Kasmet daugybė žmonių būna sužalojami autoįvykiuose, iš kurių dalis sužalojimų būna rimti arba pasibaigia mirtimi. Dedama vis daugiau pastangų kuriant įvairias sistemas, kurios padėtų mažinti nelaimių skaičių kelyje. Tokios sistemos gebėtų perspėti vairuotojus apie galimus pavojus, atpažindamos eismo dalyvius ir sekdamos jų padėtį kelyje. Eismo dalyvių kelyje atpažinimas iš vaizdo yra pakankamai sudėtinga, daug skaičiavimų reikalaujanti problema. Šiame darbe šiai problemai spręsti pasitelkti stereo vaizdai, nesugretinamumo žemėlapis bei konvoliuciniai neuroniniai tinklai. Konvoliuciniai neuroniniai tinklai reikalauja daug skaičiavimų, todėl jie optimizuoti pasitelkus grafikos procesorių ir OpenCL. Gautas iki 33,4% spartos pagerėjimas lyginant su centriniu procesoriumi. Stereo vaizdai ir nesugretinamumo žemėlapis leidžia atmesti didelius kadro regionus, kurių nereikia klasifikuoti su konvoliuciniu neuroniniu tinklu. Priklausomai nuo scenos vaizde, reikalingų klasifikavimo operacijų skaičius sumažėja vidutiniškai apie 70-95% ir tai leidžia kadrą apdoroti atitinkamai greičiau. / Many people are injured during auto accidents each year, some injures are serious or end in death. Many efforts are being put in developing various systems, which could help to reduce accidents on the road. Such systems could warn drivers of a potential danger, while recognizing on-road vehicles and tracking their position on the road. On-road vehicle recognition on image is a complex and computationally very intensive problem. In this paper, to solve this problem, stereo images, disparity map and convolutional neural networks are used. Convolutional neural networks are very computational intensive, so to optimize it GPU and OpenCL are used. 33.4% speed improvement was achieved compared to the central processor. Stereo images and disparity map allows to discard large areas of the image, which are not needed to be classified using convolutional neural networks. Depending on the scene of the image, the number of the required classification operations decreases on average by 70-95% and this allows to process the image accordingly faster.

Comprendre, analyser et modéliser l'environment 3D à partir d'images provenant de caméras et d'appareils photos est l'un des défis majeurs actuel de recherche en vision par ordinateur. Cette thèse s'interesse à plusieurs aspects géométriques et photometriques liés à la reconstruction de surface à partir de plusieurs caméras calibrées. La reconstruction 3D est vue comme un problème de rendu inverse, et vise à minimiser une fonctionnelle d'énergie afin d'optimiser un maillage triangulaire représentant la surface à reconstruire. L'énergie est définie via un modèle génératif faisant naturellement apparaître des attributs tels que la visibilité ou la photométrie. Ainsi, l'approche présentée peut indifférement s'adapter à divers cas d'application tels que la stéréovision multi-vues, la stéréo photométrique multi-vues ou encore le “shape from shading” multi-vues. Plusieurs approches sont proposées afin de résoudre les problèmes de correspondances de l'apparence pour des scènes non Lambertiennes, dont l'apparence varie en fonction du point de vue. La segmentation, la stéréo photométrique ou encore la réciprocité d'Helmholtz sont des éléments étudiés afin de contraindre la reconstruction. L'exploitation de ces contraintes dans le cadre de reconstruction multi-vues permet de reconstruire des modèles complets 3D avec une meilleure qualité. / Understanding, analyzing and modeling the 3D world from 2D pictures and videos is probably one of the most exciting and challenging problem of computer vision. In this thesis, we address several geometric and photometric aspects to 3D surface reconstruction from multi-view calibrated images. We first formulate multi-view shape reconstruction as an inverse rendering problem. Using generative models, we formulate the problem as an energy minimization method that leads to the non-linear surface optimization of a deformable mesh. A particular attention is addressed to the computation of the discrete gradient flow, which leads to coherent vertices displacements. We particularly focus on models and energy functionals that depend on visibility and photometry. The same framework can then be equally used to perform multi-view stereo, multi-view shape from shading or multi-view photometric stereo. Then, we propose to exploit different additional information to constraint the problem in the non-Lambertian case, where the appearance of the scene depends on the view-point direction. Segmentation for instance can be used to segment surface regions sharing similar appearance or reflectance. Helmholtz reciprocity can also be applied to reconstruct 3D shapes of objects of any arbitrary reflectance properties. By taking multiple image-light pairs around an object, multi-view Helmholtz stereo can be performed. Using this constrained acquisition scenario and our deformable mesh framework, it is possible to reconstruct high quality 3D models.

