Making a computer &lsquo / see&rsquo / is certainly one of the greatest challanges for today. Apart from possible applications, the solution may also shed light or at least give some idea on how, actually, the biological vision works. Many problems faced en route to successful algorithms require finding corresponding tokens in different views, which is termed the correspondence problem. For instance, given two images of the same scene from different views, if the camera positions and their internal parameters are known, it is possible to obtain the 3-Dimensional coordinates of a point in space, relative to the cameras, if the same point may be located in both images. Interestingly, the camera positions and internal parameters may be extracted solely from the images if a sufficient number of corresponding tokens can be found. In this sense, two subproblems, as the choice of the tokens and how to match these tokens, are examined. Due to the arbitrariness of the image pairs, invariant schemes for extracting and matching interest points, which were taken as the tokens to be matched, are utilised. In order to appreciate the ideas of the mentioned schemes, topics as scale-space, rotational and affine invariants are introduced. The geometry of the problem is briefly reviewed and the epipolar constraint is imposed using statistical outlier rejection methods. Despite the satisfactory matching performance of simple correlation-based matching schemes on small-baseline pairs, the simulation results show the improvements when the mentioned invariants are used on the cases for which they are strictly necessary.

The aim of this thesis is to develop a stereo vision system to locate and classify objects moving on a conveyor belt. The vision system determines the locations of the objects with respect to a world coordinate system and class of the objects. In order to estimate the locations of the objects, two cameras placed at different locations are used. Image processing algorithms are employed to extract some features of the objects. These features are fed to stereo matching and classifier algorithms. The results of stereo matching algorithm are combined with the calibration parameters of the cameras to determine the object locations. Pattern classification techniques (Bayes and Nearest Neighbor classifiers) are used to classify the objects. The linear velocity of the objects is determined by using an encoder mounted to the shaft of the motor driving the conveyor belt. A robot can plan a sequence of motion to pick the object from the conveyor belt by using the output of the proposed system.

Το αντικείμενο της εργασίας είναι η τρισδιάστατη ανακατασκευή ενός αντικειμένου ή ενός χώρου, μέσα από τουλάχιστο δύο φωτογραφίες του. Το θέμα της εργασίας είναι μέρος του τομέα της Υπολογιστικής Όρασης, που έχει μεγάλη άνθιση τα τελευταία χρόνια λόγω των πολλών εφαρμογών, όπου η γνώση της τρισδιάστατης δομής ενός αντικειμένου ή ενός χώρου κρίνεται απαραίτητη. Βέβαια, συνέβαλε σε αυτό και η ραγδαία εξέλιξη των ηλεκτρονικών υπολογιστών, με αποτέλεσμα να είναι δυνατή η ακριβής και ποιοτική απεικόνιση σύνθετων τρισδιάστατων σκηνών σε πραγματικό χρόνο, μέσω κατάλληλων αλγορίθμων. Η τρισδιάστατη ανακατασκευή ενός αντικειμένου ή ενός χώρου, από φωτογραφίες ή βίντεο αποτελεί ένα ενδιαφέρον και εντυπωσιακό θέμα με πολλές εφαρμογές και πολύ ενθαρρυντικά αποτελέσματα. Αυτά αποτέλεσαν ουσιαστικά και το έναυσμα για την ενασχόλησή μου με τον τομέα της Υπολογιστικής Όρασης και την επιλογή του θέματος της εργασίας. Οι εφαρμογές που αναπτύσσονται στα πλαίσια της εργασίας παρέχουν οπτικά ευχάριστα αποτελέσματα και έχουν μεγάλη προσαρμοστικότητα και ευελιξία στης διάφορες συνθήκες φωτογράφησης ή λήψης βίντεο. Το σημαντικό, λοιπόν, είναι ότι δεν χρειάζεται απαραίτητα περιβάλλον εργαστηρίου για την λήψη των δεδομένων, δηλαδή των εικόνων. Προκύπτουν καλά αποτελέσματα ακόμα και με εικόνες που λήφθηκαν μέσω μίας απλής φορητής φωτογραφικής κάμερας, χωρίς τρίποδα για στήριξη. Αρκεί απλά να δημιουργήσουμε τις προϋποθέσεις για μικρή κίνηση της