Disertační práce se zabývá vybranými partiemi digitální fotogrammetrie. V první části práce je definované téma a popsán současný stav poznání. V následujících kapitolách jsou postupně řešeny čtyři dílčí navzájem navazující cíle. První oblastí je návrh metody pro hledání souhlasných bodů v obraze. Byly navrženy dvě nové metody. První z nich používá konverzi snímků do nepravých barev a druhá využívá pravděpodobností model získaný ze známých párů souhlasných bodů. Druhým tématem je analýza přesnosti výsledné rekonstrukce prostorových bodů. Postupně je analyzován vliv různých faktorů na přesnost rekonstrukce. Stěžejní oblastí je zkoumání vlivu chybného zarovnání kamer a chyby v určení souhlasných bodů. Třetím tématem je tvorba hloubkových map. Byly navrženy dva postupy. První přístup spočívá v kombinaci pasivní a aktivní metody druhý přístup vychází z pasivní metody a využívá spojitosti hloubkové mapy. Poslední zvolenou oblastí zájmu je hodnocení kvality 3D videa. Byly provedeny a statisticky vyhodnoceny subjektvní testy 3D vjemu pro různé zobrazovací systémy v závislosti na úhlu pozorování

La marche occupe un rôle important dans la vie quotidienne. Ce processus apparaît comme facile et naturel pour des gens en bonne santé. Cependant, différentes sortes de maladies (troubles neurologiques, musculaires, orthopédiques...) peuvent perturber le cycle de la marche à tel point que marcher devient fastidieux voire même impossible. Ce projet utilise l'application de Poincaré pour évaluer l'asymétrie de la marche d'un patient à partir d'une carte de profondeur acquise avec un senseur Kinect. Pour valider l'approche, 17 sujets sains ont marché sur un tapis roulant dans des conditions différentes : marche normale et semelle de 5 cm d'épaisseur placée sous l'un des pieds. Les descripteurs de Poincaré sont appliqués de façon à évaluer la variabilité entre un pas et le cycle complet de la marche. Les résultats montrent que la variabilité ainsi obtenue permet de discriminer significativement une marche normale d'une marche avec semelle. Cette méthode, à la fois simple à mettre en oeuvre et suffisamment précise pour détecter une asymétrie de la marche, semble prometteuse pour aider dans le diagnostic clinique. / Gait plays an important part in daily life. This process appears to be very easy and natural for healthy people. However, different kinds of diseases (neurological, muscular, orthopedic...) can impede the gait cycle to such an extent that gait becomes tedious or even infeasible. This project applied Poincare plot analysis to assess the gait asymmetry of a patient from a depth map acquired with a Kinect sensor. To validate the approach, 17 healthy subjects had to walk on a treadmill under different conditions : normal walk and with a 5 cm thick sole under one foot. Poincare descriptors were applied in such a way that they assess the variability between a step and the corresponding complete gait cycle. Results showed that variability significantly discriminates between a normal walk and a walk with a sole. This method seems promising for a clinical use as it is simple to implement and precise enough to assess gait asymmetry.

The objective of this dissertation is to provide a new design approach to a fully automated book reader for individuals with visual impairment and blindness that is portable and cost effective. This approach relies on the geometry of the design setup and provides the mathematical foundation for integrating, in a unique way, a 3-D space surface map from a low-resolution time of flight (ToF) device with a high-resolution image as means to enhance the reading accuracy of warped images due to the page curvature of bound books and other magazines. The merits of this low cost, but effective automated book reader design include: (1) a seamless registration process of the two imaging modalities so that the low resolution (160 x 120 pixels) height map, acquired by an Argos3D-P100 camera, accurately covers the entire book spread as captured by the high resolution image (3072 x 2304 pixels) of a Canon G6 Camera; (2) a mathematical framework for overcoming the difficulties associated with the curvature of open bound books, a process referred to as the dewarping of the book spread images, and (3) image correction performance comparison between uniform and full height map to determine which map provides the highest Optical Character Recognition (OCR) reading accuracy possible. The design concept could also be applied to address the challenging process of book digitization. This method is dependent on the geometry of the book reader setup for acquiring a 3-D map that yields high reading accuracy once appropriately fused with the high-resolution image. The experiments were performed on a dataset consisting of 200 pages with their corresponding computed and co-registered height maps, which are made available to the research community (cate-book3dmaps.fiu.edu). Improvements to the characters reading accuracy, due to the correction steps, were quantified and measured by introducing the corrected images to an OCR engine and tabulating the number of miss-recognized characters. Furthermore, the resilience of the book reader was tested by introducing a rotational misalignment to the book spreads and comparing the OCR accuracy to those obtained with the standard alignment. The standard alignment yielded an average reading accuracy of 95.55% with the uniform height map (i.e., the height values of the central row of the 3-D map are replicated to approximate all other rows), and 96.11% with the full height maps (i.e., each row has its own height values as obtained from the 3D camera). When the rotational misalignments were taken into account, the results obtained produced average accuracies of 90.63% and 94.75% for the same respective height maps, proving added resilience of the full height map method to potential misalignments.