<p>Many different approaches have been taken towards solving the stereo correspondence problem and great progress has been made within the field during the last decade. This is mainly thanks to newly evolved global optimization techniques and better ways to compute pixel dissimilarity between views. The most successful algorithms are based on approaches that explicitly model smoothness assumptions made about the physical world, with image segmentation and plane fitting being two frequently used techniques.</p><p>Within the project, a survey of state of the art stereo algorithms was conducted and the theory behind them is explained. Techniques found interesting were implemented for experimental trials and an algorithm aiming to achieve state of the art performance was implemented and evaluated. For several cases, state of the art performance was reached.</p><p>To keep down the computational complexity, an algorithm relying on local winner-take-all optimization, image segmentation and plane fitting was compared against minimizing a global energy function formulated on pixel level. Experiments show that the local approach in several cases can match the global approach, but that problems sometimes arise – especially when large areas that lack texture are present. Such problematic areas are better handled by the explicit modeling of smoothness in global energy minimization.</p><p>Lastly, disparity estimation for image sequences was explored and some ideas on how to use temporal information were implemented and tried. The ideas mainly relied on motion detection to determine parts that are static in a sequence of frames. Stereo correspondence for sequences is a rather new research field, and there is still a lot of work to be made.</p>

Estimation of depth within an imaged scene can be formulated as a stereo correspondence problem. Software solutions tend to be too slow for high frame rate (i.e. > 30 fps) performance. Hardware solutions can result in marked improvements. This thesis explores one such hardware implementation that generates dense binocular disparity estimates at frame rates of over 200 fps using a dynamic programming formulation (DPML) developed by Cox et. al. A highly parameterizable field programmable gate array implementation of this architecture demonstrates equivalent accuracy while executing at significantly higher frame rates to those of current approaches. Existing hardware implementations for dense disparity estimation often use sum of squared difference, sum of absolute difference or other similar algorithms that typically perform poorly in comparison to DPML. The presented system runs at 248 fps for a resolution of 320 x 240 pixels and disparity range of 128 pixels, a performance of 2.477 billion DPS.

Estimation of depth within an imaged scene can be formulated as a stereo correspondence problem. Software solutions tend to be too slow for high frame rate (i.e. > 30 fps) performance. Hardware solutions can result in marked improvements. This thesis explores one such hardware implementation that generates dense binocular disparity estimates at frame rates of over 200 fps using a dynamic programming formulation (DPML) developed by Cox et. al. A highly parameterizable field programmable gate array implementation of this architecture demonstrates equivalent accuracy while executing at significantly higher frame rates to those of current approaches. Existing hardware implementations for dense disparity estimation often use sum of squared difference, sum of absolute difference or other similar algorithms that typically perform poorly in comparison to DPML. The presented system runs at 248 fps for a resolution of 320 x 240 pixels and disparity range of 128 pixels, a performance of 2.477 billion DPS.

