<p>Just how far is it possible to make learning of new parts for recognition and robot picking autonomous? This thesis initially gives the prerequisites for the steps in learning and calibration that are to be automated. Among these tasks are to select a suitable part model from numerous candidates with the help of a new part segmenter, as well as computing the spatial extent of this part, facilitating robotic collision handling. Other tasks are to analyze the part model in order to highlight correct and suitable edge segments for increasing pattern matching certainty, and to choose appropriate acceptance levels for pattern matching. Furthermore, tasks deal with simplifying camera calibration by analyzing the calibration pattern, as well as compensating for differences in perspective at great depth variations, by calculating the centre of perspective of the image. The image processing algorithms created in order to solve the tasks are described and evaluated thoroughly. This thesis shows that simplification of steps of learning and calibration, by the help of advanced image processing, really is possible.</p>

Over the past 50 years, electronics manufacturing industry has undergone revolutionary changes, which have provided consumers with a plethora of electronic products. The increase in functionality of electronic products and decrease in cost due to continuous miniaturization and lower manufacturing costs have evolved over time. As electronics manufacturing technology becomes more advanced, reliability of electronic products and devices have become more of a concern. Thermomechanical reliability in electronics is studied in this research. Thermomechanical failures are failures due to temperature loading conditions electronic products and devices experience during manufacturing and service. The thermomechanical issue studied in this research is the effect of convective solder reflow on the warpage of packaged electronic devices, bare boards and chip packages. A convective reflow-projection moir warpage measurement system is designed and implemented in this research. The system is the first available system capable of measuring warpage of printed wiring boards (PWBs) with and without electronic components during simulated convective reflow process. A finite element prediction tool is also developed to predict the warpage of PWBs populated with plastic ball grid array (PBGA) packages. The developed warpage measurement system as well as the developed finite element model is used to study various PWB assembly (PWBA) configurations during simulated convective reflow processes.

This thesis makes significant contributions to the object detection problem in computer vision. The object detection problem is, given a digital image of a scene, to detect the relevant object in the image. One technique for performing object detection, called ``active contours,' optimizes a constructed energy that is defined on contours (closed curves) and is tailored to image features. An optimization method can be used to perform the optimization of the energy, and thereby deform an initially placed contour to the relevant object. The typical optimization technique used in almost every active contour paper is evolving the contour by the energy's gradient descent flow, i.e., the steepest descent flow, in order to drive the initial contour to (hopefully) the minimum curve. The problem with this technique is that often times the contour becomes stuck in a sub-optimal and undesirable local minimum of the energy. This problem can be partially attributed to the fact that the gradient flows of these energies make use of only local image and contour information. By local, we mean that in order to evolve a point on the contour, only information local to that point is used. Therefore, in this thesis, we introduce a new class of flows that are global in that the evolution of a point on the contour depends on global information from the entire curve. These flows help avoid a number of problems with traditional flows including helping in avoiding undesirable local minima. We demonstrate practical applications of these flows for the object detection problem, including applications to both image segmentation and visual object tracking.

