A identificação de pontos em padrões de calibração é relatada como uma fase trabalhosa nos processos de calibração de câmeras. Essa etapa é sensível à presença de ruídos e geralmente requer a identificação de muitos pontos de controle. A detecção automática de padrões de calibração é fundamental para a automatização desse processo. Os trabalhos existentes são poucos e implementam soluções semi-automáticas ou, quando automáticas, não lidam com imagens distorcidas, com inclinações acentuadas ou exigem a detecção de todos os pontos apresentados pelo padrão de calibração. O presente trabalho vem contribuir com essa área propondo uma metodologia, denominada Chessboard Topological Detection (ChTD), completamente automática, aplicável a imagens com alta distorção, independente da detecção completa do padrão e que apresenta melhor aproveitamento dos pontos e do conjunto de imagens de calibração. A metodologia proposta é baseada em três etapas: a detecção estrutural dos pontos de interesse; triangulação e filtragem dos pontos encontrados com base em regras topológicas; e a propagação e ajuste de coordenadas via conectividade dos pontos vizinhos. A partir dessa metodologia foi implementada uma ferramenta que permite extrair pontos de calibração de um padrão xadrez de forma simples e completamente automática. Na avaliação do método ChTD foi realizada uma comparação com a função findChessBoardCorners da biblioteca OpenCV usando conjuntos de imagens reais e sintéticas. Os testes realizados com imagens reais possibilitaram comparações numéricas da quantidade de pontos e de padrões detectados, e os com imagens sintéticas permitiram avaliar o ChTD diante de inclinações do padrão e ruídos controlados. Pelos resultados obtidos foi possível verificar que o ChTD foi superior ao método do OpenCV, apresentando menor dependência à inclinação do padrão, melhor aproveitamento dos pontos e das imagens de calibração e realizando a detecção em imagens distorcidas. O ChTD é executado em um único passo, diferenciando-se do método do OpenCV que faz transformações sucessivas da imagem. A metodologia desenvolvida é modularizada, possibilitando o uso de outros algoritmos em suas fases intermediárias. / The detection of calibration points is reported as a time consuming task in camera calibration systems. This task is sensitive to noise and usually requires identification of a large set of control points. A methodology of automatic detection of calibration patterns is essential for the automation of this process. Existing works are few and usually implement semi-automatic solutions. Automatic methods do not deal with distorted images, and patterns with high tilt angles or require the detection of all the calibration points. The present work aims to contribute to this area proposing a methodology named Chessboard Topological Detection (ChTD), which is completely automatic, applicable to images with high distortion, making better use of all detected points, avoind calibration frames losses, regardless of the complete detection of the pattern features. The proposed methodology is based on three steps: the structural detection of points of interest, filtering and triangulation of the points based on topological rules and the adjust and coordinate propagation via connectivity of neighboring points inside the mesh. Based on this methodology, was implemented a tool that allows to extract calibration points of a chessboard pattern in a simple and automatic way. For the evaluation of the method ChTD, a comparison was made with the function findChessBoardCorners, which belongs to OpenCV library, using sets of synthetic and real images. Tests performed with real images allowed numerical comparisons of the number of points and detected patterns. The tests with synthetic images allowed to evaluate the ChTD facing the controlled tilt angle of the chessboard pattern and controlled image noise. The obtained results showed that the ChTD method was superior to OpenCV, with less dependence on the tilt angle of the calibration pattern, detecting more points, avoiding calibration images losses and detecting the pattern in distorted images. The ChTD runs in a single step, differing from OpenCV method that makes successive transformations of the image. The developed methodology is modular, enabling the use of different algorithms in its intermediates and some principal stages.

Integrated camera systems for increasing safety and maneuverability are becoming increasingly common for heavy vehicles. One problem with heavy vehicles today is that there are blind spots where the driver has no or very little view. There is a great demand on increasing the safety and helping the driver to get a better view of his surroundings. This can be achieved by a sophisticated camera system, using cameras with wide field of view, that could cover dangerous blind spots. This master thesis aims to investigate and develop a prototype solution for a camera system consisting of two fisheye cameras. The solution covers both hardware choices and software development including camera calibration and image stitching. Two different fisheye camera calibration toolboxes are compared and their results discussed, with the aim to find the most suitable for this application. The result from the two toolboxes differ in performance, and the result from only one of the toolboxes is sufficient for image stitching.

