A deep learning-based approach for 3D people tracking

Questa tesi si occupa dell’estensione di un framework software finalizzato all'individuazione e al tracciamento di persone in una scena ripresa da telecamera stereoscopica. In primo luogo è rimossa la necessità di una calibrazione manuale offline del sistema sfruttando algoritmi che consentono di individuare, a partire da un fotogramma acquisito dalla camera, il piano su cui i soggetti tracciati si muovono. Inoltre, è introdotto un modulo software basato su deep learning con lo scopo di migliorare la precisione del tracciamento. Questo componente, che è in grado di individuare le teste presenti in un fotogramma, consente ridurre i dati analizzati al solo intorno della posizione effettiva di una persona, escludendo oggetti che l’algoritmo di tracciamento sarebbe portato a individuare come persone.

Learning and Exploiting Camera Geometry for Computer Vision

This work explores the use of statistical methods in describing and estimating camera poses, as well as the information feedback loop between camera pose and object detection. Surging development in robotics and computer vision has pushed the need for algorithms that infer, understand, and utilize information about the position and orientation of the sensor platforms when observing and/or interacting with their environment.

The first contribution of this thesis is the development of a set of statistical tools for representing and estimating the uncertainty in object poses. A distribution for representing the joint uncertainty over multiple object positions and orientations is described, called the mirrored normal-Bingham distribution. This distribution generalizes both the normal distribution in Euclidean space, and the Bingham distribution on the unit hypersphere. It is shown to inherit many of the convenient properties of these special cases: it is the maximum-entropy distribution with fixed second moment, and there is a generalized Laplace approximation whose result is the mirrored normal-Bingham distribution. This distribution and approximation method are demonstrated by deriving the analytical approximation to the wrapped-normal distribution. Further, it is shown how these tools can be used to represent the uncertainty in the result of a bundle adjustment problem.

Another application of these methods is illustrated as part of a novel camera pose estimation algorithm based on object detections. The autocalibration task is formulated as a bundle adjustment problem using prior distributions over the 3D points to enforce the objects' structure and their relationship with the scene geometry. This framework is very flexible and enables the use of off-the-shelf computational tools to solve specialized autocalibration problems. Its performance is evaluated using a pedestrian detector to provide head and foot location observations, and it proves much faster and potentially more accurate than existing methods.

Finally, the information feedback loop between object detection and camera pose estimation is closed by utilizing camera pose information to improve object detection in scenarios with significant perspective warping. Methods are presented that allow the inverse perspective mapping traditionally applied to images to be applied instead to features computed from those images. For the special case of HOG-like features, which are used by many modern object detection systems, these methods are shown to provide substantial performance benefits over unadapted detectors while achieving real-time frame rates, orders of magnitude faster than comparable image warping methods.

The statistical tools and algorithms presented here are especially promising for mobile cameras, providing the ability to autocalibrate and adapt to the camera pose in real time. In addition, these methods have wide-ranging potential applications in diverse areas of computer vision, robotics, and imaging.

Advanced Applications of 3D Dosimetry and 3D Printing in Radiation Therapy

As complex radiotherapy techniques become more readily-practiced, comprehensive 3D dosimetry is a growing necessity for advanced quality assurance. However, clinical implementation has been impeded by a wide variety of factors, including the expense of dedicated optical dosimeter readout tools, high operational costs, and the overall difficulty of use. To address these issues, a novel dry-tank optical CT scanner was designed for PRESAGE 3D dosimeter readout, relying on 3D printed components and omitting costly parts from preceding optical scanners. This work details the design, prototyping, and basic commissioning of the Duke Integrated-lens Optical Scanner (DIOS).

The convex scanning geometry was designed in ScanSim, an in-house Monte Carlo optical ray-tracing simulation. ScanSim parameters were used to build a 3D rendering of a convex ‘solid tank’ for optical-CT, which is capable of collimating a point light source into telecentric geometry without significant quantities of refractive-index matched fluid. The model was 3D printed, processed, and converted into a negative mold via rubber casting to produce a transparent polyurethane scanning tank. The DIOS was assembled with the solid tank, a 3W red LED light source, a computer-controlled rotation stage, and a 12-bit CCD camera. Initial optical phantom studies show negligible spatial inaccuracies in 2D projection images and 3D tomographic reconstructions. A PRESAGE 3D dose measurement for a 4-field box treatment plan from Eclipse shows 95% of voxels passing gamma analysis at 3%/3mm criteria. Gamma analysis between tomographic images of the same dosimeter in the DIOS and DLOS systems show 93.1% agreement at 5%/1mm criteria. From this initial study, the DIOS has demonstrated promise as an economically-viable optical-CT scanner. However, further improvements will be necessary to fully develop this system into an accurate and reliable tool for advanced QA.

