Submitted by Daniella Santos (daniella.santos@ufma.br) on 2017-11-23T14:52:48Z No. of bitstreams: 1 DanielGomesJúnior.pdf: 8247020 bytes, checksum: ccc1a51b78a0a368f50ca5393fa8d97c (MD5) / Made available in DSpace on 2017-11-23T14:52:48Z (GMT). No. of bitstreams: 1 DanielGomesJúnior.pdf: 8247020 bytes, checksum: ccc1a51b78a0a368f50ca5393fa8d97c (MD5) Previous issue date: 2017-08-25 / This research proposes a methodology for development of Virttual Reality (VR) and Augmented Reality (AR) aplications, using natural markers for industrial scenarios. The proposed methodology uses the object annotation concept and visualization proposals are presented both for development of VR as for AR environments. In VR environments, the methodology is applied for object detection step of the semi-automatic environment development. On the other hand, in AR environments, is presented the concept of georreferenced natural markers, which use the georreferenced data integrated with object detection process using image processing techniques. The energy substations scenarios were used as case study for both approaches. Architectures are presented for construction and data visualization in industrial environments. Both for VR as for AR approaches, this work proposes using 3D natural markers based in Haar-like features for object training and detection process. The results enable the equipment detection at different points of view, within the operating scenario. Besides that, in AR, it enables the pose estimation in real-time using ORB features, while in VR it enables the semi-automatic object detection, which are used as information points for inclusion of virtual information. Several industrial scenarios, and especially the energy sector, has a high degree of complexity in the information processing and visualization. In this sense, beyond the 3D natural markers methodology, this work presents new visualization applications for industrial scenario visualization in VR and AR approaches. / Esta pesquisa propõe uma metodologia para construção de aplicações de Realidade Virtual (RV) e Realidade Aumentada (RA) com uso de marcadores naturais em cenários industriais. A metodologia usa o conceito de anotação de objetos e são apresentadas propostas de visualização para ambientes industriais tanto em formato de RV quanto de RA. Nos ambientes de RV, a metodologia é aplicada através da detecção de objetos no processo de construção semiautomática dos ambientes. Por outro lado, nos ambientes de RA, apresenta-se o conceito de marcadores naturais georreferenciados, que associam dados georreferenciados ao processo de detecção de objetos com técnicas de processamento de imagens. O cenário de subestações de energia elétrica foi utilizado como estudo de caso para as duas abordagens. São apresentadas arquiteturas para construção e visualização de dados em ambientes industriais. Tanto sob a forma de RV quanto de RA, este trabalho propõe o uso de marcadores naturais 3D baseados em Haar-like features para o processo de treinamento e detecção de objetos. Os resultados permitem a detecção de equipamentos a partir de diferentes pontos de vista no cenário de operação. Além disso, em RA, esta abordagem permite a estimativa de pose em tempo real com uso de ORB features e permite, em RV, a detecção semiautomática de objetos que são utilizados como pontos de informação para adição de informações virtuais. Diversos cenários industriais, principalmente o setor elétrico, possuem grau elevado de complexidade no tratamento e visualização das informações. Nesse sentido, além da metodologia de marcadores naturais 3D, este trabalho apresenta novas aplicações de visualização no cenário industrial com abordagens em RV e RA.

The University of Arizona's Aerial Robotics Club (ARC) sponsored two senior design teams to compete in the 2011 AUVSI Student Unmanned Aerial Systems (SUAS) competition. These teams successfully design and built a UAV platform in-house that was capable of autonomous flight, capturing aerial imagery, and filtering for target recognition but required excessive computational hardware and software bugs that limited the systems capability. A new multi-discipline team of undergrads was recruited to completely redesign and optimize the system in an attempt to reach true autonomous real-time target recognition with reasonable COTS hardware.

Performance of automatic speech recognition (ASR) systems utilizing only acoustic information degrades significantly in noisy environments such as a car cabins. Incorporating audio and visual information together can improve performance in these situations. This work proposes a lip detection and tracking algorithm to serve as a visual front end to an audio-visual automatic speech recognition (AVASR) system. Several color spaces are examined that are effective for segmenting lips from skin pixels. These color components and several features are used to characterize lips and to train cascaded lip detectors. Pre- and post-processing techniques are employed to maximize detector accuracy. The trained lip detector is incorporated into an adaptive mean-shift tracking algorithm for tracking lips in a car cabin environment. The resulting detector achieves 96.8% accuracy, and the tracker is shown to recover and adapt in scenarios where mean-shift alone fails.

This thesis deals with human body detection and gestures tracking in videosequences. First, processing of videosequences in general is described. Further, different methods of human body detection are described and represented by significant papers. The most of the attention is focused on detection by real AdaBoost algorithm based on Haar-like features and Edgelet features. The practical part starts with selection of method that is implemented in this thesis. This method is detection by real AdaBoost based on Haar-like features. Further, different options of videosequence processing in JAVA are researched with justification of choice OpenCV library with JavaCV wrapper, which is used in this thesis. In the end, application itself is described, including description of GUI and description of each class and its functionality.

