In a mobile robotic system, the interaction with the surrounding environment is essential in order to complete tasks such as localisation and mapping. This interaction can only be conducted by means of sensors that permit the accumulation of a large amount of information from several sources. However, this information is useless without adequate interpretation; thus, in order to accurately determine the positioning of the robot, it is necessary to identify and characterise landmarks in the environment required to serve as anchoring points for both localisation and mapping. Having constructed the map, an accurate analysis of the information gathered is vital. In this manner, this work is focused on two main aspects of any mobile robotic system: first, the detection and characterisation of highly descriptive landmarks by using image and point cloud processing techniques; and second, the geometrical and spatial analysis of the information gathered from the environment. For the former, two novel techniques based on image processing and geometrical analysis are presented; for the latter, a guaranteed technique for the parameter estimation of primitive shapes using interval analysis is proposed.

The mapping problem is a major player in mobile robotics, and it is essential for many real applications such as disaster response or nuclear decommissioning. Generally, the robotic mapping is addressed under the umbrella of simultaneous localization and mapping (SLAM). Several probabilistic techniques were developed in the literature to approach the SLAM problem, and despite the good performance, their convergence proof is only limited to linear Gaussian models. This thesis proposes an interval SLAM (i-SLAM) algorithm as a new approach that addresses the robotic mapping problem in the context of interval methods. The noise of the robot sensor is assumed bounded, and without any prior knowledge of its distribution, we specify soft conditions that guarantee the convergence of robotic mapping for the case of nonlinear models with non-Gaussian noise. A new theory about compact sets is developed in the context of real analysis to conclude such conditions. Then, a case study is presented where the performance of i-SLAM is compared to the probabilistic counterparts in terms of accuracy and efficiency. Moreover, this work presents an application for i-SLAM using an RGB-D sensor that operates in unknown environments. Interval methods and computer vision techniques are employed to extract planar landmarks in the environment. Then, a new hybrid data association approach is developed using a modified version of bag-of-features method to uniquely identify different landmarks across timesteps. Finally, the results obtained using the proposed data association approach are compared to the typical least-squares approaches, thus demonstrating the consistency and accuracy of the proposed approach.

The objective of the research programme has been to investigate the behaviour of masonry arch vault collapse mechanisms in the context of the problems besetting the national bridge stock. The programme has primarily involved masonry constitutive theoretical studies, supported by laboratory experimentation, which have led to the formulation of novel masonry hinge modelling. The modelling has been developed for practical application in a four hinge masonry vault mechanism analysis and subjected to testing. The technique has been applied in the field supported by a novel application of information technology (IT) image processing, reflecting the growing importance of IT within the construction industry. All theoretical studies have been mounted as micro-computer software with graphics. The accent is upon engineering requirements in practice. Chapter One reviews the context and history of the masonry vault structural form, whose presence has long been commonplace in the United Kingdom, especially on the nation's road network. It is noted that elderly arched road bridges are under continual pressure to carry ever greater loads yet their strength is uncertain. Historically, structural analysts have attempted to resolve the arch's behaviour but present methods are still inexact. Chapter Two describes how, traditionally, masonry has been assumed to possess either a linear stress-strain property or infinite stiffness and strength. An alternative, novel equation for modelling masonry stress-strain laws is presented which may be configured to mimic the behaviour of real materials as well as that of the infinite strength and linear laws it replaces. A numerical analytical procedure has been developed to 'solve' rectangular masonry sections under combined bending and thrust thereby rendering the earlier approximations unnecessary. Chapter Three develops the theme further leading to the numerical determination of limit state hinge characteristics which furnish a static limit state axial thrust/bending moment interaction diagram and a corresponding serviceability limit state, prevention of cracking interaction diagram. Differentiation is thus made possible between hitherto identically-treated though varying natural materials and comparisons made. It is further postulated that any point on a static limit state interaction diagram locus represents a masonry hinge and an extensive series of laboratory model hinge tests is undertaken to demonstrate the point by testing the foregoing theoretical studies. Chapter Four describes the incorporation of the hinge theory into a mechanism-type computer analytical tool. Crucially, the analysis is different from other mechanism analyses by virtue of the hinge modelling, enabling the effects of material properties on arch behaviour to be studied. The software is tested in Chapter Five against prototype data for laboratory model and full size masonry bridges. Chapter Six introduces computer vision, an IT technique that is relatively novel to the structures field. It is adapted to monitor the above laboratory model arch tests and then extended to the monitoring of a multi-span arch bridge test in the field. Computer vision permits the formulation of a hypothesis regarding the unusual mode of failure that occurred and this is supported by a generalisation of the mechanism hinge theory, thereby demonstrating the merits of both techniques. Finally, Chapter Seven draws conclusions on the foregoing and makes suggestions for further work. Supporting documentation is given in the Appendices.

