Thesis (MEng)--Stellenbosch University, 2015. / ENGLISH ABSTRACT: This thesis investigates the use of stereo vision sensors for dense autonomous mapping. It characterises and analyses the errors made during the stereo matching process so measurements can be correctly integrated into a 3D grid-based map. Maps are required for navigation and obstacle avoidance on autonomous vehicles in complex, unknown environments. The safety of the vehicle as well as the public depends on an accurate mapping of the environment of the vehicle, which can be problematic when inaccurate sensors such as stereo vision are used. Stereo vision sensors are relatively cheap and convenient, however, and a system that can create reliable maps using them would be beneficial. A literature review suggests that occupancy grid mapping poses an appropriate solution, offering dense maps that can be extended with additional measurements incrementally. It forms a grid representation of the environment by dividing it into cells, and assigns a probability to each cell of being occupied. These probabilities are updated with measurements using a sensor model that relates measurements to occupancy probabilities. Numerous forms of these sensor models exist, but none of them appear to be based on meaningful assumptions and sound statistical principles. Furthermore, they all seem to be limited by an assumption of unimodal, zero-mean Gaussian measurement noise. Therefore, we derive a principled inverse sensor model (PRISM) based on physically meaningful assumptions. This model is capable of approximating any realistic measurement error distribution using a Gaussian mixture model (GMM). Training a GMM requires a characterisation of the measurement errors, which are related to the environment as well as which stereo matching technique is used. Therefore, a method for fitting a GMM to the error distribution of a sensor using measurements and ground truth is presented. Since we may consider the derived principled inverse sensor model to be theoretically correct under its assumptions, we use it to evaluate the approximations made by other models from the literature that are designed for execution speed. We show that at close range these models generally offer good approximations that worsen with an increase in measurement distance. We test our model by creating maps using synthetic and real world data. Comparing its results to those of sensor models from the literature suggests that our model calculates occupancy probabilities reliably. Since our model captures the limited measurement range of stereo vision, we conclude that more accurate sensors are required for mapping at greater distances. / AFRIKAANSE OPSOMMING: Hierdie tesis ondersoek die gebruik van stereovisie sensors vir digte outonome kartering. Dit karakteriseer en ontleed die foute wat gemaak word tydens die stereopassingsproses sodat metings korrek geïntegreer kan word in 'n 3D rooster-gebaseerde kaart. Sulke kaarte is nodig vir die navigasie en hindernisvermyding van outonome voertuie in komplekse en onbekende omgewings. Die veiligheid van die voertuig sowel as die publiek hang af van 'n akkurate kartering van die voertuig se omgewing, wat problematies kan wees wanneer onakkurate sensors soos stereovisie gebruik word. Hierdie sensors is egter relatief goedkoop en gerieflik, en daarom behoort 'n stelsel wat hulle dit gebruik om op 'n betroubare manier kaarte te skep baie voordelig te wees. 'n Literatuuroorsig dui daarop dat die besettingsroosteralgoritme 'n geskikte oplossing bied, aangesien dit digte kaarte skep wat met bykomende metings uitgebrei kan word. Hierdie algoritme skep 'n roostervoorstelling van die omgewing en ken 'n waarskynlikheid dat dit beset is aan elke sel in die voorstelling toe. Hierdie waarskynlikhede word deur nuwe metings opgedateer deur gebruik te maak van 'n sensormodel wat beskryf hoe metings verband hou met besettingswaarskynlikhede. Menigde a eidings bestaan vir hierdie sensormodelle, maar dit blyk dat geen van die modelle gebaseer is op betekenisvolle aannames en statistiese beginsels nie. Verder lyk dit asof elkeen beperk word deur 'n aanname van enkelmodale, nul-gemiddelde Gaussiese metingsgeraas. Ons lei 'n beginselfundeerde omgekeerde sensormodel af wat gebaseer is op fisies betekenisvolle aannames. Hierdie model is in staat om enige realistiese foutverspreiding te weerspieël deur die gebruik van 'n Gaussiese mengselmodel (GMM). Dit vereis 'n karakterisering van 'n stereovisie sensor se metingsfoute, wat afhang van die omgewing sowel as watter stereopassingstegniek gebruik is. Daarom stel ons 'n metode voor wat die foutverspreiding van die sensor met behulp van 'n GMM modelleer deur gebruik te maak van metings en absolute verwysings. Die afgeleide ge inverteerde sensormodel is teoreties korrek en kan gevolglik gebruik word om modelle uit die literatuur wat vir uitvoerspoed ontwerp is te evalueer. Ons wys dat op kort afstande die modelle oor die algemeen goeie benaderings bied wat versleg soos die metingsafstand toeneem. Ons toets ons nuwe model deur kaarte te skep met gesimuleerde data, sintetiese data, en werklike data. Vergelykings tussen hierdie resultate en dié van sensormodelle uit die literatuur dui daarop dat ons model besettingswaarskynlikhede betroubaar bereken. Aangesien ons model die beperkte metingsafstand van stereovisie vasvang, lei ons af dat meer akkurate sensors benodig word vir kartering oor groter afstande.