κάμερας μεταξύ των λήψεων των εικόνων. Στην παρούσα εργασία παρουσιάζονται και εξετάζονται διεξοδικά όλα τα θέματα που αφορούν την τρισδιάστατη οπτικοποίηση των αντικειμένων. Αρχικά, στις παραγράφους 2.1 έως 3.2, αναλύεται η θεωρία των δύο κυριότερων μεθόδων της "Δομής και Κίνησης" και της "Στερεοσκοπικής Όρασης" . Στην συνέχεια στις παραγράφους 3.3 και 3.4 αναπτύσσεται η μεθοδολογία που ακολουθείται από τις εφαρμογές της Δομής και Κίνησης , ενώ της Στερεοσκοπική Όρασης αναπτύσσεται στην 3.5 . Στην μέθοδο της Δομής και Κίνησης περικλείονται δύο περιπτώσεις. Η πρώτη είναι η μη βαθμονομημένη περίπτωση και η δεύτερη είναι η βαθμονομημένη. Στην δεύτερη, λοιπόν, προηγείται η βαθμονόμηση της κάμερας, οπότε είναι γνωστές εκ των προτέρων οι παράμετροι της κάμερας . Η υλοποίηση των αλγορίθμων γίνεται στο παράρτημα, με την βοήθεια του περιβάλλοντος αριθμητικής υπολογιστικής της προγραμματιστικής γλώσσας Matlab. Τέλος, στο τέταρτο κεφάλαιο, δίνονται κάποια παραδείγματα ανακατασκευών που αποδεικνύουν την αποτελεσματικότητα των αλγορίθμων της υλοποίησης. Τόσο η θεωρία, όσο και οι αλγόριθμοι που παρουσιάζονται στην παρούσα εργασία καλύπτουν πλήρως τις απαραίτητες γνώσεις για την υλοποίηση της τρισδιάστατης αναπαράστασης. Συσσωρεύτηκαν πληροφορίες από δύο μεθόδους, δηλαδή της Δομής και Κίνησης αλλά και της Στερεοσκοπικής Όρασης, οι οποίες συνδυασμένες δίνουν βέλτιστα και αρτιότερα αποτελέσματα. Πρωταρχικός στόχος της εργασίας είναι η ανάδειξη των δυνατοτήτων που παρέχουν οι συγκεκριμένες μέθοδοι. Από την άλλη μεριά, η υλοποίηση των δύο μεθόδων και κατά συνέπεια των αλγόριθμων, αποτελούν μία αρκετά καλή βάση για περαιτέρω ανάπτυξη και προώθηση για μελλοντική έρευνα στον εν λόγω τομέα. Ούτως ή άλλως, τα τελευταία χρόνια, η ερεύνα που αφορά την Υπολογιστική Όραση έχει αποδώσει και έχει δημιουργήσει ικανοποιητικότατα αποτελέσματα. Οπότε στο μέλλον αναμένονται ισχυρότεροι αλγόριθμοι, βελτιώσεις αλλά και πολλές εφαρμογές στους εξελισσόμενους τομείς της ηλεκτρονικής και όχι μόνο. / The purpose of this thesis is the three-dimensional reconstruction of an object or a space, through at least two photos. The theme is part of the field of Computer Vision, which has known great development in the recent years due to the many applications, where the knowledge of the three-dimensional structure of an object or a space is necessary. Of course to this development contributed also the rapid evolution of computers, making possible the accurate and high quality display of complex three-dimensional scenes in real time, through appropriate algorithms. The three-dimensional reconstruction of an object or a space, using photos or video, is an interesting and impressive subject with many applications and very encouraging results. This was basically what intrigued me to involve with the field of Computer Vision and choose the topic of this thesis. The applications in this thesis provide visually pleasant results and have great adaptability and flexibility in various conditions of shooting and making of videos. What is important, therefore, is that a laboratory environment to obtain the data, meaning images, is not necessary. The results are satisfactory even with pictures taken by a simple handheld camera, without the use of a tripod. It’s enough if we just create the proper conditions for a small camera movement between the shots. The present thesis presents and discusses thoroughly all the subjects related with the three-dimensional visualization of objects. First in paragraphs 2.1 to 3.2, is analyzed the theory of the two most important methods, of "Structure and Motion" and of "Stereo Vision". Then in paragraphs 3.3 and 3.4 is discussed the methodology followed by the applications of Structure and Motion , and this of Stereo Vision is discussed in paragraph 3.5. The method of Structure and Motion encloses two cases. The first is the non-calibrated case and the second is the calibrated case. In the calibrated case the calibration of the camera comes first, so the parameters of the camera are known in advance. The implementation of the