Image registration is a fundamental problem that can be found in a diverse range of fields within the research community. It is used in areas such as engineering, science, medicine, robotics, computer vision and image processing, which often require the process of developing a spatial mapping between sets of data. Registration plays a crucial role in the medical imaging field where continual advances in imaging modalities, including MRI, CT and PET, allow the generation of 3D images that explicitly outline detailed in vivo information of not only human anatomy, but also human function. Mutual Information (MI) is a popular entropy-based similarity measure which has found use in a large number of image registration applications. Stemming from information theory, this measure generally outperforms most other intensity-based measures in multimodal applications as it does not assume the existence of any specific relationship between image intensities. It only assumes a statistical dependence. The basic concept behind any approach using MI is to find a transformation, which when applied to an image, will maximise the MI between two images. This thesis presents research using MI in three major topics encompassed by the computer vision and medical imaging field: rigid image registration, stereo vision, and non-rigid image registration. In the rigid domain, a novel gradient-based registration algorithm (MIGH) is proposed that uses Parzen windows to estimate image density functions and Gauss-Hermite quadrature to estimate the image entropies. The use of this quadrature technique provides an effective and efficient way of estimating entropy while bypassing the need to draw a second sample of image intensities (a procedure required in previous Parzen-based MI registration approaches). It is possible to achieve identical results with the MIGH algorithm when compared to current state of the art MI-based techniques. These results are achieved using half the previously required sample sizes, thus doubling the statistical power of the registration algorithm. Furthermore, the MIGH technique improves algorithm complexity by up to an order of N, where N represents the number of samples extracted from the images. In stereo vision, a popular passive method of depth perception, new extensions have been pro- posed in order to increase the robustness of MI-based stereo matching algorithms. Firstly, prior probabilities are incorporated into the MI measure to considerably increase the statistical power of the matching windows. The statistical power, directly related to the number of samples, can become too low when small matching windows are utilised. These priors, which are calculated from the global joint histogram, are tuned to a two level hierarchical approach. A 2D match surface, in which the match score is computed for every possible combination of template and matching windows, is also utilised to enforce left-right consistency and uniqueness constraints. These additions to MI-based stereo matching significantly enhance the algorithms ability to detect correct matches while decreasing computation time and improving the accuracy, particularly when matching across multi-spectra stereo pairs. MI has also recently found use in the non-rigid domain due to a need to compute multimodal non-rigid transformations. The viscous fluid algorithm is perhaps the best method for re- covering large local mis-registrations between two images. However, this model can only be used on images from the same modality as it assumes similar intensity values between images. Consequently, a hybrid MI-Fluid algorithm is proposed to compute a multimodal non-rigid registration technique. MI is incorporated via the use of a block matching procedure to generate a sparse deformation field which drives the viscous fluid algorithm, This algorithm is also compared to two other popular local registration techniques, namely Gaussian convolution and the thin-plate spline warp, and is shown to produce comparable results. An improved block matching procedure is also proposed whereby a Reversible Jump Markov Chain Monte Carlo (RJMCMC) sampler is used to optimally locate grid points of interest. These grid points have a larger concentration in regions of high information and a lower concentration in regions of small information. Previous methods utilise only a uniform distribution of grid points throughout the image.

