A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional 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. It is proposed 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). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.

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.

Reimaginar el mito de las gucamayas ilustraciones 3D: transición de las guacamayas de seres mágicos a mujeres

El siguiente proyecto, es una propuesta gráfica ilustrada en 3D, basada en la mitología cañari. El estudio realizado esboza breves rasgos de la cosmovisión generada a través del mito de la guacamaya. Donde se revela datos importantes que construye la identidad cultural del pueblo cañari. De igual manera se refleja la ilustración como proceso de creación de conocimientos, donde se comprende y exponen los contextos de la imagen dados desde el estudio anatómico y el uso de programas orientados a la generación de imágenes 2d y 3d. Asimismo se refleja la interpretación del mito expuesto desde la mirada del autor, desplegando potencias particulares que redefinen las practicas tradicionales, permitiendo que la ilustración se piense así misma como una producción y no solo como representación

POSE ESTIMATION AND 3D RECONSTRUCTION USING SENSOR FUSION

A camera maps 3-dimensional (3D) world space to a 2-dimensional (2D) image space. In the process it loses the depth information, i.e., the distance from the camera focal point to the imaged objects. It is impossible to recover this information from a single image. However, by using two or more images from different viewing angles this information can be recovered, which in turn can be used to obtain the pose (position and orientation) of the camera. Using this pose, a 3D reconstruction of imaged objects in the world can be computed. Numerous algorithms have been proposed and implemented to solve the above problem; these algorithms are commonly called Structure from Motion (SfM). State-of-the-art SfM techniques have been shown to give promising results. However, unlike a Global Positioning System (GPS) or an Inertial Measurement Unit (IMU) which directly give the position and orientation respectively, the camera system estimates it after implementing SfM as mentioned above. This makes the pose obtained from a camera highly sensitive to the images captured and other effects, such as low lighting conditions, poor focus or improper viewing angles. In some applications, for example, an Unmanned Aerial Vehicle (UAV) inspecting a bridge or a robot mapping an environment using Simultaneous Localization and Mapping (SLAM), it is often difficult to capture images with ideal conditions. This report examines the use of SfM methods in such applications and the role of combining multiple sensors, viz., sensor fusion, to achieve more accurate and usable position and reconstruction information. This project investigates the role of sensor fusion in accurately estimating the pose of a camera for the application of 3D reconstruction of a scene. The first set of experiments is conducted in a motion capture room. These results are assumed as ground truth in order to evaluate the strengths and weaknesses of each sensor and to map their coordinate systems. Then a number of scenarios are targeted where SfM fails. The pose estimates obtained from SfM are replaced by those obtained from other sensors and the 3D reconstruction is completed. Quantitative and qualitative comparisons are made between the 3D reconstruction obtained by using only a camera versus that obtained by using the camera along with a LIDAR and/or an IMU. Additionally, the project also works towards the performance issue faced while handling large data sets of high-resolution images by implementing the system on the Superior high performance computing cluster at Michigan Technological University.

3D Surveying and Data Management towards the Realization of a Knowledge System for Cultural Heritage

The research activities involved the application of the Geomatic techniques in the Cultural Heritage field, following the development of two themes: Firstly, the application of high precision surveying techniques for the restoration and interpretation of relevant monuments and archaeological finds. The main case regards the activities for the generation of a high-fidelity 3D model of the Fountain of Neptune in Bologna. In this work, aimed to the restoration of the manufacture, both the geometrical and radiometrical aspects were crucial. The final product was the base of a 3D information system representing a shared tool where the different figures involved in the restoration activities shared their contribution in a multidisciplinary approach. Secondly, the arrangement of 3D databases for a Building Information Modeling (BIM) approach, in a process which involves the generation and management of digital representations of physical and functional characteristics of historical buildings, towards a so-called Historical Building Information Model (HBIM). A first application was conducted for the San Michele in Acerboli’s church in Santarcangelo di Romagna. The survey was performed by the integration of the classical and modern Geomatic techniques and the point cloud representing the church was used for the development of a HBIM model, where the relevant information connected to the building could be stored and georeferenced. A second application regards the domus of Obellio Firmo in Pompeii, surveyed by the integration of the classical and modern Geomatic techniques. An historical analysis permitted the definitions of phases and the organization of a database of materials and constructive elements. The goal is the obtaining of a federate model able to manage the different aspects: documental, analytic and reconstructive ones.