algorithms is in the Annex, with the help of the numerical computing environment of the programming language Matlab. Finally, in chapter four, are given same examples of reconstructions that demonstrate the effectiveness of the algorithms of implementation. Both the theory and the algorithms presented in this thesis cover fully the necessary knowledge for the materialization of the three-dimensional representation. The information are is accumulated by two methods, this of Structure and Motion and this of Stereo Vision, which combined give the best and most complete results. Primary objective of this thesis is to highlight the possibilities offered by these methods. On the other hand, the implementation of these two methods and thus the algorithms is a good basis for further development and promotion for future research in this field. Anyway, in recent years, the research on Computer Vision has given great results. So in the future are expected stronger algorithms, improvements but also many applications relating with the developing sector of electronics and more.

Syfte – Syftet för den här studien är att utveckla en metod för att mäta diametern på travat timmers ändträytor i en bild med förvridet perspektiv där ytorna befinner sig på olika djup i förhållande till varandra, för att effektivisera mätning inom skogsindustrin. Metod – Denna studie genomfördes i samarbete med Cind AB, och arbetet var uppdelat i två faser med Design Science Research som forskningsmetod. I Fas 1 rektifierades bilder på ändträytorna manuellt och i Fas 2 utnyttjades ett punktmoln för att uppskatta rektifieringsplanet. Detta gjordes i en stereokamerarigg i skala 1:25 på 139 stockar. Samtliga stockar mättes digitalt i de rektifierade bilderna och manuellt med ett digitalt skjutmått. Ett konfidensintervall för differensen beräknades fram för att bedöma mätnoggrannheten. Resultat – Konfidensintervallet för Fas 1 tyder på att metoden har potential då rektifieringsplanet placeras korrekt, vilket Fas 2 visar är en svår och komplex uppgift. Slutsatser – Den utvecklade metodens mätnoggrannhet uppnådde inte studiens mål på 5% felmarginal. Det skulle dock vara möjligt att mäta ändträytor med god noggrannhet om punktmolnet har tillräckligt hög kvalitet. Begränsningar – Mjukvaran som använder punktmolnet för att rektifiera bilderna är en modifierad version av Cinds proprietära produkt. Datamängden som används i studien samlas endast in via Cinds testrigg. / Purpose – The purpose of this study is to develop a method for measuring the diameter of piled logs on a truck in a picture that has skewed perspective and where the end surfaces are at different depths in relation to each other. The intent of this method is to further streamline log measurement in the logging industry. Method – This study was conducted in collaboration with Cind AB, and the work was split in two phases with Design Science Research as research method. In Phase 1, images with log end surfaces were rectified manually, and in Phase 2 a point cloud was used to estimate the rectification plane. This was done with a stereo camera rig in scale 1:25 on a total of 139 logs. All logs were digitally measured in the rectified images and manually measured with a digital caliper. A confidence interval for the difference was calculated to assess the measurement accuracy. Findings – The confidence interval from Phase 1 indicates that the developed method has potential when the rectification plane is placed correctly, which Phase 2 shows is a difficult and complex task. Conclusions – The developed method did not reach the desired measurement accuracy of 5% margin of error, which means that the goal of the study was not achieved. It would be possible to measure the end surfaces of logs with high precision if the point cloud is of a sufficiently high quality. Limitations – The software that utilizes point cloud information to rectify the images is a modified version of Cind’s proprietary product. The dataset that is used in this study is collected solely through Cind’s test rig.