Les récentes paramétrisations utilisées dans les modèles spectraux de vagues offrent des résultats intéressants en termes de prévision et rejeux des états de mer. Cependant, de nombreux phénomènes physiques présents dans ces modèles sont encore mal compris et donc mal modélisés, notamment le terme de dissipation lié au déferlement des vagues.Le travail présenté dans cette thèse vise dans un premier temps à analyser et critiquer les paramétrisations existantes de la dissipation, au travers de la modélisation explicite des propriétés du déferlement sous-jacentes. Du constat de l’échec de ces paramétrisations à reproduire les observations in situ et satellite du déferlement, une nouvelle méthode d’observation et d’analyse des déferlements est proposée à l’aide de systèmes de stéréo vidéo. Cette méthode permet l’observation des déferlements sur des surfaces de mer reconstruites à haute résolution par stéréo triangulation. Ainsi, une méthode complète de reconstruction des surfaces de mer en présence de vagues déferlantes est proposée et validée. La détection des vagues déferlantes sur les images et leur reprojection sur les surfaces reconstruites est également discutée. Bien que peu d’acquisitions soient disponibles, les différents paramètres observables grâce à l’utilisation de la stéréo vidéo sont mis en avant. Ce travail montre l’intérêt des systèmes vidéo stéréo pour une meilleure observation et compréhension du déferlement des vagues, pour le développement des paramétrisations de la dissipation dans les modèles spectraux de vague. / The recent parameterizations used in spectral wave models provide today interesting results in terms of forecast and hindcast of the sea states. Nevertheless, many physical phenomena present in these models are still poorly understood and therefore poorly modeled, in particular the dissipation source term due to breaking. First, the work presented in this thesis is aimed at analyzing and criticizing the existing parameterizations of the dissipation through the explicit modeling of the underlying properties of breaking. The finding of the failure of these parameterizations to reproduce the in situ and satellite observations, a new method for the observation and the analysis of breaking is proposed using stereo video systems . This method allows the observation of breaking waves on the high-resolution stereo-reconstructed sea surfaces. Therefore, a complete method for reconstruction of the sea surfaces in the presence of breaking waves is proposed and validated.The detection of breaking waves on the images and their reprojection on reconstructed surface is also discussed. Although too few acquisitions are available to draw firm results, an overview of the various observable parameters through the use of stereo video is given.This work shows the importance of stereo video systems to a better observation and understanding of the breaking waves, required in order to improve dissipation source term in spectral wave models.

LIDAR (2D) has been widely used for mapping, localization and navigation in mobile robotics. However, its usage is limited to simple environments. This problem can be solved by adding more sensors and processing these data together. This paper explores a method how measurements from a stereo camera and LIDAR are fused to dynamical mapping. An occupancy grid map from LIDAR data is used as prerequisite and extended by a 2D grid map from stereo camera. This approach is based on the ground plane estimation in disparity map acquired from the stereo vision. For the ground plane detection, RANSAC and Least Squares methods are used. After obstacles determination, 2D occupancy map is generated. The output of this method is 2D map as a fusion of complementary maps from LIDAR and camera. Experimental results obtained from RUDA robot and MIT Stata Center Data Set are good enough to determine that this method is a benefit, although my implementation is still a prototype. In this paper, we present the applied methods, analyze the results and discuss the modifications and possible extensions to get better results.

This master’s thesis deals with the design of systems for data collection which describe the driver’s behaviour in a car. This data is used to detect risky behaviour that the driver may commit due to inattention caused by the use of either lower or higher levels of driving automation. The thesis first describes the existing safety systems, especially in relation to the driver. Then it deals with the design of the necessary measuring scenes and the implementation of new systems based on the processing of input images which are obtained via the Intel RealSense D415 stereo camera. Every system is tested in a real vehicle environment. In the end the thesis contains an evaluation regarding the detection reliability of the created algorithms, it considers their shortcomings and possible improvements.