Optimized methods to digital survey and 3D modelling of cultural heritage assets

Currently making digital 3D models and replicas of the cultural heritage assets play an important role in the preservation and having a high detail source for future research and intervention. In this dissertation, it is tried to assess different methods for digital surveying and making 3D replicas of cultural heritage assets in different scales of size. The methodologies vary in devices, software, workflow, and the amount of skill that is required. The three phases of the 3D modelling process are data acquisition, modelling, and model presentation. Each of these sections is divided into sub-sections and there are several approaches, methods, devices, and software that may be employed, furthermore, the selection process should be based on the operation's goal, available facilities, the scale and properties of the object or structure to be modeled, as well as the operators' expertise and experience. The most key point to remember is that the 3D modelling operation should be properly accurate, precise, and reliable; therefore, there are so many instructions and pieces of advice on how to perform 3D modelling effectively. It is an attempt to compare and evaluate the various ways of each phase in order to explain and demonstrate their differences, benefits, and drawbacks in order to serve as a simple guide for new and/or inexperienced users.

An Embedded In-Cabin Lightweight High-Performance 3D Gaze Estimation System

Gaze estimation has gained interest in recent years for being an important cue to obtain information about the internal cognitive state of humans. Regardless of whether it is the 3D gaze vector or the point of gaze (PoG), gaze estimation has been applied in various fields, such as: human robot interaction, augmented reality, medicine, aviation and automotive. In the latter field, as part of Advanced Driver-Assistance Systems (ADAS), it allows the development of cutting-edge systems capable of mitigating road accidents by monitoring driver distraction. Gaze estimation can be also used to enhance the driving experience, for instance, autonomous driving. It also can improve comfort with augmented reality components capable of being commanded by the driver's eyes. Although, several high-performance real-time inference works already exist, just a few are capable of working with only a RGB camera on computationally constrained devices, such as a microcontroller. This work aims to develop a low-cost, efficient and high-performance embedded system capable of estimating the driver's gaze using deep learning and a RGB camera. The proposed system has achieved near-SOTA performances with about 90% less memory footprint. The capabilities to generalize in unseen environments have been evaluated through a live demonstration, where high performance and near real-time inference were obtained using a webcam and a Raspberry Pi4.

AGV Safety Areas Obstacle Detection and Interaction with Point Cloud Derived Map

This thesis project aims to the development of an algorithm for the obstacle detection and the interaction between the safety areas of an Automated Guided Vehicles (AGV) and a Point Cloud derived map inside the context of a CAD software. The first part of the project focuses on the implementation of an algorithm for the clipping of general polygons, with which has been possible to: construct the safety areas polygon, derive the sweep of this areas along the navigation path performing a union and detect the intersections with line or polygon representing the obstacles. The second part is about the construction of a map in terms of geometric entities (lines and polygons) starting from a point cloud given by the 3D scan of the environment. The point cloud is processed using: filters, clustering algorithms and concave/convex hull derived algorithms in order to extract line and polygon entities representing obstacles. Finally, the last part aims to use the a priori knowledge of possible obstacle detections on a given segment, to predict the behavior of the AGV and use this prediction to optimize the choice of the vehicle's assigned velocity in that segment, minimizing the travel time.

Domain adaptation per classificazione di point cloud mediante pseudo-annotazioni

La classificazione di dati geometrici 3D come point cloud è un tema emergente nell'ambito della visione artificiale in quanto trova applicazione in molteplici contesti di guida autonoma, robotica e realtà aumentata. Sebbene nel mercato siano presenti una grande quantità di sensori in grado di ottenere scansioni reali, la loro annotazione costituisce un collo di bottiglia per la generazione di dataset. Per sopperire al problema si ricorre spesso alla domain adaptation sfruttando dati sintetici annotati. Questo elaborato si pone come obiettivo l'analisi e l'implementazione di metodi di domain adaptation per classificazione di point cloud mediante pseudo-labels. In particolare, sono stati condotti esperimenti all'interno del framework RefRec valutando la possibilità di sostituire nuove architetture di deep learning al modello preesistente. Tra queste, Transformer con mascheramento dell'input ha raggiunto risultati superiori allo stato dell'arte nell'adattamento da dati sintetici a reali (ModelNet->ScanNet) esaminato in questa tesi.

Sistema de análise de movimento para avaliação da postura vertical durante a corrida no teste de esforço máximo incremental

Universidade Estadual de Campinas . Faculdade de Educação Física

Structural and chemical basis for anticancer activity of a series of 'beta'-tubulin ligands: molecular modeling and 3D QSAR studies

An important approach to cancer therapy is the design of small molecule modulators that interfere with microtubule dynamics through their specific binding to the ²-subunit of tubulin. In the present work, comparative molecular field analysis (CoMFA) studies were conducted on a series of discodermolide analogs with antimitotic properties. Significant correlation coefficients were obtained (CoMFA(i), q² =0.68, r²=0.94; CoMFA(ii), q² = 0.63, r²= 0.91), indicating the good internal and external consistency of the models generated using two independent structural alignment strategies. The models were externally validated employing a test set, and the predicted values were in good agreement with the experimental results. The final QSAR models and the 3D contour maps provided important insights into the chemical and structural basis involved in the molecular recognition process of this family of discodermolide analogs, and should be useful for the design of new specific ²-tubulin modulators with potent anticancer activity.