Developing an intelligent inspection system that can enhance the public safety is challenging. An efficient video analytics system can help monitor unusual events and mitigate possible damage or loss. This thesis aims to analyze surveillance video data, report abnormal activities and retrieve corresponding video clips. The surveillance video dataset used in this thesis is derived from ALERT Dataset, a collection of surveillance videos at airport security checkpoints. The video analytics system in this thesis can be thought as a pipelined process. The system takes the surveillance video as input, and passes it through a series of processing such as object detection, multi-object tracking, person-bin association and re-identification. In the end, we can obtain trajectories of passengers and baggage in the surveillance videos. Abnormal events like taking away other's belongings will be detected and trigger the alarm automatically. The system could also retrieve the corresponding video clips based on user-defined query.

De nos jours les méthodes de vision par ordinateur sont utilisées dans de nombreuses applications telles que la vidéo-surveillance, l'aide à la conduite ou la reconstruction 3D par exemple. Ces différentes applications s'appuient généralement sur des procédés de reconnaissance de formes ou de suivi. Pour ce faire, l'image est analysée afin d'en extraire des amers ou des primitives (contours, fonctions d'intensité ou modèles morphologiques). Les méthodes les plus courantes s'appuient sur l'utilisation de points d'intérêt représentant une discontinuité des niveaux de gris caractérisant un coin dans une image. Afin de mettre en correspondance un ensemble de points d'une image à une autre, une description locale est utilisée. Elle permet d'extraire l'information du voisinage de chaque point (valeurs des pixels, des intensités lumineuses, des gradients). Dans le cas d'applications telles que la vidéo-surveillance ou les caméras embarquées, l'ajout d'une information temporelle est fortement recommandé. Cette généralisation est utilisée au sein du laboratoire pour des projets de type véhicules intelligents (CyCab : véhicule intelligent, VELAC : VEhicule du Lasmea pour l'Aide à la Conduite). Les travaux de recherche présentés dans ce mémoire ont pour objectif de mettre en oeuvre différents outils de détection, description et mise en correspondance de points d'intérêt. Un certain nombre de contraintes a été établi, notamment l'utilisation d'images en niveaux de gris, la robustesse et l'aspect générique de la méthode. Dans un premier temps, nous proposons une analyse bibliographique des méthodes existantes. Cette dernière permet en effet d'en déduire les paramètres de mise en oeuvre ainsi que les principaux avantages et inconvénients. Nous détaillons par la suite la méthode proposée. La détection des primitives repose sur l'utilisation du détecteur fast-hessien que nous optimisons. L'utilisation d'une description locale basée sur des histogrammes de gradients orientés (HOG) est très répandue et procure de très bons résultats. Nous proposons de compléter son utilisation par un recalage et une mise à l'échelle d'un masque d'analyse elliptique créant ainsi une nouvelle forme de description locale (E-HOG). La mise en correspondance des points d'intérêt se base quant à elle sur une approche par corrélation à laquelle nous ajoutons un coefficient de sélection ainsi qu'une étape de suppression des doublons. Les différents résultats validant notre approche s'appuient sur l'utilisation de transformations synthétiques (vérité terrain) ou réelles. Nous proposons également une généralisation de notre approche au domaine spatiotemporel, permettant ainsi d'élargir son domaine d'utilisation. Le masque d'analyse précédemment cité est modifié et s'appuie donc sur l'utilisation d'ellipsoïdes. Les tests de validation reposent d'une part sur des séquences vidéo ayant subi des transformations synthétiques et d'autre part sur des séquences réelles issues de la plate-forme PAVIN (Plate-forme d'Auvergne pour Véhicules Intelligents). / Pas de résumé disponible

No description available.