Computer vision is the science that studies how machines understand scenes and automatically make decisions based on meaningful information extracted from an image or multi-dimensional data of the scene, like human vision. One common and well-studied field of computer vision is visual tracking. It is challenging and active research area in the computer vision community. Visual tracking is the task of continuously estimating the pose of an object of interest from the background in consecutive frames of an image sequence. It is a ubiquitous task and a fundamental technology of computer vision that provides low-level information used for high-level applications such as visual navigation, human-computer interaction, and surveillance system. The focus of the research in this thesis is visual tracking and its applications. More specifically, the object of this research is to design a reliable tracking algorithm for a deformable object that is robust to clutter and capable of occlusion handling and target reacquisition in realistic tracking scenarios by using statistical and geometric methods. To this end, the approaches developed in this thesis make extensive use of region-based active contours and particle filters in a variational framework. In addition, to deal with occlusions and target reacquisition problems, we exploit the benefits of coupling 2D and 3D information of an image and an object. In this thesis, first, we present an approach for tracking a moving object based on 3D range information in stereoscopic temporal imagery by combining particle filtering and geometric active contours. Range information is weighted by the proposed Gaussian weighting scheme to improve segmentation achieved by active contours. In addition, this work present an on-line shape learning method based on principal component analysis to reacquire track of an object in the event that it disappears from the field of view and reappears later. Second, we propose an approach to jointly track a rigid object in a 2D image sequence and to estimate its pose in 3D space. In this work, we take advantage of knowledge of a 3D model of an object and we employ particle filtering to generate and propagate the translation and rotation parameters in a decoupled manner. Moreover, to continuously track the object in the presence of occlusions, we propose an occlusion detection and handling scheme based on the control of the degree of dependence between predictions and measurements of the system. Third, we introduce the fast level-set based algorithm applicable to real-time applications. In this algorithm, a contour-based tracker is improved in terms of computational complexity and the tracker performs real-time curve evolution for detecting multiple windows. Lastly, we deal with rapid human motion in context of object segmentation and visual tracking. Specifically, we introduce a model-free and marker-less approach for human body tracking based on a dynamic color model and geometric information of a human body from a monocular video sequence. The contributions of this thesis are summarized as follows: 1. Reliable algorithm to track deformable objects in a sequence consisting of 3D range data by combining particle filtering and statistics-based active contour models. 2. Effective handling scheme based on object's 2D shape information for the challenging situations in which the tracked object is completely gone from the image domain during tracking. 3. Robust 2D-3D pose tracking algorithm using a 3D shape prior and particle filters on SE(3). 4. Occlusion handling scheme based on the degree of trust between predictions and measurements of the tracking system, which is controlled in an online fashion. 5. Fast level set based active contour models applicable to real-time object detection. 6. Model-free and marker-less approach for tracking of rapid human motion based on a dynamic color model and geometric information of a human body.