Abstract Automatic three-dimensional scene reconstruction from multiple images is a central problem in geometric computer vision. This thesis considers topics that are related to this problem area. New models and methods are presented for various tasks in such specific domains as camera calibration, image-based modeling and image matching. In particular, the main themes of the thesis are geometric camera calibration and quasi-dense image matching. In addition, a topic related to the estimation of two-view geometric relations is studied, namely, the computation of a planar homography from corresponding conics. Further, as an example of a reconstruction system, a structure-from-motion approach is presented for modeling sewer pipes from video sequences. In geometric camera calibration, the thesis concentrates on central cameras. A generic camera model and a plane-based camera calibration method are presented. The experiments with various real cameras show that the proposed calibration approach is applicable for conventional perspective cameras as well as for many omnidirectional cameras, such as fish-eye lens cameras. In addition, a method is presented for the self-calibration of radially symmetric central cameras from two-view point correspondences. In image matching, the thesis proposes a method for obtaining quasi-dense pixel matches between two wide baseline images. The method extends the match propagation algorithm to the wide baseline setting by using an affine model for the local geometric transformations between the images. Further, two adaptive propagation strategies are presented, where local texture properties are used for adjusting the local transformation estimates during the propagation. These extensions make the quasi-dense approach applicable for both rigid and non-rigid wide baseline matching. In this thesis, quasi-dense matching is additionally applied for piecewise image registration problems which are encountered in specific object recognition and motion segmentation. The proposed object recognition approach is based on grouping the quasi-dense matches between the model and test images into geometrically consistent groups, which are supposed to represent individual objects, whereafter the number and quality of grouped matches are used as recognition criteria. Finally, the proposed approach for dense two-view motion segmentation is built on a layer-based segmentation framework which utilizes grouped quasi-dense matches for initializing the motion layers, and is applicable under wide baseline conditions.

Pas de résumé / In this thesis, we study the problem of registering 2D image sets and 3D point clouds under threedifferent acquisition set-ups. The first set-up assumes that the image sets are captured using 2Dcameras that are fully calibrated and coupled, or rigidly attached, with a 3D sensor. In this context,the point cloud from the 3D sensor is registered directly to the asynchronously acquired 2D images.In the second set-up, the 2D cameras are internally calibrated but uncoupled from the 3D sensor,allowing them to move independently with respect to each other. The registration for this set-up isperformed using a Structure-from-Motion reconstruction emanating from images and planar patchesrepresenting the point cloud. The proposed registration method is globally optimal and robust tooutliers. It is based on the theory Sum-of-Squares polynomials and a Branch-and-Bound algorithm.The third set-up consists of uncoupled and uncalibrated 2D cameras. The image sets from thesecameras are registered to the point cloud in a globally optimal manner using a Branch-and-Prunealgorithm. Our method is based on a Linear Matrix Inequality framework that establishes directrelationships between 2D image measurements and 3D scene voxels.

