensors

SLAM is a popular task used by robots and autonomous vehicles to build a map of an unknown environment and, at the same time, to determine their location within the map. This paper describes a SLAM-based, probabilistic robotic system able to learn the essential features of different parts of its environment. Some previous SLAM implementations had computational complexities ranging from O(Nlog(N)) to O(N2), where N is the number of map features. Unlike these methods, our approach reduces the computational complexity to O(N) by using a model to fuse the information from the sensors after applying the Bayesian paradigm. Once the training process is completed, the robot identifies and locates those areas that potentially match the sections that have been previously learned. After the training, the robot navigates and extracts a three-dimensional map of the environment using a single laser sensor. Thus, it perceives different sections of its world. In addition, in order to make our system able to be used in a low-cost robot, low-complexity algorithms that can be easily implemented on embedded processors or microcontrollers are used.

Improving classification using a Confidence Matrix based on weak classifiers applied to OCR

This paper proposes a new feature representation method based on the construction of a Confidence Matrix (CM). This representation consists of posterior probability values provided by several weak classifiers, each one trained and used in different sets of features from the original sample. The CM allows the final classifier to abstract itself from discovering underlying groups of features. In this work the CM is applied to isolated character image recognition, for which several set of features can be extracted from each sample. Experimentation has shown that the use of CM permits a significant improvement in accuracy in most cases, while the others remain the same. The results were obtained after experimenting with four well-known corpora, using evolved meta-classifiers with the k-Nearest Neighbor rule as a weak classifier and by applying statistical significance tests.

Bio-based PLA_PHB plasticized blend films: Processing and structural characterization

Bio-based films formed by poly(lactic acid) (PLA) and poly(3-hydroxybutyrate) (PHB) plasticized with an oligomer of the lactic acid (OLA) were used as supporting matrices for an antibacterial agent (carvacrol). This paper reports the main features of the processing and physico-chemical characterization of these innovative biodegradable material based films, which were extruded and further submitted to filmature process. The effect of the addition of carvacrol and OLA on their microstructure, chemical, thermal and mechanical properties was assessed. The presence of these additives did not affect the thermal stability of PLA_PHB films, but resulted in a decrease in their crystallinity and in the elastic modulus for the active formulations. The obtained results showed the effective presence of additives in the PLA or the PLA_PHB matrix after processing at high temperatures, making them able to be used in active and bio-based formulations with antioxidant/antimicrobial performance.

μ-MAR: Multiplane 3D Marker based Registration for depth-sensing cameras

Many applications including object reconstruction, robot guidance, and. scene mapping require the registration of multiple views from a scene to generate a complete geometric and appearance model of it. In real situations, transformations between views are unknown and it is necessary to apply expert inference to estimate them. In the last few years, the emergence of low-cost depth-sensing cameras has strengthened the research on this topic, motivating a plethora of new applications. Although they have enough resolution and accuracy for many applications, some situations may not be solved with general state-of-the-art registration methods due to the signal-to-noise ratio (SNR) and the resolution of the data provided. The problem of working with low SNR data, in general terms, may appear in any 3D system, then it is necessary to propose novel solutions in this aspect. In this paper, we propose a method, μ-MAR, able to both coarse and fine register sets of 3D points provided by low-cost depth-sensing cameras, despite it is not restricted to these sensors, into a common coordinate system. The method is able to overcome the noisy data problem by means of using a model-based solution of multiplane registration. Specifically, it iteratively registers 3D markers composed by multiple planes extracted from points of multiple views of the scene. As the markers and the object of interest are static in the scenario, the transformations obtained for the markers are applied to the object in order to reconstruct it. Experiments have been performed using synthetic and real data. The synthetic data allows a qualitative and quantitative evaluation by means of visual inspection and Hausdorff distance respectively. The real data experiments show the performance of the proposal using data acquired by a Primesense Carmine RGB-D sensor. The method has been compared to several state-of-the-art methods. The results show the good performance of the μ-MAR to register objects with high accuracy in presence of noisy data outperforming the existing methods.

