Neural networks represent a powerful means capable of processing various multi-media data. Two applications of artificial neural networks to 3D surface models are examined in this thesis - detection of significant features in 3D data and model classification. The theoretical review of existing self-organizing neural networks is presented and followed by description of feed-forward neural networks and convolutional neural networks (CNN). A novel modification of existing model - N-dimensional convolutional neural networks (ND- CNN) - is introduced. The proposed ND-CNN model is enhanced by an existing technique for enforced knowledge representation. The developed theoretical methods are assessed on supporting experiments with scanned 3D face models. The first experiment focuses on automatic detection of significant facial features while the second experiment performs classification of the models by their gender using the CNN and ND-CNN.

Orchards demand large areas of land, thus they are often situated far from major population centres. As a result it is often difficult to obtain the necessary personnel, limiting both growth and productivity. However, if autonomous robots could be integrated into the operation of the orchard, the manpower demand could be reduced. A key problem for any autonomous robot is localisation; how does the robot know where it is? In agriculture robots, the most common approach is to use GPS positioning. However, in an orchard environment, the dense and tall vegetation restricts the usage to large robots that reach above the surroundings. In order to enable the use of smaller robots, it is instead necessary to use a GPS independent system. However, due to the similarity of the environment and the lack of strong recognisable features, it appears unlikely that typical non-GPS solutions will prove successful. Therefore we present a GPS independent localisation system, specifically aimed for orchards, that utilises the inherent structure of the surroundings. Furthermore, we examine and individually evaluate three related sub-problems. The proposed system utilises a 3D point cloud created from a 2D LIDAR and the robot’s movement. First, we show how the data can be segmented into individual trees using a Hidden Semi-Markov Model. Second, we introduce a set of descriptors for describing the geometric characteristics of the individual trees. Third, we present a robust localisation method based on Hidden Markov Models. Finally, we propose a method for detecting segmentation errors when associating new tree measurements with previously measured trees. Evaluation shows that the proposed segmentation method is accurate and yields very few segmentation errors. Furthermore, the introduced descriptors are determined to be consistent and informative enough to allow localisation. Third, we show that the presented localisation method is robust both to noise and segmentation errors. Finally it is shown that a significant majority of all segmentation errors can be detected without falsely labeling correct segmentations as incorrect. / Eftersom fruktodlingar kräver stora markområden är de ofta belägna långt från större befolkningscentra. Detta gör det svårt att finna tillräckligt med arbetskraft och begränsar expansionsmöjligheterna. Genom att integrera autonoma robotar i drivandet av odlingarna skulle arbetet kunna effektiviseras och behovet av arbetskraft minska. Ett nyckelproblem för alla autonoma robotar är lokalisering; hur vet roboten var den är? I jordbruksrobotar är standardlösningen att använda GPS-positionering. Detta är dock problematiskt i fruktodlingar, då den höga och täta vegetationen begränsar användandet till större robotar som når ovanför omgivningen. För att möjliggöra användandet av mindre robotar är det istället nödvändigt att använda ett GPS-oberoende lokaliseringssystem. Detta problematiseras dock av den likartade omgivningen och bristen på distinkta riktpunkter, varför det framstår som osannolikt att existerande standardlösningar kommer fungera i denna omgivning. Därför presenterar vi ett GPS-oberoende lokaliseringssystem, speciellt riktat mot fruktodlingar, som utnyttjar den naturliga strukturen hos omgivningen.Därutöver undersöker vi och utvärderar tre relaterade delproblem. Det föreslagna systemet använder ett 3D-punktmoln skapat av en 2D-LIDAR och robotens rörelse. Först visas hur en dold semi-markovmodell kan användas för att segmentera datasetet i enskilda träd. Därefter introducerar vi ett antal deskriptorer för att beskriva trädens geometriska form. Vi visar därefter hur detta kan kombineras med en dold markovmodell för att skapa ett robust lokaliseringssystem.Slutligen föreslår vi en metod för att detektera segmenteringsfel när nya mätningar av träd associeras med tidigare uppmätta träd. De föreslagna metoderna utvärderas individuellt och visar på goda resultat. Den föreslagna segmenteringsmetoden visas vara noggrann och ge upphov till få segmenteringsfel. Därutöver visas att de introducerade deskriptorerna är tillräckligt konsistenta och informativa för att möjliggöra lokalisering. Ytterligare visas att den presenterade lokaliseringsmetoden är robust både mot brus och segmenteringsfel. Slutligen visas att en signifikant majoritet av alla segmenteringsfel kan detekteras utan att felaktigt beteckna korrekta segmenteringar som inkorrekta.