Stereo vision is a means of obtaining three-dimensional information by considering the same scene from two different positions. Stereo correspondence has long been and will continue to be the active research topic in computer vision. The requirement of dense disparity map output is great demand motivated by modern applications of stereo such as three-dimensional high-resolution object reconstruction and view synthesis, which require disparity estimates in all image regions. Stereo correspondence algorithms usually require significant computation. The challenges are computational economy, accuracy and robustness. While a large number of algorithms for stereo matching have been developed, there still leaves the space for improvement especially when a new mathematical tool such as wavelet analysis becomes mature. The aim of the thesis is to investigate the stereo matching approach using wavelet transform with a view to producing efficient and dense disparity map outputs. After the shift invariance property of various wavelet transforms is identified, the main contributions of the thesis are made in developing and evaluating two wavelet approaches (the dyadic wavelet transform and complex wavelet transform) for solving the standard correspondence problem. This comprises an analysis of the applicability of dyadic wavelet transform to disparity map computation, the definition of a waveletbased similarity measure for matching, the combination of matching results from different scales based on the detectable minimum disparity at each scale and the application of complex wavelet transform to stereo matching. The matching method using the dyadic wavelet transform is through SSD correlation comparison and is in particular detailed. A new measure using wavelet coefficients is defined for similarity comparison. The approach applying a dual tree of complex wavelet transform to stereo matching is formulated through phase information. A multiscale matching scheme is applied for both the matching methods. Imaging testing has been made with various synthesised and real image pairs. Experimental results with a variety of stereo image pairs exhibit a good agreement with ground truth data, where available, and are qualitatively similar to published results for other stereo matching approaches. Comparative results show that the dyadic wavelet transform-based matching method is superior in most cases to the other approaches considered.

No description available.

Este trabalho apresenta um procedimento de estimação dos parâmetros de movimento de um corpo rígido, quais sejam, posição, velocidade linear, velocidade angular e aceleração linear, empregando técnicas de visão computacional fundamentadas na manipulação de sequências de imagens estéreo ruidosas. A estimação envolve o uso de detetares de cantos, observação de pontos ruidosos tridimensionais, aquisição e processamento de imagens e estimação de estados. Atenção especial é dada às duas primeiras técnicas pois é a partir delas que os atributos geométricos do objeto são adquiridos durante o processamento de imagens digitalizadas. O processo de recuperação de pontos tridimensionais foi simulado a partir de informações bidimensionais, usando dois métodos de observação de pontos ruidosos. Um desses métodos reduz o problema de determinação dos pontos tridimensionais à resolução de um sistema de equações lineares pelo método dos mínimos quadrados. O outro utiliza informação do range de um ponto imagem e da correspondência entre um ponto projetado em uma câmera e o correspondente ponto conjugado, localizado na outra câmera. Ainda neste trabalho, técnicas aplicáveis na resolução do problema da correspondência entre imagens estéreos foram estudadas. Duas abordagens são consideradas. Em uma delas, o estudo da correspondência é feito a partir da manipulação de imagens segmentadas e na outra utiliza-se as imagens adquiridas. Um experimento empregando o procedimento de estimação dos parâmetros obtido foi realizado. O experimento consistiu no deslocamento de um corpo rígido em uma mesa e na aquisição de uma seqüência de imagens estéreo. As estimativas obtidas foram comparadas com os valores dos parâmetros de movimento observados experimentalmente. / This work presents a procedure for the estimation of object motion parameters, namely, position, linear velocity, angular velocity and linear acceleration, using computer vision techniques based on manipulation of a sequence of noisy stereo images. The estimation involves corner detection, 3-D noisy point observation, image acquisition, digital image processing and state estimates. Special attention was given to the first two techniques mentioned above because the acquisition of the object features during the image processing was based on them. The process of recovering three dimensional points was simulated from the 2-D information, using two methods based on noisy points observation. One of these methods formulates the problem of determination of the three-dimensional points as a linear system equation problem via least square techniques. The other solves the same problem by using the definition of the range of image points and the correspondence that exists between a projected point on one camera and the correspondent conjugate point on the other camera. We still made in this work a study of techniques dedicated to solve the problem of stereo images correspondence. Two approaches are examined. In one of them, the correspondence is made from segmented images. In the other one, the acquired images are used directly. An experiment using the parameter estimate procedure was performed. The experiment consisted in observing a moving object on a test table and in acquiring a stereo image sequence. The estimates were compared with the motion parameters experimentally observed.

