Wrinkling and pilling caused in wear and care procedures are vital performance characteristics of fabric. The advance of three-dimensional (3D) imaging techniques has made it possible to develop a convenient, reliable and low cost tool for automatic and efficient evaluation of fabric wrinkling and pilling. We suggest that 3D imaging and measurement system can provide a convenient, accommodating and comprehensive mean to fabric surface assessment. A 3D imaging system based on stereo vision technology is developed. To make it more affordable and portable, the system consists of a pair of consumer grade high resolution digital cameras with mounting hardware. The system is calibrated with classic camera calibration technique. The calibration procedure is relatively complicated, but there is no need to repeat frequently as long as the relative positions between cameras are not changed. In this system, image acquisition can be completed in less than one second. This efficient surface capturing feature is important for a large amount of measurement tasks. However, the computation in stereo vision is complex and intensive, thus it remains a challenge. A two-phase multi-resolution stereo matching algorithm is developed. In the first phase, a discrete disparity map is generated by block matching. In the second phase, local least-squares matching is performed in combination with global optimization within a regularization framework, so as to ensure both accuracy and reliability. To make the 3D imaging system ready for practical use, detection and measurement modules for wrinkling and pilling were developed to take advantage of the depth information in the 3D surface data. The practical feasibility of the 3D imaging system in fabric surface assessment was demonstrated in comparison with human visual ratings. The results showed agreement between the 3D automatic assessment and subjective visual assessment. / text

In this thesis, we build a robust end-to-end pipeline for the localization of multiple drones in a GPS-denied environment. This pipeline would help us with cooperative formation control, autonomous delivery, search and rescue operations etc. To achieve this we integrate a custom trained YOLO (You Only Look Once) object detection network, for drones, with the ZED2 stereo camera system. With the help of this sensor we obtain a relative vector from the left camera to that drone. After calibrating it from the left camera to that drone's center of mass, we then estimate the location of all the drones in the leader drone's frame of reference. We do this by solving the localization problem with least squares estimation and thus acquire the location of the follower drone's in the leader drone's frame of reference. We present the results with the stereo camera system followed by simulations run in AirSim to verify the precision of our pipeline. / Master of Science / In the recent years, technologies like Deep Learning and Machine Learning have seen many rapid developments. This has lead to the rise of fields such as autonomous drones and their application in fields such as bridge inspection, search and rescue operations, disaster management relief, agriculture, real estate etc. Since GPS is a highly unreliable sensor, we need an alternate method to be able to localize the drones in various environments in real time. In this thesis, we integrate a robust drone detection neural network with a camera which estimates the location. We then use this data to get the relative location of all the follower drones from the leader drone. We run experiments with the camera and in a simulator to show the accuracy of our results.

Fabric appearance is usually the highest priority consideration for consumers. Pilling and wrinkling are two major factors which cause the fabric to have a worse appearance after a certain service period. In order to prevent more piling and wrinkling, a fabric pilling and wrinkling severity evaluation is very important. Traditional visual examination needs at least three trained experts to judge each sample, which is both subjective and time-consuming. Objective, high efficiency, and automatic pilling and wrinkling evaluation based on computer processing techniques are now being developed quickly. In this study, an integrated fabric pilling and wrinkling measurement system based on stereovision was developed. The hardware part of the system consists of a pair of consumer high resolution cameras and a mounting stage, which is affordable and portable in comparison with other 3D imaging systems. A novel pilling detection algorithm focusing on 3D image local information was proposed to extract three pilling features including pilling density, pilling average height, and pilling average size. The logistic regression classifier was applied for pilling severity classification because it showed a good accuracy with 80% on the 120 3D pilling images. A fast wrinkle detection algorithm with leveled 3D fabric surface was developed to measure wrinkle density, hardness, tip-angle, and roughness. According to these four wrinkling features, 180 3D wrinkling images were tested by the logistic regression classifier with an overall 74.4% accuracy in comparison with visual judging results. Both pilling and wrinkling results obtained from the proposed automatic 3D fabric pilling and wrinkling severity evaluation system were consistent with the subjective visual evaluation results. The system is ready for practical use. / text