The improvements in 3D scanning technologies have led the necessity for managing range image databases. Hence, the requirement of describing and indexing this type of data arises. Up to now, rather much work is achieved on capturing, transmission and visualization / however, there is still a gap in the 3D semantic analysis between the requirements of the applications and the obtained results. In this thesis we studied 3D semantic analysis of range data. Under this broad title we address segmentation of range scenes, correspondence matching of range images and the similarity retrieval of range models. Inputs are considered as single view depth images. First, possible research topics related to 3D semantic analysis are introduced. Planar structure detection in range scenes are analyzed and some modifications on available methods are proposed. Also, a novel algorithm to segment 3D point cloud (obtained via TOF camera) into objects by using the spatial information is presented. We proposed a novel local range image matching method that combines 3D surface properties with the 2D scale invariant feature transform. Next, our proposal for retrieving similar models where the query and the database both consist of only range models is presented. Finally, analysis of heat diffusion process on range data is presented. Challenges and some experimental results are presented.

Σήμερα υπάρχουν πολυάριθμα εργαλεία για την κατασκευή και παραμετροποίηση τρισδιάστατων μοντέλων με το καθένα από αυτά να χρησιμοποιεί το δικό του πρωτόκολλο περιγραφής της τρισδιάστατης πληροφορίας που αποθηκεύει και επεξεργάζεται. Εντούτοις δεν είναι λίγες η φορές που απαιτείται η μεταφορά περιεχομένου απο το ένα εργαλείο στο άλλο. Το παραπάνω οδήγησε στην ανάγκη δημιουργίας κοινώς αποδεκτών πρωτοκόλλων περιγραφής της τρισδιάστατης πληροφορίας για την διευκόλυνση της διαχείρισής της. Απο τα πρωτόκολλα αυτά, το COLLADA φαίνεται να επικρατεί λόγω του οτι είναι ανοιχτό, επεκτάσιμο και ευρέως διαδεδομένο. Στην παρούσα εργασία γίνεται παρουσίαση αυτού και δίνεται έμφαση στους λόγους που οδηγούν στην ολοένα και ταχύτερη ανάπτυξή του και στις τελευταίες λειτουργείες που έχουν προστεθεί. Στη συνέχεια, με βάση το πρωτοκολλο αυτό, υλοποιείται μια πιλοτική εφαρμογή για την απεικόνιση και την αλληλεπίδραση με τρισδιάτατα αντικείμενα, χρησιμοποιώντας σύγχρονες τεχνικές και τεχνολογίες για διαδικτυακή παρουσίαση τρισδιάστατου περιεχομένου. Η εφαρμογή αυτή στοχεύει σε φυλλομετρητές προσωπικών υπολογιστών, ενδέχεται ωστόσο να επεκταθεί ώστε να είναι δυνατή η χρήση της ακόμα και από φυλλομετρητές τελευταίας τεχνολογίας κινητών τηλεφώνων (iPhone). Τα συμπεράσματα που θα προκύψουν από την χρήση της εφαρμογής αυτής ενδέχεται να οδηγήσουν στην δημιουργία ενός μετέπειτα ολοκληρωμένου προϊόντος. / Today there are numerous tools for the construction and configuration of three-dimensional models, each of them uses its own protocol describes the three-dimensional information stored and processed. However, there are few times when the need to transfer content from one tool to another. The above led to the need for commonly accepted protocol describes the three-dimensional information to facilitate management. Of these protocols, the COLLADA seems to prevail because it is open, scalable and ubiquitous. In the present study it and focus on the reasons leading to ever more rapid development in recent operations that have been added. Then, based on this protocol, implemented a pilot application to display and interact with trisdiatata items using modern techniques and technologies for web-dimensional presentation of content. This application is targeted at PC browsers, but may be extended to allow the use of browsers and even the art mobile phones (iPhone). The conclusions arising from the use of this application may result in the creation of a finished product later.

