Etude bibliographique sur le recalage d'images de visage et sur le recalage d'images et travail en collaboration avec Son VuS, pour définir la précision nécessaire du recalage en fonction des exigences des méthodes de reconnaissance de visages. / Face alignment is an important step in a typical automatic face recognition system.This thesis addresses the alignment of faces for face recognition applicationin video surveillance context. The main challenging factors of this research includethe low quality of images (e.g., low resolution, motion blur, and noise), uncontrolledillumination conditions, pose variations, expression changes, and occlusions. In orderto deal with these problems, we propose several face alignment methods using differentstrategies. The _rst part of our work is a three-stage method for facial pointlocalization which can be used for correcting mis-alignment errors. While existingalgorithms mostly rely on a priori knowledge of facial structure and on a trainingphase, our approach works in an online mode without requirements of pre-de_nedconstraints on feature distributions. The proposed method works well on images underexpression and lighting variations. The key contributions of this thesis are aboutjoint image alignment algorithms where a set of images is simultaneously alignedwithout a biased template selection. We respectively propose two unsupervised jointalignment algorithms : \Lucas-Kanade entropy congealing" (LKC) and \gradient correlationcongealing" (GCC). In LKC, an image ensemble is aligned by minimizing asum-of-entropy function de_ned over all images. GCC uses gradient correlation coef-_cient as similarity measure. The proposed algorithms perform well on images underdi_erent conditions. To further improve the robustness to mis-alignments and thecomputational speed, we apply a multi-resolution framework to joint face alignmentalgorithms. Moreover, our work is not limited in the face alignment stage. Since facealignment and face acquisition are interrelated, we develop an adaptive appearanceface tracking method with alignment feedbacks. This closed-loop framework showsits robustness to large variations in target's state, and it signi_cantly decreases themis-alignment errors in tracked faces.

<div> Planar homography estimation is foundational to many computer vision problems, such as Simultaneous Localization and Mapping (SLAM) and Augmented Reality (AR). However, conditions of high variance confound even the state-of-the-art algorithms. In this report, we analyze the performance of two recently published methods using Convolutional Neural Networks (CNNs) that are meant to replace the more traditional feature-matching based approaches to the estimation of homography. Our evaluation of the CNN based methods focuses particularly on measuring the performance under conditions of significant noise, illumination shift, and occlusion. We also measure the benefits of training CNNs to varying degrees of noise. Additionally, we compare the effect of using color images instead of grayscale images for inputs to CNNs. Finally, we compare the results against baseline feature-matching based homography estimation methods using SIFT, SURF, and ORB. We find that CNNs can be trained to be more robust against noise, but at a small cost to accuracy in the noiseless case. Additionally, CNNs perform significantly better in conditions of extreme variance than their feature-matching based counterparts. With regard to color inputs, we conclude that with no change in the CNN architecture to take advantage of the additional information in the color planes, the difference in performance using color inputs or grayscale inputs is negligible. About the CNNs trained with noise-corrupted inputs, we show that training a CNN to a specific magnitude of noise leads to a ``Goldilocks Zone'' with regard to the noise levels where that CNN performs best.</div>

This thesis investigates the problem of detecting and tracking sticky notes on Kanban boards using classical computer vision techniques. Currently, there exists some alternatives for digitizing sticky notes, but none keep track of notes that have already been digitized, allowing for duplicate notes to be created when scanning multiple images of the same Kanban board. Kanban boards are widely used in various industries, and being able to recognize, and possibly in the future even digitize entire Kanban boards could provide users with extended functionality. The implementation presented in this thesis is able to, given two images, detect the Kanban boards in each image and rectify them. The rectified images are then sent to the Google Cloud Vision API for text detection. Then, the rectified images are used to detect all the sticky notes. The positional information of the notes and columns of the Kanban boards are then used to filter the text detection to find the text inside each note as well as the header text for each column. Between the two images, the columns are compared and matched, as well as notes of the same color. If columns or notes in one image do not have a match in the second image, it is concluded that the boards are different, and the user is informed of why. If all columns and notes in one image have matches in the second image but some notes have moved, the user is informed of which notes that have moved, and how they have moved as well. The different experiments conducted in this thesis on the implementation show that it works well, but it is very confined to strict requirements, making it unsuitable for commercial use. The biggest problem to solve is to make the implementation more general, i.e. the Kanban board layout, sticky note shapes and colors as well as their actual content. / Denna avhandling undersöker problemet med att upptäcka och spåra klisterlappar och Kanban-tavlor med hjälp av klassiska datorseendetekniker. För närvarande finns det några alternativ för att digitalisera klisterlappar, men ingen håller reda på anteckningar som redan har digitaliserats, vilket gör att duplicerade anteckningar kan skapas när du skannar flera bilder av samma Kanban-kort. Kanban-kort används flitigt i olika branscher och att kunna känna igen, och eventuellt i framtiden även digitalisera hela Kanban-tavlor, skulle kunna ge användarna utökad funktionalitet. Implementeringen som presenteras i denna avhandling kan, givet två bilder, upptäcka Kanban-brädorna i varje bild och korrigera dem. De korrigerade bilderna skickas sedan till Google Cloud Vision API för textidentifiering. Sedan används de korrigerade bilderna för att upptäcka alla klisterlappar. Positionsinformationen för anteckningarna och kolumnerna på Kanban-tavlan används sedan för att filtrera textdetekteringen för att hitta texten i varje anteckning såväl som rubriktexten för varje kolumn. Mellan de två bilderna jämförs och matchas kolumnerna, samt anteckningar av samma färg. Om kolumner eller anteckningar i en bild inte har en matchning i den andra bilden dras slutsatsen att brädorna är olika och användaren informeras om varför. Om alla kolumner och anteckningar i en bild har matchningar i den andra bilden men några anteckningar har flyttats, informeras användaren om vilka anteckningar som har flyttats och hur de har flyttats. De olika experiment som genomförs i denna avhandling om implementering visar att den fungerar bra, men den är mycket begränsad till strikta krav, vilket gör den olämplig för kommersiellt bruk. Det största problemet att lösa är att göra implementeringen mer generell, d.v.s. Kanban-tavlans layout, klisterlapparnas former och färger samt deras faktiska innehåll.