In this thesis, novel approaches for dense depth field estimation and object segmentation from mono, stereo and multiple views are presented. In the first stage, a novel graph-theoretic color segmentation algorithm is proposed, in which the popular Normalized Cuts 59H[6] segmentation algorithm is improved with some modifications on its graph structure. Segmentation is obtained by the recursive partitioning of the weighted graph. The simulation results for the comparison of the proposed segmentation scheme with some well-known segmentation methods, such as Recursive Shortest Spanning Tree 60H[3] and Mean-Shift 61H[4] and the conventional Normalized Cuts, show clear improvements over these traditional methods. The proposed region-based approach is also utilized during the dense depth map estimation step, based on a novel modified plane- and angle-sweeping strategy. In the proposed dense depth estimation technique, the whole scene is assumed to be region-wise planar and 3D models of these plane patches are estimated by a greedy-search algorithm that also considers visibility constraint. In order to refine the depth maps and relax the planarity assumption of the scene, at the final step, two refinement techniques that are based on region splitting and pixel-based optimization via Belief Propagation 62H[32] are also applied. Finally, the image segmentation algorithm is extended to object segmentation in multi-view video with the additional depth and optical flow information. Optical flow estimation is obtained via two different methods, KLT tracker and region-based block matching and the comparisons between these methods are performed. The experimental results indicate an improvement for the segmentation performance by the usage of depth and motion information.

Three dimensional television (3DTV) is believed to be the future of television broadcasting that will replace current 2D HDTV technology. In the future, 3DTV will bring a more life-like and visually immersive home entertainment experience, in which users will have the freedom to navigate through the scene to choose a different viewpoint. A desired view can be synthesized at the receiver side using depth image-based rendering (DIBR). While this approach has many advantages, one of the key challenges in DIBR is generating high quality synthesized views. This work presents novel methods to measure and enhance the quality of 3D videos generated through DIBR. For quality measurements we describe a novel method to characterize and measure distortions by multiple cameras used to capture stereoscopic images. In addition, we present an objective quality measure for DIBR-based 3D videos by evaluating the elements of visual discomfort in stereoscopic 3D videos. We also introduce a new concept called the ideal depth estimate, and define the tools to estimate that depth. Full-reference and no-reference profiles for calculating the proposed measures are also presented. Moreover, we introduce two innovative approaches to improve the quality of the synthesized views generated by DIBR. The first approach is based on hierarchical blending of the background and foreground information around the disocclusion areas which produces a natural looking, synthesized view with seamless hole-filling. This approach yields virtual images that are free of any geometric distortions, unlike other algorithms that preprocess the depth map. In contrast to the other hole-filling approaches, our approach is not sensitive to depth maps with high percentage of bad pixels from stereo matching. The second approach further enhances the results through a depth-adaptive preprocessing of the colored images. Finally, we propose an enhancement over depth estimation algorithm using the depth monocular cues from luminance and chrominance. The estimated depth will be evaluated using our quality measure, and the hole-filling algorithm will be used to generate synthesized views. This application will demonstrate how our quality measures and enhancement algorithms could help in the development of high quality stereoscopic depth-based synthesized videos.