Οι καρδιαγγειακές παθήσεις αποτελούν σήμερα την πρώτη αιτία θανάτου στις αναπτυγμένες χώρες. Οι αιτίες που τις προκαλούν συνδέονται πολύ συχνά με τις ιδιότητες και την γενική κατάσταση των τοιχωμάτων των μεγάλων αρτηριών. Η υπερηχητική απεικόνιση των τελευταίων είναι εξαιρετικά σημαντική για τη διάγνωση πιθανών παθολογικών καταστάσεων, καθώς χαρακτηρίζεται από χαμηλό κόστος και ελάχιστη επιβάρυνση για τον οργανισμό του ασθενούς, ενώ μπορεί να πραγματοποιείται σε πραγματικό χρόνο. Επιπλέον, οι υπερηχητικές τεχνικές απεικόνισης επιτρέπουν την παρακολούθηση της κίνησης των αρτηριακών τοιχωμάτων, από την οποία μπορούν να εξαχθούν αρκετά ασφαλή συμπεράσματα για την κατάστασή τους. Για την παρακολούθηση της κίνησης των αρτηριακών τοιχωμάτων έχουν χρησιμοποιηθεί διάφορες μέθοδοι, με κυριότερες αυτές που βασίζονται στο φαινόμενο Doppler (Tissue Doppler Imaging), τις διαφορικές μεθόδους οπτικής ροής και τις μεθόδους ταύτισης περιοχών (block matching). Οι μέθοδοι Doppler είναι εξαιρετικά ακριβείς, μόνο όμως κοντά στη διεύθυνση της υπερηχητικής δέσμης. Οι μέθοδοι οπτικής ροής μπορούν να χρησιμοποιηθούν σε διδιάστατες απεικονίσεις με αρκετά ικανοποιητική ακρίβεια, αδυνατούν ωστόσο να παρακολουθήσουν μεγάλες μετατοπίσεις. Από την άλλη πλευρά, οι μέθοδοι ταύτισης περιοχών δεν παρουσιάζουν τα παραπάνω προβλήματα, υστερούν όμως σε ακρίβεια. Μια σχετικά νέα τεχνική με ευρεία εφαρμογή στην ιατρική απεικόνιση είναι τα ενεργά περιγράμματα (active contours). Πρόκειται για παραμετρικές καμπύλες που κινούνται στο επίπεδο της εικόνας έτσι ώστε να ελαχιστοποιείται ένα ενεργειακό συναρτησιακό και επιτρέπουν την ανίχνευση αντικειμένων στην εικόνα. Στις κλασικές μεθόδους των ενεργών περιγραμμάτων, η αρχική καμπύλη πρέπει να ορίζεται κοντά στο προς ανίχνευση αντικείμενο. Για την αντιμετώπιση του προβλήματος αυτού έχουν προταθεί διάφορες βελτιώσεις του κλασικού μοντέλου των ενεργών περιγραμμάτων, όπως η εισαγωγή της λεγόμενης «δύναμης μπαλονιού». Τα ενεργά περιγράμματα μπορούν να χρησιμοποιηθούν και για παρακολούθηση κίνησης σε ακολουθίες εικόνων, καθώς μπορούν να προσαρμόζονται στα εξέχοντα χαρακτηριστικά των κινούμενων δομών. Ωστόσο, στην υπερηχητική απεικόνιση των αρτηριακών τοιχωμάτων, η περιπλοκότητα της κίνησής τους και ο έντονος θόρυβος καθιστούν ιδιαίτερα δύσκολη την άμεση εφαρμογή των ενεργών περιγραμμάτων για την παρακολούθηση κίνησης. Στόχος της παρούσας εργασίας είναι ο συνδυασμός των ενεργών περιγραμμάτων και των μεθόδων ταύτισης περιοχών για την αυτοματοποίηση της παρακολούθησης κίνησης σε ακολουθίες εικόνων των τοιχωμάτων αρτηριών (συγκεκριμένα της καρωτιδικής και της βραχιακής) και για τη βελτίωση της επαναληψιμότητας των σχετικών μετρήσεων. Αρχικά, εφαρμόστηκαν οι μέθοδοι ταύτισης περιοχών ενός επιπέδου (Single Level Block Matching) και πολλών επιπέδων (Multilevel Block Matching) για την παρακολούθηση της κίνησης των αρτηριακών τοιχωμάτων από ακολουθίες εγκάρσιων τομών της καρωτιδικής και της βραχιακής αρτηρίας. Μια κλειστή καμπύλη ορίστηκε από το χρήστη στο πρώτο πλαίσιο της ακολουθίας, έτσι ώστε να αντιστοιχεί κατά προσέγγιση στο περίγραμμα των ορίων του αρτηριακού τοιχώματος και καταγράφηκε η επιφάνεια που περικλείεται από την καμπύλη αυτή κατά τη διάρκεια ενός καρδιακού κύκλου. Η μετατόπιση των σημείων της καμπύλης από πλαίσιο σε πλαίσιο εκτιμήθηκε με τις μεθόδους ταύτισης περιοχών. Η μορφή της γραφικής παράστασης της επιφάνειας αυτής σε συνάρτηση με το χρόνο (δηλαδή τον αριθμό του πλαισίου) αποτελεί έναν πολύ καλό δείκτη της κατάστασης της αρτηρίας. Η αυτοματοποίηση της διαδικασίας λήψης των παραπάνω μετρήσεων μπορεί να επιτευχθεί αν η επιλογή της αρχικής κλειστής καμπύλης δεν βασίζεται στην εκτίμηση του χρήστη αλλά στην ανίχνευση των τοιχωμάτων με ενεργά περιγράμματα. Το κλασικό μοντέλο των ενεργών περιγραμμάτων και το μοντέλο της «δύναμης μπαλονιού» εφαρμόστηκαν για αυτό το σκοπό στο πρώτο πλαίσιο των ακολουθιών εικόνων των αρτηριών. Διαπιστώθηκε ότι το μοντέλο της δύναμης μπαλονιού δίνει ικανοποιητικά αποτελέσματα ανίχνευσης των αρτηριακών τοιχωμάτων και μάλιστα με ικανοποιητική επαναληψιμότητα, καθώς το αποτέλεσμα της ανίχνευσης δεν διαφοροποιούνταν σημαντικά από την επιλογή της αρχικής κλειστής καμπύλης του ενεργού περιγράμματος, αρκεί η ακτίνα της τελευταίας να είναι τέτοια ώστε η καμπύλη να βρίσκεται εξ ολοκλήρου στο εσωτερικό της αρτηρίας. Στη συνέχεια, η καμπύλη που προέκυψε από την ανίχνευση των τοιχωμάτων χρησιμοποιήθηκε ως αρχική καμπύλη για την παρακολούθηση κίνησης με τις μεθόδους ταύτισης περιοχών. Τα αποτελέσματα που προέκυψαν δεν διαφέρουν σημαντικά σε σχέση με την περίπτωση όπου ο ορισμός της καμπύλης στο πρώτο πλαίσιο γίνεται από το χρήστη. Συνεπώς, η ανίχνευση των αρτηριακών τοιχωμάτων με ενεργά περιγράμματα μπορεί να χρησιμοποιηθεί για να βελτιώσει την επαναληψιμότητα των μετρήσεων για την παρακολούθηση κίνησης και να συμβάλει στην αυτοματοποίηση της διαδικασίας λήψης τους. / Cardiovascular diseases are the leading cause of death today in developed countries. Their causes are very frequently related with the status of artery walls. Ultrasonic imaging is very important for the diagnosis of possible arterial pathology, because it is of low cost, safe for the patient and can be performed in real time. Ultrasonic imaging also allows arterial wall motion tracking, which can provide critical diagnostic information. Motion tracking methods include Tissue Doppler Imaging (TDI), differential optical flow methods and block matching. Tissue Doppler Imaging offers excellent accuracy, restricted however to directions close to the direction of the ultrasonic beam. Optical flow methods can be used in two dimensions with considerable accuracy, but they fail in cases of fast moving structures. In the case of block matching, no such problems have to be dealt with, however with significant cost in accuracy. Active contours, a relatively new technique widely used in medical imaging, are parameterized curves moving on the image plane in order to minimize an energy functional and allowing object detection. Classical active contour methods require that the initial curve of the model is defined close to the object to be detected. In order to avoid this, several techniques have been proposed, such as the so-called “balloon force”. Active contours can also be used for motion tracking in series of image frames, provided that they can fit to salient features of moving structures. In arterial wall ultrasonic imaging however, motion complexity and noise obstruct motion tracking with active contours. In the current study active contours and block matching methods are combined to improve reproducibility of motion tracking measurements in series of artery wall images (namely for the carotid and brachial artery). Single level and multilevel block matching methods were used for artery wall motion tracking. A closed curve was defined by the user in the first frame of the image series, both for the carotid and brachial artery. This curve is a rough estimation of the arterial wall contour. The area enclosed by the curve is recorded throughout a cardiac cycle. Curve movement is estimated with block matching methods. The graph pattern of enclosed area versus time (i.e. frame number) is a very good indicator for the status of the artery. The above process can be automatized if the initial closed curve is produced by object detection with active contours and not by estimation. The active contours classical model and the balloon force model were used for artery wall detection in the first frame of the artery image series. The balloon force model yielded satisfactory wall detection results with considerable reproducibility. The choice of the dimensions of the initial contour of the model did not affect the final result considerably, provided that the initial contour is fully placed inside the arterial lumen. The curve that resulted from object detection was used to initialize the motion tracking process with block matching methods. In this way, similar motion tracking results can be obtained for the artery image series, but with much improved reproducibility.