Microscopic video images of microcirculation have been used in clinical diagnosis for years, and theparameters obtained from images reveal most physiological activities and body organizations.Particularly, the blood flow speed is one of important indexes, which reflects the state ofmicrocirculation and make significant marks in diagnosis.In order to measure capillary blood velocity, a quantity of methods and instruments have beenstudied and developed. Based on the format of measurement, microscopy approaches used widely,can be grouped into two categories. One direct way applies microscopic-imaging technology forvisualization. The other way uses assistant methods such as laser-illumination [1] or labeling RBCswith fluorescein isothiocyanate [2]. In previous study, four methods (Direct Observation Method,Dual-windows Method, Single-window Method, Optical Flow Method) have been studied andanalysed in order to achieve better performance. But still there is a non-negligible deviation inmeasurement within different tries and compared to the data we retrieve from hospital.This study, inspired by previous work, aims to further investigate efficient and reliable algorithms forextracting capillary blood velocity. One possible solution is to implement feature based estimation tocalculate the blood flow speed distribution automatically, point by point along the middle line oftargeting blood vessel. We inherit the idea of generating motion vectors from Optic Flow algorithmwhich has the best accuracy performance in vehicle identification domain. But original optic flowalgorithm makes the system too sophisticated and time consuming. Moreover, its two required basicrules may not stand during the blood flow velocity detection. So a customized feature basedestimation is brought up here and supposed to be a practicable method for analysis not only inaccuracy but also in efficiency. Moreover, this report also introduces picture shifting, red blood cellmotion, and double windows marking to compare and to confirm the results. Previous work will beused as a reference for the assessment of new algorithms. / Mikroskopiska videobilder av mikrosirkulation har använts vid klinisk diagnos i flera år, och parametrarna erhållna från bilder avslöjar de flesta fysiologiska aktiviteter och kroppsorganisationer. Särskilt är blodflödeshastigheten ett av viktiga index, som återspeglar tillståndet för mikrosirkulation och gör betydande märken vid diagnosen.För att mäta kapillärblodshastighet har en mängd metoder och instrument studerats och utvecklats. Baserat på mätformatet kan mikroskopimetoder som används allmänt grupperas i två kategorier. Ett direkt sätt använder mikroskopisk bildteknologi för visualisering. Det andra sättet använder assistentmetoder som laserbelysning [1] eller märkning av RBC med fluoresceinisotiocyanat [2]. I tidigare studier har fyra metoder (Direct Observation Method, Dual-windows Method, Single-Window Method, Optical Flow Method) studerats och analyserats för att uppnå bättre prestanda. Men det finns fortfarande en icke försumbar avvikelse i mätningen inom olika försök och jämfört med de data vi hämtar från sjukhuset.Denna studie, inspirerad av tidigare arbete, syftar till att ytterligare undersöka effektiva och tillförlitliga algoritmer för att extrahera kapillärblodhastighet. En möjlig lösning är att implementera funktionsbaserad uppskattning för att beräkna blodflödeshastighetsfördelningen automatiskt, punkt för punkt längs mittlinjen för riktad blodkärl. Vi ärver idén att generera rörelsesvektorer från Optic Flow-algoritmen som har den bästa noggrannhetsprestanda inom fordonsidentifieringsdomän. Men den ursprungliga optiska flödesalgoritmen gör systemet för sofistikerat och tidskrävande. Dessutom kanske dess två nödvändiga grundregler inte gäller under detektionen av blodflödeshastighet. Så en anpassad funktionsbaserad uppskattning tas upp här och antas vara en genomförbar metod för analys inte bara i noggrannhet utan också i effektivitet. Dessutom introducerar detta papper också bildförskjutning, rörelse av röda blodkroppar och dubbla fönstermarkeringar för att jämföra och bekräfta resultaten. Tidigare arbete kommer att användas som referens förbedömning av nya algoritmer.