In this thesis, we would like to present a new way to enhance the “depth map” image which is called as the fusion of depth images. The goal of our thesis is to try to enhance the “depth images” through a fusion of different classification methods. For that, we will use three similar but different methodologies, the Graph-Cut, Super-Pixel and Principal Component Analysis algorithms to solve the enhancement and output of our result. After that, we will compare the effect of the enhancement of our result with the original depth images. This result indicates the effectiveness of our methodology. / Room 401, No.56, Lane 21, Yin Gao Road, Shanghai, China

[pt] Modelagem e renderização baseadas em imagem tem sido uma área de pesquisa muito ativa nas últimas décadas, tendo recebido grande atenção como uma alternativa às técnicas tradicionais de síntese de imagens baseadas primariamente em geometria. Nesta área, algoritmos de visão computacional são usados para processar e interpretar fotos ou vídeos do mundo real a fim de construir um modelo representativo de uma cena, ao passo que técnicas de computação gráfica são usadas para tomar proveito desta representação e criar cenas foto-realistas. O propósito deste trabalho é investigar técnicas de renderização capazes de gerar vistas virtuais de alta qualidade de uma cena, em tempo real. Para garantir a performance interativa do algoritmo, além de aplicar otimizações a métodos de renderização existentes, fazemos uso intenso da GPU para o processamento de geometria e das imagens para gerar as imagens finais. Apesar do foco deste trabalho ser a renderização, sem reconstruir o mapa de profundidade a partir das fotos, ele implicitamente contorna possíveis problemas na estimativa da profundidade para que as cenas virtuais geradas apresentem um nível aceitável de realismo. Testes com dados públicos são apresentados para validar o método proposto e para ilustrar deficiências dos métodos de renderização baseados em imagem em geral. / [en] Image-based modeling and rendering has been a very active research topic as a powerful alternative to traditional geometry-based techniques for image synthesis. In this area, computer vision algorithms are used to process and interpret real-world photos or videos in order to build a model of a scene, while computer graphics techniques use this model to create photorealistic images based on the captured photographs or videos. The purpose of this work is to investigate rendering techniques capable of delivering visually accurate virtual views of a scene in real-time. Even though this work is mainly focused on the rendering task, without the reconstruction of the depth map, it implicitly overcomes common errors in depth estimation, yielding virtual views with an acceptable level of realism. Tests with publicly available datasets are also presented to validate our framework and to illustrate some limitations in the IBR general approach.