Unmanned aerial vehicles (UAV) have become an interesting and active research topic for photogrammetry. Current research is based on images acquired by an UAV, which have a high ground resolution and good spectral and radiometrical resolution, due to the low flight altitudes combined with a high resolution camera. UAV image flights are also cost effective and have become attractive for many applications including, change detection in small scale areas. One of the main problems preventing full automation of data processing of UAV imagery is the degradation effect of blur caused by camera movement during image acquisition. This can be caused by the normal flight movement of the UAV as well as strong winds, turbulence or sudden operator inputs. This blur disturbs the visual analysis and interpretation of the data, causes errors and can degrade the accuracy in automatic photogrammetric processing algorithms. The detection and removal of these images is currently achieved manually, which is both time consuming and prone to error, particularly for large image-sets. To increase the quality of data processing an automated process is necessary, which must be both reliable and quick. This thesis proves the negative affect that blurred images have on photogrammetric processing. It shows that small amounts of blur do have serious impacts on target detection and that it slows down processing speed due to the requirement of human intervention. Larger blur can make an image completely unusable and needs to be excluded from processing. To exclude images out of large image datasets an algorithm was developed. The newly developed method makes it possible to detect blur caused by linear camera displacement. The method is based on human detection of blur. Humans detect blurred images best by comparing it to other images in order to establish whether an image is blurred or not. The developed algorithm simulates this procedure by creating an image for comparison using image processing. Creating internally a comparable image makes the method independent of additional images. However, the calculated blur value named SIEDS (saturation image edge difference standard-deviation) on its own does not provide an absolute number to judge if an image is blurred or not. To achieve a reliable judgement of image sharpness the SIEDS value has to be compared to other SIEDS values of the same dataset. This algorithm enables the exclusion of blurred images and subsequently allows photogrammetric processing without them. However, it is also possible to use deblurring techniques to restor blurred images. Deblurring of images is a widely researched topic and often based on the Wiener or Richardson-Lucy deconvolution, which require precise knowledge of both the blur path and extent. Even with knowledge about the blur kernel, the correction causes errors such as ringing, and the deblurred image appears muddy and not completely sharp. In the study reported in this paper, overlapping images are used to support the deblurring process. An algorithm based on the Fourier transformation is presented. This works well in flat areas, but the need for geometrically correct sharp images for deblurring may limit the application. Another method to enhance the image is the unsharp mask method, which improves images significantly and makes photogrammetric processing more successful. However, deblurring of images needs to focus on geometric correct deblurring to assure geometric correct measurements. Furthermore, a novel edge shifting approach was developed which aims to do geometrically correct deblurring. The idea of edge shifting appears to be promising but requires more advanced programming.

京都大学 / 新制・課程博士 / 博士(情報学) / 甲第23543号 / 情博第773号 / 新制||情||132(附属図書館) / 京都大学大学院情報学研究科知能情報学専攻 / (主査)准教授 延原 章平, 教授 西野 恒, 教授 西田 眞也, 教授 佐藤 いまり(国立情報学研究所) / 学位規則第4条第1項該当 / Doctor of Informatics / Kyoto University / DFAM

The diploma thesis focuses on programming in the Matlab for the Raspberry Pi 3 platform. For the purpose of the presentation, there are two applications designed for Raspberry Pi that are using available hardware, camera and servos. The first application serves as colour object detecting and accurate tracking by using camera calibration. The second application serves as a face detection and recognition. These applications are implemented by modern methods and knowledge of computer vision. Tracking of the objects and face recognition are verified by an experiment that reveals the accuracy of the used methods.

The thesis falls within the field of computer vision. It describes the development of the software environment for 3D data processing. The thesis deals with the design of C++ classes suitable for scene description and representation of bonding conditions between scenes elements. There is also discussed the solution of camera calibration, geometric distortion identification and 3D coordinates reconstruction. The solving of these tasks is augmented with planarity and linearity conditions, which support projection equations and augment the computational ability of the environment.

Zařízení k analýze pohybu umožnují zdokonalit chirurgický zákrok, rahebilitaci patologií pohybového systému a jsou také velmi přínosné pro výzkum v oboru biomechaniky. V dešní době existuje mnoho zařízení k analýze pohybu, jejihž cena může dosáhnout až 150 k€ (Vicon, Motion Analysis). Cílem této diplomové práce je vyvinutí levného prototypu zařízení k analýze pohybu založeného na sledování barevných terčíků pomocí dvou jedoduchých digitálních kamer a programu ke zpracování obrazu.

Stereo camera systems can be utilized for different applications such as position estimation,distance measuring, and 3d modelling. However, this requires the cameras to be calibrated.This paper proposes a traditional calibration solution with Aruco-markers mounted on avehicle to estimate the pose of a stereo camera system in a tolling environment. Our method isbased on Perspective N Point which presumes the intrinsic matrix to be already known. Thegoal is to find each camera’s pose by identifying the marker corners in pixel coordinates aswell as in world coordinates. Our tests show a worst-case error of 21.5 cm and a potential forcentimetre accuracy. It also verifies validity by testing the obtained pose estimation live in thecamera system. The paper concludes that the method has potential for higher accuracy notobtained in our experiment due to several factors. Further work would focus on enlarging themarkers and widening the distance between the markers.