Pre-clinical animal studies are used as a conventional means of translational research, as a midpoint between in-vitro cell studies and clinical implementation. However, modern small animal radiotherapy platforms are primitive in comparison with conventional linear accelerators. This work also investigates a series of 3D printed tools to expand the treatment capabilities of the X-RAD 225Cx orthovoltage irradiator, and applies them to a feasibility study of hippocampal avoidance in rodent whole-brain radiotherapy.

As an alternative material to lead, a novel 3D-printable tungsten-composite ABS plastic, GMASS, was tested to create precisely-shaped blocks. Film studies show virtually all primary radiation at 225 kVp can be attenuated by GMASS blocks of 0.5cm thickness. A state-of-the-art software, BlockGen, was used to create custom hippocampus-shaped blocks from medical image data, for any possible axial treatment field arrangement. A custom 3D printed bite block was developed to immobilize and position a supine rat for optimal hippocampal conformity. An immobilized rat CT with digitally-inserted blocks was imported into the SmART-Plan Monte-Carlo simulation software to determine the optimal beam arrangement. Protocols with 4 and 7 equally-spaced fields were considered as viable treatment options, featuring improved hippocampal conformity and whole-brain coverage when compared to prior lateral-opposed protocols. Custom rodent-morphic PRESAGE dosimeters were developed to accurately reflect these treatment scenarios, and a 3D dosimetry study was performed to confirm the SmART-Plan simulations. Measured doses indicate significant hippocampal sparing and moderate whole-brain coverage.

Evaluation of a ToF Camera for Remote Surveying of Underground Cavities Excavated by Jet Boring

Cigar Lake is a high-grade uranium deposit, located in northern Saskatchewan, Canada. In order to extract the uranium ore remotely, thus ensuring minimal radiation dose to workers and also to access the ore from stable ground, the Jet Boring System (JBS) was developed by Cameco Corporation. This system uses a high-powered water jet to remotely excavate cavities. Survey data is required to determine the final shape, volume, and location of the cavity for mine planning purposes and construction. This paper provides an overview of the challenges involved in remotely surveying a JBS-mined cavity and studies the potential use of a time-of-flight (ToF) camera for remote cavity surveying. It reports on data collected and analyzed from inside an experimental environment as well as on real data acquired on site from the Cigar Lake and Rabbit Lake mines.

Simulations in 3D research : Can Unity3D be used to simulate a 3D display system?

Mid Sweden University is currently researching how to capture more of a scene with a camera and how to create 3D images that does not require extra equipment for the viewer. In the process of this research they have started looking into simulating some of the tests that they wish to conduct. The goal of this project is to research whether the 3D graphics engine Unity3D could be used to simulate these tests, and to what degree. To test this a simulation was designed and implemented. The simulation used a split display system where each camera is directly connected to a part of the screen and using the position of the viewer the correct part of the camera feed is shown. Some literary studies were also done into how current 3D technology works. The simulation was successfully implemented and shows that simple simulation can be done in Unity3D, however, some problems were encountered in the process. The conclusion of the project show that there is much work left before simulation is viable but that there is potential in the technology and that the research team should continue to investigate it.

Analisi sperimentale e progettazione di cinematismi atti alla movimentazione di devices protesici all’interno di una camera di deposizione pvd

analisi sperimentale e progettazione di cinematismi atti alla movimentazione di devices protesici all’interno di una camera di deposizione pvd. descrizione delle tecniche di deposizione PVD attualmente esistenti. deduzione e progetto ex novo, con l'ausilio di Autodesk Inventor (CAD 3D), di movimentazioni per particolari devices medici dalla geometria complessa all'interno di una speciale camera di deposizione.