Abstract Three-dimensional scene reconstruction has been an important area of research for many decades. It has a myriad of applications ranging from entertainment to medicine. This thesis explores the 3D reconstruction pipeline and proposes novel methods to improve many of the steps necessary to achieve a high quality reconstruction. It proposes novel methods in the areas of depth sensor calibration, simultaneous localization and mapping, depth map inpainting, point cloud simplification, and free-viewpoint rendering. Geometric camera calibration is necessary in every 3D reconstruction pipeline. This thesis focuses on the calibration of depth sensors. It presents a review of sensors models and how they can be calibrated. It then examines the case of the well-known Kinect sensor and proposes a novel calibration method using only planar targets. Reconstructing a scene using only color cameras entails di_erent challenges than when using depth sensors. Moreover, online applications require real-time response and must update the model as new frames are received. The thesis looks at these challenges and presents a novel simultaneous localization and mapping system using only color cameras. It adaptively triangulates points based on the detected baseline while still utilizing non-triangulated features for pose estimation. The thesis addresses the extrapolating missing information in depth maps. It presents three novel methods for depth map inpainting. The first utilizes random sampling to fit planes in the missing regions. The second method utilizes a 2nd-order prior aligned with intensity edges. The third method learns natural filters to apply a Markov random field on a joint intensity and depth prior. This thesis also looks at the issue of reducing the quantity of 3D information to a manageable size. It looks at how to merge depth maps from multiple views without storing redundant information. It presents a method to discard this redundant information while still maintaining the naturally variable resolution. Finally, transparency estimation is examined in the context of free-viewpoint rendering. A procedure to estimate transparency maps for the foreground layers of a multi-view scene is presented. The results obtained reinforce the need for a high accuracy 3D reconstruction pipeline including all the previously presented steps. / Tiivistelmä Kolmiuloitteisen ympäristöä kuvaavan mallin rakentaminen on ollut tärkeä tutkimuksen kohde jo usean vuosikymmenen ajan. Sen sovelluskohteet ulottuvat aina lääketieteestä viihdeteollisuuteen. Väitöskirja tarkastelee 3D ympäristöä kuvaavan mallin tuottamisprosessia ja esittää uusia keinoja parantaa korkealaatuisen rekonstruktion tuottamiseen vaadittavia vaiheita. Työssä esitetään uusia menetelmiä etäisyyssensoreiden kalibrointiin, samanaikaisesti tapahtuvaan paikannukseen ja kartoitukseen, syvyyskartan korjaamiseen, etäisyyspistepilven yksinkertaistamiseen ja vapaan katselukulman kuvantamiseen. Väitöskirjan ensi osa keskittyy etäisyyssensoreiden kalibrointiin. Työ esittelee erilaisia sensorimalleja ja niiden kalibrointia. Yleisen tarkastelun lisäksi keskitytään hyvin tunnetun Kinect-sensorin käyttämiseen, ja ehdotetaan uutta kalibrointitapaa pelkkiä tasokohteita hyväksikäyttäen. Pelkkien värikameroiden käyttäminen näkymän rekonstruointiin tuottaa erilaisia haasteita verrattuna etäisyyssensoreiden käyttöön kuvan muodostamisessa. Lisäksi verkkosovellukset vaativat reaaliaikaista vastetta. Väitös tarkastelee kyseisiä haasteita ja esittää uudenlaisen yhtäaikaisen paikannuksen ja kartoituksen mallin tuottamista pelkkiä värikameroita käyttämällä. Esitetty tapa kolmiomittaa adaptiivisesti pisteitä taustan pohjalta samalla kun hyödynnetään eikolmiomitattuja piirteitä asentotietoihin. Työssä esitellään kolme uudenlaista tapaa syvyyskartan korjaamiseen. Ensimmäinen tapa käyttää satunnaispisteitä tasojen kohdentamiseen puuttuvilla alueilla. Toinen tapa käyttää 2nd-order prior kohdistusta ja intensiteettireunoja. Kolmas tapa oppii filttereitä joita se soveltaa Markov satunnaiskenttiin yhteisillä tiheys ja syvyys ennakoinneilla. Tämä väitös selvittää myös mahdollisuuksia 3D-information määrän pienentämiseen käsiteltävälle tasolle. Työssä selvitetään, kuinka syvyyskarttoja voidaan yhdistää ilman päällekkäisen informaation tallentamista. Työssä esitetään tapa jolla päällekkäisestä datasta voidaan luopua kuitenkin säilyttäen luonnollisesti muuttuva resoluutio. Viimeksi, tutkimuksessa on esitetty läpinäkyvyyskarttojen arviointiproseduuri etualan kerroksien monikatselukulmanäkymissä vapaan katselukulman renderöinnin näkökulmasta. Saadut tulokset vahvistavat tarkan 3D-näkymän rakentamisliukuhihnan tarvetta sisältäen kaikki edellä mainitut vaiheet.