"Stereovision has been applied in many fields including UGV (Unmanned Ground Vehicle) navigation and surgical robotics. Traditionally most stereovision applications are binocular which uses information from a horizontal 2-camera array to perform stereo matching and compute the depth image. Trinocular stereovision with a 3-camera array has been proved to provide higher accuracy in stereo matching which could benefit application like distance finding, object recognition and detection. However, as a result of an extra camera, additional information to be processed would increase computational burden and hence not practical in many time critical applications like robotic navigation and surgical robot. Due to the nature of GPUÂ’s highly parallelized SIMD (Single Instruction Multiple Data) architecture, GPGPU (General Purpose GPU) computing can effectively be used to parallelize the large data processing and greatly accelerate the computation of algorithms used in trinocular stereovision. So the combination of trinocular stereovision and GPGPU would be an innovative and effective method for the development of stereovision application. This work focuses on designing and implementing a real-time trinocular stereovision algorithm with GPU (Graphics Processing Unit). The goal involves the use of Open Source Computer Vision Library (OpenCV) in C++ and NVidia CUDA GPGPU Solution. Algorithms were developed with many different basic image processing methods and a winner-take-all method is applied to perform fusion of disparities in different directions. The results are compared in accuracy and speed to verify the improvement."

Objective and accurate surface measurements are important in many clinical disciplines. Non-irradiating and low cost alternatives are available but validation of these measurement tools for clinical application is variable and sparse. This thesis presents a three dimensional (3D) surface measurement method validated by gold standard Computed Tomography (CT). Forty-one 3D surface data sets were acquired by two modalities, a laser scanner and a binocular camera. The binocular camera was tested with three different texture modifiers that increased the colour variability of the imaged surface. A surface area calculation algorithm was created to process the data sets. Relative differences were calculated for each area measurement with respect to its corresponding CT measurement. The laser scanner data sets were affected by movement and specular reflection artefacts. The measurements were statistically equivalent to CT if less than 20% error were considered acceptable. The binocular camera with the slide projected texture modifier was shown to be statistically equivalent to CT gold standard with less than 5% error (p < 0.0005). The surface area measurement method can easily be expanded and customized. By following the protocol outlined by the example in this work, researchers and clinicians would also be able to objectively asses other vision systems' performance and suitability. / Thesis (Master, Computing) -- Queen's University, 2012-01-10 11:37:50.374

Vårt magisterarbete är en 3D-animation som ska simulera en bergochdalbana. Vår uppgift har varit att ta reda på hur man genom illusioner kan lura människans hjärna att se djup även då bilden är helt platt. Vårt främsta verktyg vi använt oss av är glasögon med röd- och cyanfärgade filter. Till vår produktion har vi anlitat andra studenter för att komponera musik och mixa 5.1-ljud. Allt för att öka upplevelsen ännu mer. / Detta är en reflektionsdel till en digital medieproduktion. Mattias e-mail: mape78@gmail.com, Johan e-mail: atra@telia.com

This thesis deals with 3D reconstruction using stereo cameras. This work is to show the usefulness of GPU acceleration for sophisticated algorithm

Thesis solves 3D reconstruction of an object by method of lighting by pattern. A projector lights the measured object by defined pattern and two cameras are measuring 2D points from it. The pedestal of obejct rotates and during the measure are acquired data from different angles. Points are indentified from measured images, transformed to 3D using stereovision, connected to 3D model and displayed.

Autonomous proximity operations are the future of Deep space robotic exploration for searchof life, mining for resources and to establish outposts. Part of that future depends on howwell the spacecraft is capable to navigate around the complex environment of the smallcelestial body. The shift from huge monolithic spacecraft to a lightweight distributed Spacesystems has opened up a new opportunity for early characterization and global mappingmissions around these bodies. This project aims to contribute to help solve a part of thedream, wherein multiple spacecrafts operate cooperatively in proximity of small celestialbodies. To that extent, a 6 DoF controlled software-in-loop simulation is performed withsimulated optical sensors and IMU on board the spacecraft for verification of the controlledcooperative operation of two spacecrafts in a Leader-Follower configuration.