Thesis (MSc (Applied Mathematics))--Stellenbosch University, 2008. / A popular method for interpolating multidimensional scattered data is using radial basis functions. In this thesis we present the basic theory of radial basis function interpolation and also regard the solvability and stability of the method. Solving the interpolant directly has a high computational cost for large datasets, hence using numerical methods to approximate the interpolant is necessary. We consider some recent numerical algorithms. Software to implement radial basis function interpolation and to display the 3D interpolants obtained, is developed. We present results obtained from using our implementation for radial basis functions on GIS and 3D face data as well as an image warping application.

La fabrication de pièces manufacturées génère un nombre très important de données de différents types définissant les géométries de fabrication ainsi que la qualité de production. Ce travail de thèse s’inscrit dans le cadre de la réalisation d’un système de vision cognitif dédié à l’évaluation d’objets 3D manufacturés incluant éventuellement des surfaces gauches, en tenant compte des tolérances géométriques et des incertitudes. Ce système permet un contrôle exhaustif de pièces manufacturées et offre la possibilité d’une inspection tridimensionnelle automatique de la pièce. La mise en place d’un système de mesures multi-capteurs (passifs et actifs) a permis d’améliorer significativement la qualité d’évaluation par le biais d’une reconstruction tridimensionnelle enrichie de l’objet à évaluer. En particulier, nous avons employé simultanément un système stéréoscopique de vision et un système à projection de lumière structurée afin de reconstruire les contours et les surfaces de différents objets 3D. / Producing industrially manufactured parts generates a very large number of data of various types defining the manufacturing geometries as well as the quality of production. This PhD work has been carried out within the framework of the realization of a cognitive vision system dedicated to the 3D evaluation of manufactured objects including possibly free form surfaces, taking into account the geometric tolerances and uncertainties. This system allows the comprehensive control of manufactured parts, and provides the means for their automated 3D dimensional inspection. The implementation of a multi-sensor (passive and active) measuring system enabled to improve significantly the assessment quality through an enriched three-dimensional reconstruction of the object to be evaluated. Specifically, we made use simultaneously of a stereoscopic vision system and of a structured light based system in order to reconstruct the edges and surfaces of various 3D objects.

Multicomponent seismic imaging techniques improve geological interpretation by providing crucial information about subsurface characteristics. These techniques deliver different images of the same subsurface using multiple waveforms. Compressional (P) and shear (S) waves respond to lithology and fluid variations differently, providing independent measurements of rock and fluid properties. Joint interpretation of multicomponent images requires P-wave and S-wave events to be aligned in depth. The process of identifying P and S events from the same reflector is called depth-registration. The purpose of this investigation is to illustrate procedures for depth-registering P and S seismic data when the most fundamental information needed for depth-registration – reliable velocity data – are not available. This work will focus on the depth-registration of a 9-component 3-dimensional seismic dataset targeting the Sycamore formation in Stephens County, Oklahoma. The survey area – 16 square miles – is located in Sho-Vel-Tum oilfield. Processed P-P, SV-SV, and SH-SH wave data are available for post-stack analysis. However, the SV-data volume will not be interpreted because of its inferior data-quality compared to the SH-data volume. Velocity data are essential in most depth-registration techniques: they can be used to convert the seismic data from the time domain to the depth domain. However, velocity data are not available within the boundaries of the 9C/3D seismic survey. The data are located in a complex area that is folded and faulted in the northwest part of the Ardmore basin, between the eastern Arbuckle Mountains and the western Wichita Mountains. Large hydrocarbon volumes are produced from stratigraphic traps, fault closures, anticlines, and combination traps. Sho-Vel-Tum was ranked 31st in terms of proved oil reserves among U.S. oil fields by a 2009 survey. I will interpret different depth-registered horizons on the P-wave and S-wave seismic data volumes. Then, I will present several methods to verify the accuracy of event-registration. Seven depth-registered horizons are mapped through the P-P and SH-SH seismic data. These horizons show the structural complexity that imposes serious challenges on well drilling within the Sho-Vel-Tum oil field. Interval Vp/Vs – a seismic attribute often used as lithological indicator – was mapped to constrain horizon picking and to characterize lateral stratigraphic variations. / text