An acoustic array was deployed in the nearsurface layer in Saanich Inlet, B.C. to image breaking waves using only the naturally occurring acoustical radiation from the breaking region over the band [160 Hz, 2000 Hz]. The 1.5-element array was configured as a horizontal cross with an 8 m aperture, bottom-moored, and positioned nominally 3 m beneath the surface. Due to sensor sparseness, the array PSF at any particular frequency was badly contaminated by grating lobes. A novel broadband scheme was devised to combine information at multiple independent frequencies to yield unambiguous images with resolution of about 0.2 m at the sea surface. The broadband scheme assumed space-time separability in the source mutual spectral density. This is only considered valid for breaking waves above about 400 Hz. Nonstationarity and time-bandwidth constraints yielded at most six independent frequency bands within the system passband. A parametric image analysis showed that the images align closely with the wind and can be observed moving downwind with a speed about two-thirds the phase speed of the dominant component of the wind waves. Absolute power levels were found to be consistent with previously published results. The absolute power levels were parameterized by where [special characters omitted] and λ (f) is well-described by a simple first order relation [special characters omitted], where [special characters omitted] varied depending on the size of the wave but b1 appeared to be a more universal constant estimated at -4.55 ± 0.47. The source mechanism for frequencies below about, 400 Hz was modeled two ways: (1) as a point source (which would follow if an acoustically compact “collective oscillation" region had formed), and (2) as due to off-peak spectral contributions from bubbles resonant at 400 Hz. Neither model achieved a satisfactory fit to the observed data. This seems to imply that the mechanism below about 400 Hz was acoustically extended and radiating as energetically as any resonant bubbles. / Graduate

Mirrors are often studied for camera calibration since they provide symmetric relationship for object which can guarantee synchronization in multiple views. However, it is sometimes difficult to compute the reflection matrices of mirrors. This thesis aims to solve the problem of camera calibration and shape recovery from a two-mirror system which is able to generate five views of an object. It firstly studies the similarity relationship of the motion formed by the five views in two-mirror system with the circular motion. It is shown that the motion formed by the five views can be regarded as two circular motions so that we can avoid computing the reflection matrices of mirrors. This thesis then shows the most important problem which is to recover the vanishing line of rotation plane and the imaged circular points by two unknown equal angles via metric rectification. After that, it is easy to recover the imaged rotation axis and the vanishing points X-axis via imaged circular points. Different from the state-of-the-art algorithm, this thesis avoid computing vanishing points X-axis at first because it will cause accumulative error when recovering the imaged rotation axis. By now it is enough to compute the camera intrinsics which is the main objective of this thesis. At last, a 3D visual hull model of object could be reconstructed once all the projective matrices of views were computed. This thesis uses a short video instead of static snapshots so that the reconstructed 3D visual hull model of each frame can be put together based on the motion sequence of object to make a 3D animation. This animation can help to boost the accuracy of action recognition in contrast to 2D video. In general, the action recognition by 2D videos always distinguishes action according to the side of human taken by videos but cannot do for the side does not appear in videos. It then requires to store every direction for human actions of video into database which causes redundancy. The 3D animation can deal with this problem since the reconstructed model can be seen in every direction so that only one 3D animation of human action is needed to store in database. The experimental results show that the more frames are used, the less error of camera intrinsics will occur and the reconstructed 3D model shows the feasibility of the approach.

Thesis (Masters Diploma (Electrical Engineering)--Cape Technikon, Cape Town, 1993 / This thesis describes the design and development of a computer vision system. The system (Video Frame Grabber) will give PCUsers the potential to capture any visual image into the memory of a computer. This computer intelligible image opens the way for new development in computer photography, Image recognition and . Desktop Publishing.

This study proposes a generic model for optical character recognition (OCR) on remote objects, using digitised video and digital camera input. Currently, most applications using this technique are ad hoc. Lack of formalism creates the risk of fragmented adhocracy. The purpose of this model is to introduce some degree of formalism based on classical character recognition, thereby providing a theoretical basis, and to explore the potential of character recognition on digital images for automated reading. The model also propogates the use of off the shelf commercial software and hardware currently available. The model “CRODI” which is an abbreviation for Character Recognition On Digital Images, consists of several objects or building blocks necessary for any remote character recognition application. In order to provide an optimal solution for any application it is necessary to select the most appropriate and effective building blocks. The combination and sequence in which these building blocks are selected is called a visual routine. This study does not only focus on choosing the correct building blocks for an application but also describes how certain visual routines and methodologies can be used to cater for applications with a certain profile. Furthermore, a formal notation in the form of an Expert Support System is introduced to describe optimised visual routines and the selection of building blocks in an efficient way. An example is given in chapter six of the efficiency and effectiveness of the model on a classical but dynamic application, where character recognition is performed on stationary and fast moving vehicles’ number plates. The biggest advantage of CRODI is to propose a generic framework or model from which an intuitive selection of objects, visual routines or methodologies can occur to expedite and optimise remote character recognition on almost any stationary or moving object. / Ehlers, E.M., Prof.