L'étude des caméras et des images a été un sujet prédominant depuis le début de la vision par ordinateur, l'un des principaux axes étant l'estimation de la pose et la reconstruction 3D. Le but de cette thèse est d'aborder et d'étudier certains problèmes et méthodes spécifiques du pipeline de la structure-from-motion afin d'améliorer la précision, de réaliser de vastes études pour comprendre les avantages et les inconvénients des modèles existants et de créer des outils mis à la disposition du public. Plus spécifiquement, nous concentrons notre attention sur les pairs stéréoscopiques et les triplets d'images et nous explorons certaines des méthodes et modèles capables de fournir une estimation de la pose et une reconstruction 3D de la scène.Tout d'abord, nous abordons la tâche d'estimation de la profondeur pour les pairs stéréoscopiques à l'aide de la correspondance de blocs. Cette approche suppose implicitement que tous les pixels du patch ont la même profondeur, ce qui produit l'artefact commun dénommé "foreground-fattening effect". Afin de trouver un support plus approprié, Yoon et Kweon ont introduit l'utilisation de poids basés sur la similarité des couleurs et la distance spatiale, analogues à ceux utilisés dans le filtre bilatéral. Nous présentons la théorie de cette méthode et l'implémentation que nous avons développée avec quelques améliorations. Nous discutons de quelques variantes de la méthode et analysons ses paramètres et ses performances.Deuxièmement, nous considérons l'ajout d'une troisième vue et étudions le tenseur trifocal, qui décrit les contraintes géométriques reliant les trois vues. Nous explorons les avantages offerts par cet opérateur dans la tâche d'estimation de pose d'un triplet de caméras par opposition au calcul des poses relatives paire par paire en utilisant la matrice fondamentale. De plus, nous présentons une étude et l’implémentation de plusieurs paramétrisations du tenseur. Nous montrons que l'amélioration initiale de la précision du tenseur trifocal n'est pas suffisante pour avoir un impact remarquable sur l'estimation de la pose après ajustement de faisceau et que l'utilisation de la matrice fondamentale avec des triplets d'image reste pertinente.Enfin, nous proposons d'utiliser un modèle de projection différent de celui de la caméra à sténopé pour l'estimation de la pose des caméras en perspective. Nous présentons une méthode basée sur la factorisation matricielle due à Tomasi et Kanade qui repose sur la projection orthographique. Cette méthode peut être utilisée dans des configurations où d'autres méthodes échouent, en particulier lorsque l'on utilise des caméras avec des objectifs à longue distance focale. La performance de notre implémentation de cette méthode est comparée à celle des méthodes basées sur la perspective, nous considérons que l'exactitude obtenue et la robustesse démontré en font un élément à considérer dans toute procédure de la SfM / The study of cameras and images has been a prominent subject since the beginning of computer vision, one of the main focus being the pose estimation and 3D reconstruction. The goal of this thesis is to tackle and study some specific problems and methods of the structure-from-motion pipeline in order to provide improvements in accuracy, broad studies to comprehend the advantages and disadvantages of the state-of-the-art models and useful implementations made available to the public. More specifically, we center our attention to stereo pairs and triplets of images and discuss some of the methods and models able to provide pose estimation and 3D reconstruction of the scene.First, we address the depth estimation task for stereo pairs using block-matching. This approach implicitly assumes that all pixels in the patch have the same depth producing the common artifact known as the ``foreground fattening effect''. In order to find a more appropriate support, Yoon and Kweon introduced the use of weights based on color similarity and spatial distance, analogous to those used in the bilateral filter. We present the theory of this method and the implementation we have developed with some improvements. We discuss some variants of the method and analyze its parameters and performance.Secondly, we consider the addition of a third view and study the trifocal tensor, which describes the geometric constraints linking the three views. We explore the advantages offered by this operator in the pose estimation task of a triplet of cameras as opposed to computing the relative poses pair by pair using the fundamental matrix. In addition, we present a study and implementation of several parameterizations of the tensor. We show that the initial improvement in accuracy of the trifocal tensor is not enough to have a remarkable impact on the pose estimation after bundle adjustment and that using the fundamental matrix with image triplets remains relevant.Finally, we propose using a different projection model than the pinhole camera for the pose estimation of perspective cameras. We present a method based on the matrix factorization due to Tomasi and Kanade that relies on the orthographic projection. This method can be used in configurations where other methods fail, in particular, when using cameras with long focal length lenses. The performance of our implementation of this method is compared to that given by the perspective-based methods, we consider that the accuracy achieved and its robustness make it worth considering in any SfM procedure