Abstract This work addresses the problems related to three-dimensional modeling of scenes and objects and model evaluation. The work is divided into four main parts. At first, the work concentrates on purely image-based reconstruction while the second part presents a modeling pipeline based on an active depth sensor. Then, the work introduces methods for producing surface meshes from point clouds, and finally, a novel approach for model evaluation is presented. In the first part, this work proposes a multi-view stereo (MVS) reconstruction method that takes a set of images as an input and outputs a model represented as a point cloud. The method is based on match propagation, where a set of initial corresponding points between images is expanded iteratively into larger regions by searching new correspondences in the spatial neighborhood of the existing ones. The expansion is implemented using a best-first strategy, where the most reliable match is always expanded first. The method produces comparable results with the state-of-the-art but significantly faster. In the second part, this work presents a method that merges a sequence of depth maps into a single non-redundant point cloud. In the areas, where the depth maps overlap, the method fuses points together by giving more weight to points which seem to be more reliable. The method overcomes its predecessor both in accuracy and robustness. In addition, this part introduces a method for depth camera calibration. The method develops on an existing calibration approach which was originally designed for the first generation Microsoft Kinect device. The third part of the thesis addresses the problem of converting the point clouds to surface meshes. The work briefly reviews two well-known approaches and compares their ability to produce sparse mesh models without sacrificing accuracy. Finally, the fourth part of this work describes the development of a novel approach for performance evaluation of reconstruction algorithms. In addition to the accuracy and completeness, which are the metrics commonly used in existing evaluation benchmarks, the method also takes the compactness of the models into account. The metric enables the evaluation of the accuracy-compactness trade-off of the models. / Tiivistelmä Tässä työssä käsitellään näkymän tai esineen kolmiulotteista mallintamista ja tulosten laadun arviointia. Työ on jaettu neljään osaan. Ensiksi keskitytään pelkästään valokuvia hyödyntävään mallinnukseen ja sitten esitellään menetelmä syvyyskamerapohjaiseen mallinnukseen. Kolmas osa kuvaa menetelmiä verkkomallien luomiseen pistepilvestä ja lopuksi esitellään menetelmä mallien laadun arviointiin. Ensimmäisessä osassa esitellään usean kuvan stereoon perustuva mallinnusmenetelmä, joka saa syötteenä joukon valokuvia ja tuottaa kuvissa näkyvästä kohteesta pistepilvimallin. Menetelmä perustuu vastinpisteiden laajennukseen, jossa kuvien välisiä pistevastaavuuksia laajennetaan iteratiivisesti suuremmiksi vastinalueiksi hakemalla uusia vastinpistepareja jo löydettyjen läheisyydestä. Laajennus käyttää paras ensin -menetelmää, jossa luotettavin pistevastaavuus laajennetaan aina ensin. Menetelmä tuottaa vertailukelpoisia tuloksia johtaviin menetelmiin verrattuna, mutta merkittävästi nopeammin. Toisessa osassa esitellään menetelmä, joka yhdistää joukon syvyyskameralla kaapattuja syvyyskarttoja yhdeksi pistepilveksi. Alueilla, jotka sisältävät syvyysmittauksia useasta syvyyskartasta, päällekkäiset mittaukset yhdistetään painottamalla luotettavammalta vaikuttavaa mittausta. Menetelmä on tarkempi kuin edeltäjänsä ja toimii paremmin kohinaisemmalla datalla. Lisäksi tässä osassa esitellään menetelmä syvyyskameran kalibrointiin. Menetelmä kehittää jo olemassa olevaa kalibrointityökalua, joka alun perin kehitettiin ensimmäisen sukupolven Microsoft Kinect laitteelle. Väitöskirjan kolmas osa käsittelee pintamallin luomista pistepilvestä. Työ esittelee kaksi hyvin tunnettua menetelmää ja vertailee niiden kykyä luoda harvoja, mutta edelleen tarkkoja malleja. Lopuksi esitellään uudenlainen menetelmä mallinnusmenetelmien arviointiin. Tarkkuuden ja kattavuuden lisäksi, jotka ovat yleisimmät arvioinnissa käytetyt metriikat, menetelmä ottaa huomioon myös mallin pistetiheyden. Metriikan avulla on mahdollista arvioida kompromissia mallin tarkkuuden ja tiheyden välillä.

Stereo vision is one of the most popular elements in the field of mobile robots and significantly contributes to their autonomous behaviour. The aim of the diploma thesis was to design and implement a camera module as a hardware sensor input, which is independent, with the possibility of supplementing the system with other cameras, and to create a depth map from a pair of cameras. The diploma thesis consists of theoretical and practical part, including the conclusion of results. The theoretical part introduces the ROS framework, discusses methods of creating depth maps, and provides an overview of the most popular stereo cameras in robotics. The practical part describes in detail the preparation of the experiment and its implementation. It also describes the camera calibration and the depth map creating. The last chapter contains an evaluation of the experiment.