Computer Vision aims at developing techniques to extract and exploit information from images. The successful applications of computer vision approaches are multiple and have benefited diverse fields such as manufacturing, medicine or defense. Some of the most challenging tasks performed by computer vision systems are arguably segmentation and tracking. Segmentation can be defined as the partitioning of an image into homogeneous or meaningful regions. Tracking also aims at extracting meaning or information from images, however, it is a dynamic task that operates on temporal (video) sequences. Active contours have been proven to be quite valuable at performing the two aforementioned tasks. The active contours framework is an example of variational approaches, in which a problem is compactly (and elegantly) described and solved in terms of energy functionals. The objective of the proposed research is to develop statistical and shape-based tools inspired from or completing the geometric active contours methodology. These tools are designed to perform segmentation and tracking. The approaches developed in the thesis make an extensive use of partial differential equations and differential geometry to address the problems at hand. Most of the proposed approaches are cast into a variational framework. The contributions of the thesis can be summarized as follows: 1. An algorithm is presented that allows one to robustly track the position and the shape of a deformable object. 2. A variational segmentation algorithm is proposed that adopts a shape-driven point of view. 3. Diverse frameworks are introduced for including prior knowledge on shapes in the geometric active contour framework. 4. A framework is proposed that combines statistical information extracted from images with shape information learned a priori from examples 5. A technique is developed to jointly segment a 3D object of arbitrary shape in a 2D image and estimate its 3D pose with respect to a referential attached to a unique calibrated camera. 6. A methodology for the non-deterministic evolution of curves is presented, based on the theory of interacting particles systems.