abstract: Using stereo vision for 3D reconstruction and depth estimation has become a popular and promising research area as it has a simple setup with passive cameras and relatively efficient processing procedure. The work in this dissertation focuses on locally adaptive stereo vision methods and applications to different imaging setups and image scenes. Solder ball height and substrate coplanarity inspection is essential to the detection of potential connectivity issues in semi-conductor units. Current ball height and substrate coplanarity inspection tools are expensive and slow, which makes them difficult to use in a real-time manufacturing setting. In this dissertation, an automatic, stereo vision based, in-line ball height and coplanarity inspection method is presented. The proposed method includes an imaging setup together with a computer vision algorithm for reliable, in-line ball height measurement. The imaging setup and calibration, ball height estimation and substrate coplanarity calculation are presented with novel stereo vision methods. The results of the proposed method are evaluated in a measurement capability analysis (MCA) procedure and compared with the ground-truth obtained by an existing laser scanning tool and an existing confocal inspection tool. The proposed system outperforms existing inspection tools in terms of accuracy and stability. In a rectified stereo vision system, stereo matching methods can be categorized into global methods and local methods. Local stereo methods are more suitable for real-time processing purposes with competitive accuracy as compared with global methods. This work proposes a stereo matching method based on sparse locally adaptive cost aggregation. In order to reduce outlier disparity values that correspond to mis-matches, a novel sparse disparity subset selection method is proposed by assigning a significance status to candidate disparity values, and selecting the significant disparity values adaptively. An adaptive guided filtering method using the disparity subset for refined cost aggregation and disparity calculation is demonstrated. The proposed stereo matching algorithm is tested on the Middlebury and the KITTI stereo evaluation benchmark images. A performance analysis of the proposed method in terms of the I0 norm of the disparity subset is presented to demonstrate the achieved efficiency and accuracy. / Dissertation/Thesis / Doctoral Dissertation Electrical Engineering 2017

Introduction : La stimulation électrique directe basse fréquence est pratiquée sur des patients épileptiques pharmaco-résistants implantés avec des électrodes profondes. Elle induit de potentiels évoqués cortico-corticaux (PECC) qui permettent d’estimer la connectivité in vivo et ont permis de caractériser des réseaux locaux. Pour estimer la connectivité à l’échelle du cortex, le projet multicentrique F-TRACT vise à rassembler plusieurs centaines de patients dans une base de données pour proposer un atlas probabiliste de tractographie fonctionnelle.Méthodes : La construction de la base de données à nécessité la mise en place technique de pipelines de traitement semi-automatiques pour faciliter la gestion du nombre important de données de stéréo-électroencéphalographie (SEEG) et d’imagerie. Ces pipelines incluent des nouvelles méthodes de traitement du signal et d’apprentissage automatique, qui ont été développées pour identifier automatiquement les mauvais contacts et corriger l’artefact induit par la stimulation. Les analyses de groupe se sont basées sur des métriques des PECC et des cartes temps-fréquences des réponses à la stimulation.Résultats : La performance des méthodes développées pour le projet a été validée sur des données hétérogènes, en termes de paramètres d’acquisition et de stimulation, provenant de différents centres hospitaliers. L’atlas a été généré à partir d’un échantillon de 173 patients, fournissant une mesure de probabilité de connectivité pour 79% des connexions et d’estimer des propriétés biophysiques des fibres pour 46% d’entre elles. Son application à une sous-population de patients a permis d’étudier les réseaux impliqués dans la génération de symptômes auditifs. L’analyse de groupe oscillatoire a mis en