A Cloud-based Framework for Security Analysis of Browser Extensions

In today's internet world, web browsers are an integral part of our day-to-day activities. Therefore, web browser security is a serious concern for all of us. Browsers can be breached in different ways. Because of the over privileged access, extensions are responsible for many security issues. Browser vendors try to keep safe extensions in their official extension galleries. However, their security control measures are not always effective and adequate. The distribution of unsafe extensions through different social engineering techniques is also a very common practice. Therefore, before installation, users should thoroughly analyze the security of browser extensions. Extensions are not only available for desktop browsers, but many mobile browsers, for example, Firefox for Android and UC browser for Android, are also furnished with extension features. Mobile devices have various resource constraints in terms of computational capabilities, power, network bandwidth, etc. Hence, conventional extension security analysis techniques cannot be efficiently used by end users to examine mobile browser extension security issues. To overcome the inadequacies of the existing approaches, we propose CLOUBEX, a CLOUd-based security analysis framework for both desktop and mobile Browser EXtensions. This framework uses a client-server architecture model. In this framework, compute-intensive security analysis tasks are generally executed in a high-speed computing server hosted in a cloud environment. CLOUBEX is also enriched with a number of essential features, such as client-side analysis, requirements-driven analysis, high performance, and dynamic decision making. At present, the Firefox extension ecosystem is most susceptible to different security attacks. Hence, the framework is implemented for the security analysis of the Firefox desktop and Firefox for Android mobile browser extensions. A static taint analysis is used to identify malicious information flows in the Firefox extensions. In CLOUBEX, there are three analysis modes. A dynamic decision making algorithm assists us to select the best option based on some important parameters, such as the processing speed of a client device and network connection speed. Using the best analysis mode, performance and power consumption are improved significantly. In the future, this framework can be leveraged for the security analysis of other desktop and mobile browser extensions, too.

HELPING YOUTH WITH AUTISM SPECTRUM DISORDER DEVELOP SOCIAL COMPETENCE IN COMMUNITY-BASED SETTINGS

The purpose of the current dissertation is to identify the features of effective interventions by exploring the experiences of youth with ASD who participate in such interventions, through two intervention studies (Studies 1 and 2) and one interview study (Study 3). Studies 1 and 2 were designed to support the development of social competence of youth with ASD through Structured Play with LEGO TM (Study 1, 12 youths with ASD, ages 7–12) and Minecraft TM (Study 2, 4 youths with ASD, ages 11–13). Over the course of the sessions, the play of the youth developed from parallel play (children playing alone, without interacting) to co-operative play (playing together with shared objectives). The results of Study 2 showed that rates of initiations and levels of engagement increased from the first session to the final session. In Study 3, 12 youths with ASD (ages 10–14) and at least one of their parents were interviewed to explore what children and their parents want from programs designed to improve social competence, which activities and practices were perceived to promote social competence by the participants, and which factors affected their decisions regarding these programs. The adolescents and parents looked for programs that supported social development and emotional wellbeing, but did not always have access to the programs they would have preferred, with factors such as cost and location reducing their options. Three overarching themes emerged through analysis of the three studies: (a) interests of the youth; (b) structure, both through interactions and instruction; and (c) naturalistic settings. Adolescents generally engage more willingly in interventions that incorporate their interests, such as play with Minecraft TM in Study 2. Additionally, Structured Play and structured instruction were crucial components of providing safe and supportive contexts for the development of social competence. Finally, skills learned in naturalistic settings tend to be applied more successfully in everyday situations. The themes are analysed through the lens of Vygotsky’s (1978) perspectives on learning, play, and development. Implications of the results for practitioners and researchers are discussed.

An Investigation of the Features and Effectiveness of the Full-Day Early Learning Kindergarten Program in Ontario

This dissertation includes two studies. Study 1 is a qualitative case study that describes enactment of the main components of a high fidelity Full-Day Early Learning Kindergarten (FDELK) classroom, specifically play-based learning and teacher-ECE collaboration. Study 2 is a quantitative analysis that investigates how effectively the FDELK program promotes school readiness skills, namely self-regulation, literacy, and numeracy, in Kindergarteners. To describe the main components of an FDELK classroom in Study 1, a sub-sample of four high fidelity case study schools were selected from a larger case study sample. Interview data from these schools’ administrators, educators, parents, and community stakeholders were used to describe how the main components of the FDELK program enabled educators to meet the individual needs of students and promote students’ SR development. In Study 2, hierarchical regression analyses of 32,207 students’ self-regulation, literacy, and numeracy outcomes using 2012 Ontario Early Development Instrument (EDI) data revealed essentially no benefit for students participating in the FDELK program when compared to peers in Half-Day or Alternate-Day Kindergarten programs. Being older and female predicted more positive SR and literacy outcomes. Age and gender accounted for limited variance in numeracy outcomes. Results from both studies suggest that the Ontario Ministry of Education should take steps to improve the quality of the FDELK program by incorporating evidence-based guidelines and goals for play, reducing Kindergarten class sizes to more effectively scaffold learning, and revising curriculum expectations to include a greater focus on SR, literacy, and numeracy skills.