M. Ing. / The process of extracting depth information from multiple two-dimensional images taken of the same scene is known as stereo vision. It is of central importance to the field of machine vision as it is a low level task required for many higher level applications. The past few decades has witnessed the development of hundreds of different stereo vision algorithms. This has made it difficult to classify and compare the various approaches to the problem. In this research we provide an overview of the types of approaches that exist to solve the problem of stereo vision. We focus on a specific subset of algorithms, known as local stereo algorithms. Our goal is to critically analyse and compare a representative sample of local stereo algorithm in terms of both speed and accuracy. We also divide the algorithms into discrete interchangeable components and experiment to determine the effect that each of the alternative components has on an algorithm’s speed and accuracy. We investigate even further to quantify and analyse the effect of various design choices within specific algorithm components. Finally we assemble all of the knowledge gained through the experimentation to compose and optimise a novel algorithm. The experimentation highlighted the fact that by far the most important component of a local stereo algorithm is the manner in which it aggregates matching costs. All of the top performing local stereo algorithms dynamically define the shape of the windows over which the matching costs are aggregated. This is done in a manner that aims to only include pixels in a window that is likely to be at the same depth as the depth of the centre pixel of the window. Since the depth is unknown, the cost aggregation techniques use colour and proximity information to best guess whether pixels are at the same depth when defining the shape of the aggregation windows. Local stereo algorithms are usually less accurate than global methods but they are supposed to be faster and more parallelisable. These cost aggregation techniques result in very accurate depth estimates but unfortunately they are also very expensive computationally. We believe the focus of local stereo algorithm development should be speed. Using the experimental results we developed an algorithm that achieves accuracies in the same order of magnitude as the state-of-the-art algorithms while reducing the computation time by over 50%.

This thesis investigates techniques and designs an autonomous visual stereo based navigation sensor to improve stereo visual odometry for purpose of navigation in unknown environments. In particular, autonomous navigation in a space mission context which imposes challenging constraints on algorithm development and hardware requirements. For instance, Global Positioning System (GPS) is not available in this context. Thus, a solution for navigation cannot rely on similar external sources of information. Support to handle this problem is required with the conception of an intelligent perception-sensing device that provides precise outputs related to absolute and relative 6 degrees of freedom (DOF) positioning. This is achieved using only images from stereo calibrated cameras possibly coupled with an inertial measurement unit (IMU) while fulfilling real time processing requirements. Moreover, no prior knowledge about the environment is assumed. Robotic navigation has been the motivating research to investigate different and complementary areas such as stereovision, visual motion estimation, optimisation and data fusion. Several contributions have been made in these areas. Firstly, an efficient feature detection, stereo matching and feature tracking strategy based on Kanade-Lucas-Tomasi (KLT) feature tracker is proposed to form the base of the visual motion estimation. Secondly, in order to cope with extreme illumination changes, High dynamic range (HDR) imaging solution is investigated and a comparative assessment of feature tracking performance is conducted. Thirdly, a two views local bundle adjustment scheme based on trust region minimisation is proposed for precise visual motion estimation. Fourthly, a novel KLT feature tracker using IMU information is integrated into the visual odometry pipeline. Finally, a smart standalone stereo visual/IMU navigation sensor has been designed integrating an innovative combination of hardware as well as the novel software solutions proposed above. As a result of a balanced combination of hardware and software implementation, we achieved 5fps frame rate processing up to 750 initials features at a resolution of 1280x960. This is the highest reached resolution in real time for visual odometry applications to our knowledge. In addition visual odometry accuracy of our algorithm achieves the state of the art with less than 1% relative error in the estimated trajectories. / © Cranfield University, 2014