avant l’influence de l’anatomie sur la réponse à la stimulation.Discussion : Cette thèse présente une méthodologie d’étude des PECC à l’échelle du cortex cérébral, utilisant des données hétérogènes en termes d’acquisition, de paramètres de stimulation et spatialement. L’incrémentation du nombre de patients dans l’atlas généré permettra d’étudier les interactions cortico-corticales de manière causale. / Introduction: Low-frequency direct electrical stimulation is performed in drug-resistant epileptic patients, implanted with depth electrodes. It induces cortico-cortical evoked potentials (CCEP) that allow in vivo connectivity mapping of local networks. The multicentric project F-TRACT aims at gathering data of several hundred patients in a database to build a propabilistic functional tractography atlas that estimates connectivity at the cortex level.Methods: Semi-automatic processing pipelines have been developed to handle the amount of stereo-electroencephalography (SEEG) and imaging data and store them in a database. New signal processing and machine-learning methods have been developed and included in the pipelines, in order to automatically identify bad channels and correct the stimulation artifact. Group analyses have been performed using CCEP features and time-frequency maps of the stimulation responses.Results: The new methods performance has been assessed on heterogeneous data, coming from different hospital center recording and stimulating using variable parameters. The atlas was generated from a sample of 173 patients, providing a connectivity probability value for 79% of the possible connections and estimating biophysical properties of fibers for 46% of them. The methodology was applied on patients who experienced auditory symptoms that allowed the identification of different networks involved in hallucination or illusion generation. Oscillatory group analysis showed that anatomy was driving the stimulation response pattern.Discussion: A methodology for CCEP study at the cerebral cortex scale is presented in this thesis. Heterogeneous data in terms of acquisition and stimulation parameters and spatially were used and handled. An increasing number of patients’ data will allow the maximization of the statistical power of the atlas in order to study causal cortico-cortical interactions.

The purpose of this project is to implement, analyze and compare visual odometry approaches to help the localization task in autonomous vehicles. The stereo visual odometry algorithm Libviso2 is compared with a proposed omnidirectional multi-camera approach. The proposed method consists of performing monocular visual odometry on all cameras individually and selecting the best estimate through a voting scheme involving all cameras. The omnidirectionality of the vision system allows the part of the surroundings richest in features to be used in the relative pose estimation. Experiments are carried out using cameras Bumblebee XB3 and Ladybug 2, fixed on the roof of a vehicle. The voting process of the proposed omnidirectional multi-camera method leads to some improvements relatively to the individual monocular estimates. However, stereo visual odometry provides considerably more accurate results. / O objetivo deste mestrado é implementar, analisar e comparar abordagens de odometria visual, de forma a contribuir para a localização de um veículo autônomo. O algoritmo de odometria visual estéreo Libviso2 é comparado com um método proposto, que usa um sistema multi-câmera omnidirecional. De acordo com este método, odometria visual monocular é calculada para cada câmera individualmente e, seguidamente, a melhor estimativa é selecionada através de um processo de votação que involve todas as câmeras. O fato de o sistema de visão ser omnidirecional faz com que a parte dos arredores mais rica em características possa sempre ser usada para estimar a pose relativa do veículo. Nas experiências são utilizadas as câmeras Bumblebee XB3 e Ladybug 2, fixadas no teto de um veículo. O processo de votação do método multi-câmera omnidirecional proposto apresenta melhorias relativamente às estimativas monoculares individuais. No entanto, a odometria visual estéreo fornece resultados mais precisos.