Analysis of Protein Turnover by Quantitative SNAP-Based Pulse-Chase Imaging

Assessment of protein dynamics in living cells is crucial for understanding their biological properties and functions. The SNAP-tag, a self labeling suicide enzyme, presents a tool with unique features that can be adopted for determining protein dynamics in living cells. Here we present detailed protocols for the use of SNAP in fluorescent pulse-chase and quench-chase-pulse experiments. These time-slicing methods provide powerful tools to assay and quantify the fate and turnover rate of proteins of different ages. We cover advantages and pitfalls of SNAP-tagging in fixed- and live-cell studies and evaluate the recently developed fast-acting SNAPf variant. In addition, to facilitate the analysis of protein turnover datasets, we present an automated algorithm for spot recognition and quantification.

A multimodal tablet-based interface for designing and reviewing 3D engineering models

The ability to view and interact with 3D models has been happening for a long time. However, vision-based 3D modeling has only seen limited success in applications, as it faces many technical challenges. Hand-held mobile devices have changed the way we interact with virtual reality environments. Their high mobility and technical features, such as inertial sensors, cameras and fast processors, are especially attractive for advancing the state of the art in virtual reality systems. Also, their ubiquity and fast Internet connection open a path to distributed and collaborative development. However, such path has not been fully explored in many domains. VR systems for real world engineering contexts are still difficult to use, especially when geographically dispersed engineering teams need to collaboratively visualize and review 3D CAD models. Another challenge is the ability to rendering these environments at the required interactive rates and with high fidelity. In this document it is presented a virtual reality system mobile for visualization, navigation and reviewing large scale 3D CAD models, held under the CEDAR (Collaborative Engineering Design and Review) project. It’s focused on interaction using different navigation modes. The system uses the mobile device's inertial sensors and camera to allow users to navigate through large scale models. IT professionals, architects, civil engineers and oil industry experts were involved in a qualitative assessment of the CEDAR system, in the form of direct user interaction with the prototypes and audio-recorded interviews about the prototypes. The lessons learned are valuable and are presented on this document. Subsequently it was prepared a quantitative study on the different navigation modes to analyze the best mode to use it in a given situation.

Integrated architecture for vision-based indoor localization and mapping of a quadrotor micro-air vehicle

Atualmente os sistemas de pilotagem autónoma de quadricópteros estão a ser desenvolvidos de forma a efetuarem navegação em espaços exteriores, onde o sinal de GPS pode ser utilizado para definir waypoints de navegação, modos de position e altitude hold, returning home, entre outros. Contudo, o problema de navegação autónoma em espaços fechados sem que se utilize um sistema de posicionamento global dentro de uma sala, subsiste como um problema desafiante e sem solução fechada. Grande parte das soluções são baseadas em sensores dispendiosos, como o LIDAR ou como sistemas de posicionamento externos (p.ex. Vicon, Optitrack). Algumas destas soluções reservam a capacidade de processamento de dados dos sensores e dos algoritmos mais exigentes para sistemas de computação exteriores ao veículo, o que também retira a componente de autonomia total que se pretende num veículo com estas características. O objetivo desta tese pretende, assim, a preparação de um sistema aéreo não-tripulado de pequeno porte, nomeadamente um quadricóptero, que integre diferentes módulos que lhe permitam simultânea localização e mapeamento em espaços interiores onde o sinal GPS ´e negado, utilizando, para tal, uma câmara RGB-D, em conjunto com outros sensores internos e externos do quadricóptero, integrados num sistema que processa o posicionamento baseado em visão e com o qual se pretende que efectue, num futuro próximo, planeamento de movimento para navegação. O resultado deste trabalho foi uma arquitetura integrada para análise de módulos de localização, mapeamento e navegação, baseada em hardware aberto e barato e frameworks state-of-the-art disponíveis em código aberto. Foi também possível testar parcialmente alguns módulos de localização, sob certas condições de ensaio e certos parâmetros dos algoritmos. A capacidade de mapeamento da framework também foi testada e aprovada. A framework obtida encontra-se pronta para navegação, necessitando apenas de alguns ajustes e testes.

A graphic summary of American agriculture based largely on the census /

Includes index.