Arts and Humanities Research Council, through a Collaborative Doctoral Partnership studentship / The full text will be available at the end of the embargo period

Les fonctions de texture directionnelle "Bidirectional Texture Function" (BTF) ont rencontrés un certain succès ces dernières années, notamment pour le rendu temps-réel d'images de synthèse, grâce à la fois au réalisme qu'elles apportent et au faible coût de calcul nécessaire. Cependant, un inconvénient de cette approche reste la taille gigantesque des données : de nombreuses méthodes ont été proposées afin de les compresser. Dans ce document, nous proposons une nouvelle représentation des BTFs qui améliore la cohérence des données et qui permet ainsi une compression plus efficace. Dans un premier temps, nous étudions les méthodes d'acquisition et de génération des BTFs et plus particulièrement, les méthodes de compression adaptées à une utilisation sur cartes graphiques. Nous réalisons ensuite une étude à l'aide de notre logiciel "BTFInspect" afin de déterminer parmi les différents phénomènes visuels dans les BTFs, ceux qui influencent majoritairement la cohérence des données par texel. Dans un deuxième temps, nous proposons une nouvelle représentation pour les BTFs, appelées Flat Bidirectional Texture Function (Flat-BTFs), qui améliore la cohérence des données d'une BTF et donc la compression des données. Dans l'analyse des résultats obtenus, nous montrons statistiquement et visuellement le gain de cohérence obtenu ainsi que l'absence d'une perte significative de qualité en comparaison avec la représentation d'origine. Enfin, dans un troisième temps, nous démontrons l'utilisation de notre nouvelle représentation dans des applications de rendu en temps-réel sur cartes graphiques. Puis, nous proposons une compression de l'apparence grâce à une méthode de quantification sur GPU et présentée dans le cadre d'une application de diffusion de données 3D entre un serveur contenant des modèles 3D et un client désirant visualiser ces données. / In recent years, Bidirectional Texture Function (BTF) has emerged as a flexible solution for realistic and real-time rendering of material with complex appearance and low cost computing. However one drawback of this approach is the resulting huge amount of data: several methods have been proposed in order to compress and manage this data. In this document, we propose a new BTF representation that improves data coherency and allows thus a better data compression. In a first part, we study acquisition and digital generation methods of BTFs and more particularly, compression methods suitable for GPU rendering. Then, We realise a study with our software BTFInspect in order to determine among the different visual phenomenons present in BTF which ones induce mainly the data coherence per texel. In a second part, we propose a new BTF representation, named Flat Bidirectional Texture Function (Flat-BTF), which improves data coherency and thus, their compression. The analysis of results show statistically and visually the gain in coherency as well as the absence of a noticeable loss of quality compared to the original representation. In a third and last part, we demonstrate how our new representation may be used for realtime rendering applications on GPUs. Then, we introduce a compression of the appearance thanks to a quantification method on GPU which is presented in the context of a 3D data streaming between a server of 3D data and a client which want visualize them.

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.