Im Rahmen dieser Arbeit wurde der Einfluss von passiven und elastischen Rückstromklappen, die auch als Flaps bezeichnet werden, auf einen Tragflügel mit NACA0020 Profil untersucht. Mithilfe einer Kraftwaage erfolgte zunächst die Erfassung der Auswirkungen auf das aerodynamische Verhalten des Tragflügels vor und nach der Strömungsablösung. Für ein detailliertes Verständnis wurde zusätzlich die Umströmung mit der Rauchdrahttechnik visualisiert und die Flapkinematik mit der Stereo Vision Technik aufgenommen. Es konnte festgestellt werden, dass die Vorderkantenflaps mit der geringsten Biegesteifigkeit die Gleitzahl des Tragflügels vor allem in abgelöster Strömung erhöhen. Die festgestellte Auftriebssteigerung resultiert aus der langsamen Aufstellbewegung und beschleunigten Anlegebewegung der Flaps, die eine einhergehende Reduzierung der turbulenten Ablösung verursachen. Die Ergebnisse der Arbeit liefern zahlreiche Erkenntnisse, die eine Übertragung des festgestellten Effekts auf andere technische Anwendungen erleichtern.:Abbildungsverzeichnis....................................................................... VII Tabellenverzeichnis............................................................................ XII Symbol- & Abkürzungsverzeichnis..................................................XVI 1 Einleitung......................................................................................... 1 2 Stand der Forschung........................................................................ 4 2.1 Wesentliche Aspekte von Profilumströmungen ................................. 4 2.2 Zusammenfassung essenzieller Aspekte von Tragflügeln mit Flaps ......7 3 Numerische Untersuchung der Profilumströmung....................... 13 3.1 Numerische Modell ......................................................................13 3.1.1 Grundgleichungen und Turbulenzmodell ..............................13 3.1.2 Randbedingungen und Diskretisierungsschema .....................16 3.2 Ergebnisse für das NACA0018 Profil .............................................18 3.3 Ergebnisse für das NACA0020 Profil .............................................19 3.4 Schlussfolgerung aus den Simulationen ..........................................22 4 Kraftmessungen an einem NACA0020 Tragflügel ....................... 23 4.1 Versuchsvorbereitung ...................................................................23 4.1.1 Windkanal ........................................................................23 4.1.2 Tragflügel und Funktionsweise der Kraftwaage .....................25 4.2 Messunsicherheit und Validierung .................................................27 4.3 Position der Flaps auf dem Tragflügel............................................ 31 4.3.1 Flapgeometrie und Flappositionen....................................... 31 4.3.2 Polardiagramme für variierende Flapposition........................34 4.4 Faserverstärkte Silikonflaps...........................................................36 4.4.1 Verwendeten Materialien ....................................................36 4.4.2 Polardiagramm für faserverstärkte Silikonflaps .....................38 4.5 Flapgeometrie .............................................................................40 4.5.1 Untersuchte Flapformen .....................................................40 4.5.2 Polardiagramm der untersuchten Flapformen ....................... 41 4.6 Wirkung der Flaps bei instationären Anströmung...........................43 4.6.1 Versuchsdurchführung ........................................................43 4.6.2 Ergebnisse der instationären Untersuchung...........................45 4.7 Schlussfolgerung der Auftriebs- und Widerstandsuntersuchungen .....47 5 Strömungsvisualisierung mithilfe der Rauchdrahttechnik........... 49 5.1 Experimenteller Aufbau ...............................................................49 5.2 Vorgehensweise bei der Auswertung...............................................50 5.3 Ergebnisse der Visualisierung........................................................ 51 6 Flapkantenkinematik..................................................................... 58 6.1 Versuchsaufbau und Versuchsdurchführung ....................................58 6.2 Bildauswertung ........................................................................... 61 6.3 Ergebnisse ..................................................................................62 6.3.1 VK Konfiguration - ohne Faserverstärkung...........................62 6.3.2 Bewegungsausführung des Vorderkantenflaps der VK-HK Konfiguration - ohne Faserverstärkung.......................................69 6.3.3 Bewegungsausführung des Vorderkantenflaps der VK-HK Konfiguration - mit Faserverstärkung ........................................75 6.3.4 Auswertung und Interpretation ...........................................82 7 Zusammenfassung.......................................................................... 87 8 Ausblick.......................................................................................... 89 Anhang ................................................................................................ 