Stress distribution in the cervical region of an upper central incisor in a 3D finite element model

The aim of this study was to evaluate the stress distribution in the cervical region of a sound upper central incisor in two clinical situations, standard and maximum masticatory forces, by means of a 3D model with the highest possible level of fidelity to the anatomic dimensions. Two models with 331,887 linear tetrahedral elements that represent a sound upper central incisor with periodontal ligament, cortical and trabecular bones were loaded at 45º in relation to the tooth's long axis. All structures were considered to be homogeneous and isotropic, with the exception of the enamel (anisotropic). A standard masticatory force (100 N) was simulated on one of the models, while on the other one a maximum masticatory force was simulated (235.9 N). The software used were: PATRAN for pre- and post-processing and Nastran for processing. In the cementoenamel junction area, tensile forces reached 14.7 MPa in the 100 N model, and 40.2 MPa in the 235.9 N model, exceeding the enamel's tensile strength (16.7 MPa). The fact that the stress concentration in the amelodentinal junction exceeded the enamel's tensile strength under simulated conditions of maximum masticatory force suggests the possibility of the occurrence of non-carious cervical lesions such as abfractions.

Ventilation behavior in trained and untrained men during incremental test: evidence of one metabolic transition point

This study aimed to describe and compare the ventilation behavior during an incremental test utilizing three mathematical models and to compare the feature of ventilation curve fitted by the best mathematical model between aerobically trained (TR) and untrained ( UT) men. Thirty five subjects underwent a treadmill test with 1 km.h(-1) increases every minute until exhaustion. Ventilation averages of 20 seconds were plotted against time and fitted by: bi-segmental regression model (2SRM); three-segmental regression model (3SRM); and growth exponential model (GEM). Residual sum of squares (RSS) and mean square error (MSE) were calculated for each model. The correlations between peak VO2 (VO2PEAK), peak speed (Speed(PEAK)), ventilatory threshold identified by the best model (VT2SRM) and the first derivative calculated for workloads below (moderate intensity) and above (heavy intensity) VT2SRM were calculated. The RSS and MSE for GEM were significantly higher (p < 0.01) than for 2SRM and 3SRM in pooled data and in UT, but no significant difference was observed among the mathematical models in TR. In the pooled data, the first derivative of moderate intensities showed significant negative correlations with VT2SRM (r = -0.58; p < 0.01) and Speed(PEAK) (r = -0.46; p < 0.05) while the first derivative of heavy intensities showed significant negative correlation with VT2SRM (r = -0.43; p < 0.05). In UT group the first derivative of moderate intensities showed significant negative correlations with VT2SRM (r = -0.65; p < 0.05) and Speed(PEAK) (r = -0.61; p < 0.05), while the first derivative of heavy intensities showed significant negative correlation with VT2SRM (r= -0.73; p < 0.01), Speed(PEAK) (r = -0.73; p < 0.01) and VO2PEAK (r = -0.61; p < 0.05) in TR group. The ventilation behavior during incremental treadmill test tends to show only one threshold. UT subjects showed a slower ventilation increase during moderate intensities while TR subjects showed a slower ventilation increase during heavy intensities.

Shoulder Muscular Activity During Isometric Three-Point Kneeling Exercise on Stable and Unstable Surfaces

The purpose of this study was to determine if performing isometric 3-point kneeling exercises on a Swiss ball influenced the isometric force output and EMG activities of the shoulder muscles when compared with performing the same exercises on a stable base of support. Twenty healthy adults performed the isometric 3-point kneeling exercises with the hand placed either on a stable surface or on a Swiss ball. Surface EMG was recorded from the posterior deltoid, pectoralis major, biceps brachii, triceps brachii, upper trapezius, and serratus anterior muscles using surface differential electrodes. All EMG data were reported as percentages of the average root mean square (RMS) values obtained in maximum voluntary contractions for each muscle studied. The highest load value was obtained during exercise on a stable surface. A significant increase was observed in the activation of glenohumeral muscles during exercises on a Swiss ball. However, there were no differences in EMG activities of the scapulothoracic muscles. These results suggest that exercises performed on unstable surfaces may provide muscular activity levels similar to those performed on stable surfaces, without the need to apply greater external loads to the musculoskeletal system. Therefore, exercises on unstable surfaces may be useful during the process of tissue regeneration.

Dynamical Lorentz symmetry breaking in 3D and charge fractionalization

We analyze the breaking of Lorentz invariance in a 3D model of fermion fields self-coupled through four-fermion interactions. The low-energy limit of the theory contains various submodels which are similar to those used in the study of graphene or in the description of irrational charge fractionalization.