The generation of urban digital elevation models from satellite images using stereo reconstruction techniques poses several challenges due to its precision requirements. In this thesis we study three problems related to the reconstruction of urban models using stereo images in a low baseline disposition. They were motivated by the MISS project, launched by the CNES (Centre National d'Etudes Spatiales), in order to develop a low baseline acquisition model. The first problem is the restoration of irregularly sampled images and image fusion using a band limited interpolation model. A novel restoration algorithm is proposed, which incorporates the image formation model as a set of local constraints, and uses of a family of regularizers that allow to control the spectral behavior of the solution. Secondly, the problem of interpolating sparsely sampled images is addressed using a self-similarity prior. The related problem of image inpainting is also considered, and a novel framework for exemplar-based image inpainting is proposed. This framework is then extended to consider the interpolation of sparsely sampled images. The third problem is the regularization and interpolation of digital elevation models imposing geometric restrictions. The geometric restrictions come from a reference image. For this problem three different regularization models are studied: an anisotropic minimal surface regularizer, the anisotropic total variation and a new piecewise affine interpolation algorithm. / La generación de modelos urbanos de elevación a partir de imágenes de satélite mediante técnicas de reconstrucción estereoscópica presenta varios retos debido a sus requisitos de precisión. En esta tesis se estudian tres problemas vinculados a la generación de estos modelos partiendo de pares estereoscópicos adquiridos por satélites en una configuración con baseline pequeño. Estos problemas fueron motivados por el proyecto MISS, lanzado por el CNES (Centre National d'Etudes Spatiales) con el objetivo de desarrollar las técnicas de reconstrucción para imágenes adquiridas con baseline pequeños. El primer problema es la restauración de imágenes muestreadas irregularmente y la fusión de imágenes usando un modelo de interpolación de banda limitada. Se propone un nuevo método de restauración, el cual usa una familia de regularizadores que permite controlar el decaimiento espectral de la solución e incorpora el modelo de formación de imagen como un conjunto de restricciones locales. El segundo problema es la interpolación de imágenes muestreadas en forma dispersa usando un prior de auto similitud, se considera también el problema relacionado de inpainting de imágenes. Se propone un nuevo framework para inpainting basado en ejemplares, el cual luego es extendido a la interpolación de imágenes muestreadas en forma dispersa. El tercer problema es la regularización e interpolación de modelos digitales de elevación imponiendo restricciones geométricas las cuales se extraen de una imagen de referencia. Para este problema se estudian tres modelos de regularización: un regularizador anisótropo de superficie mínima, la variación total anisótropa y un nuevo algoritmo de interpolación afín a trozos.

The text covers the theory of the Mumford and Shah model for digital image segmentation. The strong and weak formulation is presented and the questions of existence, uniqueness, and solution regularity is answered. Then, a particular variant of the model called `active contours without edges' is numerically implemented. This implementation is tested on several images, the results are presented in detail and theoretically explained.

This master’s thesis deals with kidney segmentation in perfusion magnetic resonance image sequences. Kidney segmentation is carry out by a few methods such as regionbased techniques, deformable models, specimen-based methods, edge-oriented methods etc. The universal algorithm for patient kidney segmentation still does not exist. Proposed method is an active contour Snake, which is created in programming environment MatLab. Final contours are quantitatively and visually compared to manual kidney segmentation.

Autofluorescence retinal images are obtained with a confocal laser scanning ophthalmoscope, and used for the diagnostic of glaucoma. Glaucoma causes a gradual death of nerve cells and can cause blindness. Retina autofluorescence is caused by pigment lipofuscin, which causes cell damage. The aim of this work was to study methods suitable for segmentation of autofluorescence zones and method for tracking objects in an image. In this project was implemented algorithm of autofluorescence zone detection using method of region growing, designed and realized method for tracking autofluorescence regions.