97 A Anhang 1....................................................................................97 B Anhang 2....................................................................................98 C Anhang 3....................................................................................99 / In the following study the effects of elastic and passive flaps were investigated on an airfoil with a NACA0020 profile. At first the aerodynamic performance of different configurations was measured with a force balance. In order to detect its effects before and after stall the angle of attack was varied during the experiments. For the configurations with increased aerodynamic performance additional experiments were carried out. The smoke wire visualization and stereo vision technique allowed a detailled insight in the flow around the NACA0020 profile and the flap movement. The results show that elastic flaps at the leading and trailing edge of the airfoil improve notably the airfoil performance in deep stall. Furthermore, the highest increase of the lift-to-drag ratio was achieved for the configuration with lowest bending stiffness. It was observed that the highest reduction of the turbulent separation region is caused by the flap movement. The increase of lift-to-drag ratio results from a slow upward and a fast downward motion of the elastic flap. The study delivers helpful information for transfer of the observed effect to other technical applications.:Abbildungsverzeichnis....................................................................... VII Tabellenverzeichnis............................................................................ XII Symbol- & Abkürzungsverzeichnis..................................................XVI 1 Einleitung......................................................................................... 1 2 Stand der Forschung........................................................................ 4 2.1 Wesentliche Aspekte von Profilumströmungen ................................. 4 2.2 Zusammenfassung essenzieller Aspekte von Tragflügeln mit Flaps ......7 3 Numerische Untersuchung der Profilumströmung....................... 13 3.1 Numerische Modell ......................................................................13 3.1.1 Grundgleichungen und Turbulenzmodell ..............................13 3.1.2 Randbedingungen und Diskretisierungsschema .....................16 3.2 Ergebnisse für das NACA0018 Profil .............................................18 3.3 Ergebnisse für das NACA0020 Profil .............................................19 3.4 Schlussfolgerung aus den Simulationen ..........................................22 4 Kraftmessungen an einem NACA0020 Tragflügel ....................... 23 4.1 Versuchsvorbereitung ...................................................................23 4.1.1 Windkanal ........................................................................23 4.1.2 Tragflügel und Funktionsweise der Kraftwaage .....................25 4.2 Messunsicherheit und Validierung .................................................27 4.3 Position der Flaps auf dem Tragflügel............................................ 31 4.3.1 Flapgeometrie und Flappositionen....................................... 31 4.3.2 Polardiagramme für variierende Flapposition........................34 4.4 Faserverstärkte Silikonflaps...........................................................36 4.4.1 Verwendeten Materialien ....................................................36 4.4.2 Polardiagramm für faserverstärkte Silikonflaps .....................38 4.5 Flapgeometrie .............................................................................40 4.5.1 Untersuchte Flapformen .....................................................40 4.5.2 Polardiagramm der untersuchten Flapformen ....................... 41 4.6 Wirkung der Flaps bei instationären Anströmung...........................43 4.6.1 Versuchsdurchführung ........................................................43 4.6.2 Ergebnisse der instationären Untersuchung...........................45 4.7 Schlussfolgerung der Auftriebs- und Widerstandsuntersuchungen .....47 5 Strömungsvisualisierung mithilfe der Rauchdrahttechnik........... 49 5.1 Experimenteller Aufbau ...............................................................49 5.2 Vorgehensweise bei der Auswertung...............................................50 5.3 Ergebnisse der Visualisierung........................................................ 51 6 Flapkantenkinematik..................................................................... 58 6.1 Versuchsaufbau und Versuchsdurchführung ....................................58 6.2 Bildauswertung ........................................................................... 61 6.3 Ergebnisse ..................................................................................62 6.3.1 VK Konfiguration - ohne Faserverstärkung...........................62 6.3.2 Bewegungsausführung des Vorderkantenflaps der VK-HK Konfiguration - ohne Faserverstärkung.......................................69 6.3.3 Bewegungsausführung des Vorderkantenflaps der VK-HK Konfiguration - mit Faserverstärkung ........................................75 6.3.4 Auswertung und Interpretation ...........................................82 7 Zusammenfassung.......................................................................... 87 8 Ausblick.......................................................................................... 89 Anhang ................................................................................................ 97 A Anhang 1....................................................................................97 B Anhang 2....................................................................................98 C Anhang 3....................................................................................99