In recent years wearable devices have been advancing at a rapid pace and one of the largest growing segments is the smart glass segment. In this thesis the feasibility of today’s ARM-based smart glasses are evaluated for automatic license plate recognition (ALPR). The license plate is by far the most prominent visual feature to identify a spe- cific vehicle, and exists on both old and newly produced vehicles. This thesis propose an ALPR system based on a sequence of vertical edge detection, a cascade classifier, verti- cal and horizontal projection as well as a general purpose optical character recognition library. The study further concludes that the optimal input resolution for license plate detection using vertical edges is 640x360 pixels and that the license plate need to be at least 20 pixels high or the characters 15 pixels high in order to successfully segment the plate and recognize each character. The separate stages were successfully implemented into a complete ALPR system that achieved 79.5% success rate while processing roughly 3 frames per second when running on a pair of Google Glass. / Under de senaste åren har området wearables avancerat i snabb takt, och ett av de snabbast växande segmenten är smarta glaögon. I denna examensuppsats utvärderas lämpligheten av dagens ARM-baserade smarta glasögon med avseende på automatisk registreringsskyltigenkänning. Registreringsskylten är den i särklass mest framträdande visuella egenskapen som kan användas för att identifiera ett specifikt fordon, och den finns på både gamla och nyproducerade fordon. Detta examensarbete föreslår ett system för automatisk registreringsskyltigenkänning baserat på en följd av vertikal kantdetektering, en kaskad av boostade klassificerare, vertikal och horisontell projektion samt ett optiskt teckenigenkänningsbibliotek. Studien konstaterar vidare att den optimala upplösningen för registreringsskyltdetektion med hjälp av vertikala kanter på smarta glasögonär 640x360 pixlar och att registreringsskylten måste vara minst 20 pixlar hög eller tecknen 15 pixlar höga för att registreringsskylten framgångsrikt skall kunna segmenteras samt tecken identifieras. De separata stegen implementerades framgångsrikt till ett system för automatisk registreringsskyltigenkänning på ett par Google Glass och lyckades känna igen 79,5% av de testade registreringsskyltarna, med en hastighet av ungefär 3 bilder per sekund.

This thesis deals with the image object detection using Haar--like features and AdaBoost algorithm. The text describes methods how to train and test an object detector. The main contributon of this thesis consists in creation image object detector in Java programming language. Created algorithms were integrated as plugin into the RapidMiner tool, which is widely used and known worldwide as tool for data mining. The thesis contains the instructions for created operators and few exaples for executing in RapidMiner tool. The functionality of image object detector was demonstrated on selected medical images.

In this thesis, we present the local rank differences (LRD). These novel image features are invariant to lighting changes and are suitable for object detection in programmable hardware, such as FPGA. The performance of AdaBoost classifiers with the LRD was tested on a face detection dataset with results which are similar to the Haar-like features which are the state of the art in real-time object detection. These results together with the fact that the LRD are evaluated much faster in FPGA then the Haar-like features are very encouraging and suggest that the LRD may be a solution for future hardware object detectors. We also present a framework for experiments with boosting methods in computer vision. This framework is very flexible and, at the same time, offers high learning performance and a possibility for future parallelization. The framework is available as open source software and we hope that it will simplify work for other researchers.

Systems like autonomous vehicles may require real time embedded image processing under hardware constraints. This paper provides directions to design time and resource efficient Haar cascade detection algorithms. It also reviews some software architecture and hardware aspects. The considered algorithms were meant to be run on platforms equipped with a CPU and a GPU under power consumption limitations. The main aim of the project was to design and develop real time underwater object detection algorithms. However the concepts that are presented in this paper are generic and can be applied to other domains where object detection is required, face detection for instance. The results show how the solutions outperform OpenCV cascade detector in terms of execution time while having the same accuracy. / System så som autonoma vehiklar kan kräva inbyggd bildbehandling i realtid under hårdvarubegränsningar. Denna uppsats tillhandahåller anvisningar för att designa tidsoch resurseffektiva Haar-kasad detekterande algoritmer. Dessutom granskas en del mjukvaruarkitektur och hårdvaruaspekter. De avsedda algoritmerna är menade att användas på plattformar försedda med en CPU och en GPU under begränsad energitillgång. Det huvudsakliga målet med projektet var att designa och utveckla realtidsalgoritmer för detektering av objekt under vatten. Dock är koncepten som presenteras i arbetet generiska och kan appliceras på andra domäner där objektdetektering kan behövas, till exempel vid detektering av ansikten. Resultaten visar hur lösningarna överträffar OpenCVs kaskaddetektor beträffande exekutionstid och med samtidig lika stor träffsäkerhet.

Humans can visually track objects mostly effortlessly. However, it is hard for a computer to track a fast moving object under varying illumination and occlusions, in clutter, and with varying appearance in camera projective space due to its relaxed rigidity or change in viewpoint. Since a generic, precise, robust, and fast tracker could trigger many applications, object tracking has been a fundamental problem of practical importance since the beginnings of computer vision. The first contribution of the thesis is a computationally efficient approach to tracking objects of various shapes and motions. It describes a unifying tracking system that can be configured to track the pose of a deformable object in a low or high-dimensional state-space. The object is decomposed into a chained assembly of segments of multiple parts that are arranged under a hierarchy of tailored spatio-temporal constraints. The robustness and generality of the approach is widely demonstrated on tracking various flexible and articulated objects. Haar-like features are widely used in tracking. The second contribution of the thesis is a parser of ensembles of Haar-like features to compute them efficiently. The features are decomposed into simpler kernels, possibly shared by subsets of features, thus forming multi-pass convolutions. Discovering and aligning these kernels within and between passes allows forming recursive trees of kernels that require fewer memory operations than the classic computation, thereby producing the same result but more efficiently. The approach is validated experimentally on popular examples of Haar-like features

In this thesis project techniques for training a rapid image classifier that can recognize an object of a predefined type has been studied. Classifiers have been trained with the AdaBoost algorithm, with and without the use of Viola-Jones cascades. The use of Weight trimming in the classifier training has been evaluated and resulted in a significant speed up of the training, as well as improving the performance of the trained classifier. Different preprocessings of the images have also been tested, but resulted for the most part in worse performance for the classifiers when used individually. Several rectangle shaped Haar-like features including novel versions have been evaluated and the magnitude versions proved to be best at separating the image classes.