Memoria académica para optar al título de Periodista / El fenómeno del rock latino representa un hito excepcional dentro de los anales de la música contemporánea. Desde principios de la década de los ’80 y en medio de las dictaduras militares de Argentina y Chile se albergó un prolífico movimiento musical que rápidamente se extendió por el resto del continente. Si bien es cierto, en ambos países el proceso tiene características muy similares, es posible establecer como uno de los puntos primigenios, la censura impuesta en Argentina para la difusión de música en inglés debido a la Guerra de Las Malvinas (1982). A partir de ese momento y casi como un efecto dominó, el rock abre sus banderas de lucha ante el régimen político y desde Argentina irrumpe abruptamente en nuestro país, hacia 1984. Pero nuestra escena rockera no era una página en blanco. Ya existía un claro precedente musical de la mano del llamado “Canto Nuevo”, cuna de grandes figuras nacionales (Hugo Moraga, Eduardo Gatti, “Los Jaivas”, “Quilapayún”, etc.) y nuevos espacios de difusión (“Café del Cerro”, “Teatro Caupolicán, “Teatro Cariola”, etc). Asimismo, los rockeros nacionales tenían a sus principales exponentes en grupos como : “Tumulto”, “Arena Movediza”, “Millantún”, “Sol y Medianoche”, entre otros. Los medios de comunicación locales vivían un tiempo de censura y la radio, aparece como un bastión fundamental para la difusión de este semillero artístico. Surgen dos nombres importantes: Radio Chilena y Radio Galaxia. La primera de ellas difundió gran parte del material del Canto Nuevo, gracias al programa “Nuestro Canto”. La segunda, se convirtió en uno de los principales soportes del rock en español a través del programa “Hecho en Chile” , conducido por Sergio “Pirincho Cárcamo”. Frente a este espectro nacional, entre 1984 y 1985, Chile consume la producción discográfica de rock argentino correspondiente a cinco años. Llegan a nuestra palestra radial, nombres como : Charly García, Celeste Carballo, “Virus”, “Miguel Mateos”, “Los Enanitos Verdes”, “G.I.T.”, entre muchos otros. La camada rockera argentina aterrizó estrepitosamente apoderándose fuertemente de los gustos populares. En medio de aquella maraña musical, surge un nombre poderoso: “SODA STEREO”. Trío bonaerense que meteóricamente saltó a los primeros lugares cantando “Te hacen falta vitaminas” y “¿Por qué no puedo ser Jet?”, de su disco homónimo (1983).

Alpha matting is one of the key techniques in image processing and is used to extract accurate foreground from a still image or video sequences. Chroma keying is a special case of alpha matting with a solid background color. Color spill is one of the difficulties in chroma keying, and it has not been effectively solved by current methods. Sometimes, an image contains both reflected regions and transparent regions. When the foreground in such images is chroma keyed, reflection on the foreground is often falsely treated as transparency and causes unreal foreground extraction and composition. This problem is called color spill. Color spill suppression aims to extract the opaque foreground with the correct transparency descriptor (i.e. alpha value) and remove the reflected background color on it. When the background color presented on the foreground is simultaneously caused by reflection and transparency, color spill suppression becomes extremely challenging. It is because that the reflection removal and the actual transparency estimation is a dilemma. Our proposed method for color spill suppression is to separate reflected regions from transparent regions, and process reflected regions as foreground while keeping transparency unchanged at the same time. In this thesis, we propose a novel method for color spill suppression for chroma keying. The quality of the estimated alpha matte could be significantly improved. In our approach, we suppress color spill by using the polarization and the optical flow algorithm based on disparity estimation. Specifically, we make the assumption that reflection changes more than transparency when the scene is captured by a binocular camera with a polaroid filter. Based on this assumption, we took stereo images with polarization filter, registered stereo images by optical flow and conducted the variance analysis on histograms of input images to separate transparency and reflection. Our experiments show that the opaque foreground with background color spill can be reliably extracted while the real transparency can be kept.

Tato práce se snaží najít odpověď na otázku, zda je v současnosti možné autonomně měřit rychlost vozidel pomocí stereoskopické měřící metody s průměrnou chybou v rozmezí 1 km/h, maximální chybou v rozmezí 3 km/h a směrodatnou odchylkou v rozmezí 1 km/h. Tyto rozsahy chyb jsou založené na požadavcích organizace OIML, jejichž doporučení jsou základem metrologických legislativ mnoha zemí. Pro zodpovězení této otázky je zformulována hypotéza, která je následně testována. Metoda, která využívá stereo kameru pro měření rychlosti vozidel je navržena a experimentálně vyhodnocena. Výsledky pokusů ukazují, že navržená metoda překonává výsledky dosavadních metod. Průměrná chyba měření je přibližně 0.05 km/h, směrodatná odchylka chyby je menší než 0.20 km/h a maximální absolutní hodnota chyby je menší než 0.75 km/h. Tyto výsledky jsou v požadovaném rozmezí a potvrzují tedy testovanou hypotézu.

Detta arbete syftar till att undersöka hur binauralt ljud upplevs i avseende till spelares förmåga att lokalisera ljudkällor i olika våningsplan i digitala spel i jämförelse med stereoljud. Arbetet kopplas till tidigare forskning inom ljudteknik i digitala spel. För att undersöka frågeställningen har en artefakt skapats i form av en digital miljö där målet är att lokalisera ljudkällor i olika våningsplan. Artefakten är skapad i två versioner, där den ena versionen använder binauralt ljud och den andra använder stereoljud. Arbetet har använt kvantitativa och kvalitativa metoder. Resultatet av dessa analyseras och jämförs för att utröna vilken teknik som lämpas bäst för ljudlokalisering i digitala spel.