Made available in DSpace on 2014-12-17T14:55:32Z (GMT). No. of bitstreams: 1 MarcosDM_capa_ate_pag07.pdf: 5340923 bytes, checksum: 475069211667569a40c60f5e4bdc1e5a (MD5) Previous issue date: 2006-12-18 / We propose a multi-resolution, coarse-to-fine approach for stereo matching, where the first matching happens at a different depth for each pixel. The proposed technique has the potential of attenuating several problems faced by the constant depth algorithm, making it possible to reduce the number of errors or the number of comparations needed to get equivalent results. Several experiments were performed to demonstrate the method efficiency, including comparison with the traditional plain correlation technique, where the multi-resolution matching with variable depth, proposed here, generated better results with a smaller processing time / Para acelerar o rnatching em sistemas de vis?o est?reo ? proposta uma abordagem multi-resolu??o, coarse-to-fine, variando a profundidade do nivel inicial para cada pixel da imagem. A t?cnica proposta tem o potencial de atenuar diversos problemas do algoritmo com profundidade constante, tornando possivel reduzir o n?mero de erros ou o n?mero de compara??es necess?rias para obter resultados semelhantes. Para demonstrar a efici?ncia do m?todo, foram realizados v?rios experimentos, incluindo compara??o com a t?cnica tradicional de correla??o simples, na qual o rnatching usando imagens em multi-resolu??o com profundidade vari?vel obteve resultados superiores com um menor tempo de processamento

Att filma i 3D är en process som kräver mycket kunskap, tid och teknisk utrustning. För att fullständigt behärska detta fält krävs dessutom omfattande praktisk erfarenhet. Denna erfarenhet kan vara svår att få eftersom den ekonomiska investeringen för att filma i 3D ofta är stor. I denna uppsats visar vi att det är möjligt att konstruera en egen 3D-rigg och att filma med vanliga konsumentkameror för att skapa 3D-film. Uppsatsen visar på de begränsningar och svårigheter man stöter på då man bygger sin egen rigg och diskuterar den ekonomiska besparing man kan göra i jämförelse med kommersiella lösningar. Att bygga en egen rigg är tidskrävande och oftast inte att rekommendera i professionella sammanhang. För indieproduktioner, hobby-fotografer eller om man har väldigt specifika krav som ej uppfylls av tillgängliga kommersiella 3D-riggar kan det dock vara motiverat att konstruera sin egen rigg. Kunskapen som uppsatsen redovisar möjliggör ett resonemang för hur bildkvalitet, funktion och ekonomi kan ställas mot varandra i de avvägningar man ställs inför i konstruktionen av en spegelrigg för att filma i 3D.

En modern grafikprocessor är oerhört kraftfull och har en prestanda som potentiellt sett är många gånger högre än för en modern mikroprocessor. I takt med att grafikprocessorn blivit alltmer programmerbar har det blivit möjligt att använda den för beräkningstunga tillämpningar utanför dess normala användningsområde. Inom det här arbetet utreds vilka möjligheter och begränsningar som uppstår vid användandet av grafikprocessorer för generell programmering. Arbetet inriktas främst mot signal- och bildbehandlingstillämpningar men mycket av principerna är tillämpliga även inom andra områden. Ett ramverk för bildbehandling implementeras och några algoritmer inom bildanalys realiseras och utvärderas, bland annat stereoseende och beräkning av optiskt flöde. Resultaten visar på att vissa tillämpningar kan uppvisa en avsevärd prestandaökning i en grafikprocessor jämfört med i en mikroprocessor men att andra tillämpningar kan vara ineffektiva eller mycket svåra att implementera. / The modern graphical processing unit, GPU, is an extremely powerful unit, potentially many times more powerful than a modern microprocessor. Due to its increasing programmability it has recently become possible to use it in computation intensive applications outside its normal usage. This work investigates the possibilities and limitations of general purpose programming on GPUs. The work mainly concentrates on signal and image processing although much of the principles are applicable to other areas as well. A framework for image processing on GPUs is implemented and a few computer vision algorithms are implemented and evaluated, among them stereo vision and optical flow. The results show that some applications can gain a substantial speedup when implemented correctly in the GPU but others can be inefficent or extremly hard to implement.