Navigating 3d Scatter Plots in Immersive Virtual Reality

Thesis (Master's)--University of Washington, 2016-01

Bin picking de objetos polimórficos convexos usando perceção 3D

O bin picking é um processo de grande interesse na indústria, uma vez que permite maior automatização, aumento da capacidade de produção e redução dos custos. Este tem vindo a evoluir bastante ao longo dos anos e essa evolução fez com que sistemas de perceção 3D começassem a ser implementados. Este trabalho tem como principal objetivo desenvolver um sistema de bin picking usando apenas perceção 3D. O sistema deve ser capaz de determinar a posição e orientação de objetos com diferentes formas e tamanhos, posicionados aleatoriamente numa superfície de trabalho. Os objetos utilizados para fazer os testes experimentais, são esferas, cilindros e prismas, uma vez que abrangem as formas geométricas existentes em muitos produtos submetidos a bin picking. Após a identi cação e seleção do objeto a apanhar, o manipulador deve autonomamente posicionar-se para fazer a aproximação e recolha do mesmo. A aquisição de dados é feita através de uma câmara Kinect. Dos dados recebidos apenas são trabalhados os referentes à profundidade, centrando-se assim este trabalho na análise e tratamento de nuvem de pontos. O sistema desenvolvido cumpre com os objetivos estabelecidos. Consegue localizar e apanhar objetos em várias posições e orientações. Além disso apresenta uma velocidade de processamento compatível com a aplicação em causa.

Sistema integrado de generación de mapas de profundidad para videoconferencia 3D en tiempo real

This paper presents the implementation of a high quality real-time 3D video system intended for 3D videoconferencing -- Basically, the system is able to extract depth information from a pair of images coming from a short-baseline camera setup -- The system is based on the use of a variant of the adaptive support-weight algorithm to be applied on GPU-based architectures -- The reason to do it is to get real-time results without compromising accuracy and also to reduce costs by using commodity hardware -- The complete system runs over the GStreamer multimedia software platform to make it even more flexible -- Moreover, an autoestereoscopic display has been used as the end-up terminal for 3D content visualization

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.

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.

Rilevazione ottica delle dimensioni della camera di combustione per la stima del rapporto di compressione reale

La ricerca di un'ottima qualità costruttiva è diventata, per ogni fornitore o produttore legato all’ambito automotive/motoristico, l’aspetto principale nella produzione di un veicolo, soprattutto nel caso specifico di un motore: per garantire, dunque, una buona qualità generale lungo tutta la gamma di produzione, è necessario avere una buona “ripetibilità” di costruzione, ossia, è fondamentale poter assemblare un alto numero di motori che siano il più possibile identici tra loro; considerando tutte le variabili che intervengono lungo la catena di produzione, a partire dalla banale lavorazione meccanica delle parti, fino all’assemblaggio stesso del motore. E' facilmente intuibile, pertanto, come non sia così raro avere delle leggere imperfezioni tra motore e motore che possono poi andare ad impattare sulla vita e sulle performance stesse del mezzo. Questo discorso è ancora più valido se si parla dell’ambito racing, in cui la qualità costruttiva, e, quindi, le performance, giocano un ruolo fondamentale nella progettazione di un motore, nonostante il volume produttivo sia tutto sommato piccolo. L’obiettivo dell'elaborato è quello di creare un metodo di controllo e di confronto della qualità/precisione costruttiva, intesa sia come qualità di produzione delle parti che di assemblaggio del motore finito. A partire da una scansione laser tridimensionale, sotto forma di una nuvola di punti, si è creato un software di elaborazione dati che permettesse di arrivare a calcolare il rapporto di compressione reale del motore in analisi e la mappa di squish tramite la sovrapposizione virtuale delle due scansioni relative ai cilindri/pistoni del blocco motore e la testa del motore stesso.

Metodologia para analise cinematica de volumes respiratorios parciais de nadadores

Universidade Estadual de Campinas . Faculdade de Educação Física

Calibração de câmeras para análises subaquáticas de movimentos = : Cameras calibration for underwater motion analysis

Universidade Estadual de Campinas . Faculdade de Educação Física

Fundamentos geometricos e algebricos da calibração e reconstrução tridimensional : aplicação na analise cinematica de movimentos humanos

Universidade Estadual de Campinas . Faculdade de Educação Física