<p dir="ltr">Several industrial and commercial bulk material management applications rely on accurate, current stockpile volume estimation. Proximal imaging and LiDAR sensing modalities can be used to derive stockpile volume estimates in outdoor and indoor storage facilities. Among available imaging and LiDAR sensing modalities, the latter is more advantageous for indoor storage facilities due to its ability to capture scans under poor lighting conditions. Evaluating volumes from such sensing modalities requires the pose (i.e., position and orientation) parameters of the used sensors relative to a common reference frame. For outdoor facilities, a Global Navigation Satellite System (GNSS) combined with an Inertial Navigation System (INS) can be used to derive the sensors’ pose relative to a global reference frame. For indoor facilities, GNSS signal outages will not allow for such capability. Prior research has developed strategies for establishing the sensor position and orientation for stockpile volume estimation while relying on multi-beam spinning LiDAR units. These approaches are feasible due to the large range and Field of View (FOV) of such systems that can capture the internal surfaces of barn and dome storage facilities.</p><p dir="ltr">The mechanical movement of multi-beam spinning LiDAR units together with the harsh conditions within indoor facilities (e.g., excessive humidity, dust, and corrosive environment in deicing salt storage facilities) limit the use of such systems. With the increasing availability of solid-state LiDAR units, there is an interest in exploring their potential for stockpile volume estimation. In spite of their higher robustness to harsh conditions, solid-state LiDAR units have shorter distance measurement range and limited FOV when compared with multi-beam spinning LiDAR. This research presents a strategy for the extrinsic calibration (i.e., estimating the relative pose parameters) of installed solid-state LiDAR units inside stockpile storage facilities. The extrinsic calibration is made possible using deployed spherical targets and a complete, reference scan of the facility from another LiDAR sensing modality. The proposed research introduces strategies for: 1) automated extraction of the spherical targets; 2) automated matching of these targets in the solid-state LiDAR and reference scans using invariant relationships among them; and 3) coarse-to-fine estimation of the calibration parameters. Experimental results in several facilities have shown the feasibility of using the proposed methodology to conduct the extrinsic calibration and volume evaluation with an error percentage less than 3.5% even with occlusion percentages reaching up to 50%.</p>

Tato práce popisuje problematiku návrhu a vývoje aplikace pro rekonstrukci 3D modelů z 2D obrazových dat, označované jako bundle adjustment. Práce analyzuje proces 3D rekonstrukce a důkladně popisuje jednotlivé kroky. Prvním z kroků je automatizované získání obrazové sady z internetu. Je představena sada skriptů pro hromadné stahování obrázků ze služeb Flickr a Google Images a shrnuty požadavky na tyto obrázky pro co nejlepší 3D rekonstrukci. Práce dále popisuje různé detektory, extraktory a párovací algoritmy klíčových bodů v obraze s cílem najít nejvhodnější kombinaci pro rekonstrukci budov. Poté je vysvětlen proces rekonstrukce 3D struktury, její optimalizace a jak je tato problematika realizovaná v našem programu. Závěr práce testuje výsledky získané z implementovaného programu pro několik různých datových sad a porovnává je s výsledky ostatních podobných programů, představených v úvodu práce.

We formulate Local Shape Descriptor selection for model-based object recognition in range data as an optimization problem and offer a platform that facilitates a solution. The goal of object recognition is to identify and localize objects of interest in an image. Recognition is often performed in three phases: point matching, where correspondences are established between points on the 3-D surfaces of the models and the range image; hypothesis generation, where rough alignments are found between the image and the visible models; and pose refinement, where the accuracy of the initial alignments is improved. The overall efficiency and reliability of a recognition system is highly influenced by the effectiveness of the point matching phase. Local Shape Descriptors are used for establishing point correspondences by way of encapsulating local shape, such that similarity between two descriptors indicates geometric similarity between their respective neighbourhoods. We present a generalized platform for constructing local shape descriptors that subsumes a large class of existing methods and allows for tuning descriptors to the geometry of specific models and to sensor characteristics. Our descriptors, termed as Variable-Dimensional Local Shape Descriptors, are constructed as multivariate observations of several local properties and are represented as histograms. The optimal set of properties, which maximizes the performance of a recognition system, depend on the geometry of the objects of interest and the noise characteristics of range image acquisition devices and is selected through pre-processing the models and sample training images. Experimental analysis confirms the superiority of optimized descriptors over generic ones in recognition tasks in LIDAR and dense stereo range images. / Thesis (Ph.D, Electrical & Computer Engineering) -- Queen's University, 2009-09-01 11:07:32.084