Assisted visual servoing by means of structured light

Aquesta tesi tracta sobre la combinació del control visual i la llum estructurada. El control visual clàssic assumeix que elements visuals poden ser fàcilment extrets de les imatges. Això fa que objectes d'aspecte uniforme o poc texturats no es puguin tenir en compte. En aquesta tesi proposem l'ús de la llum estructurada per dotar d'elements visuals als objectes independentment de la seva aparença. En primer lloc, es presenta un ampli estudi de la llum estructurada, el qual ens permet proposar un nou patró codificat que millora els existents. La resta de la tesi es concentra en el posicionament d'un robot dotat d'una càmara respecte diferents objectes, utilitzant la informació proveïda per la projecció de diferents patrons de llum. Dos configuracions han estat estudiades: quan el projector de llum es troba separat del robot, i quan el projector està embarcat en el robot juntament amb la càmara. Les tècniques proposades en la tesi estan avalades per un ampli estudi analític i validades per resultats experimentals.

Single fluoroscopic image based 2D/3D reconstruction of a scaled, patient-specific vertebral model

Purpose Accurate three-dimensional (3D) models of lumbar vertebrae can enable image-based 3D kinematic analysis. The common approach to derive 3D models is by direct segmentation of CT or MRI datasets. However, these have the disadvantages that they are expensive, timeconsuming and/or induce high-radiation doses to the patient. In this study, we present a technique to automatically reconstruct a scaled 3D lumbar vertebral model from a single two-dimensional (2D) lateral fluoroscopic image. Methods Our technique is based on a hybrid 2D/3D deformable registration strategy combining a landmark-to-ray registration with a statistical shape model-based 2D/3D reconstruction scheme. Fig. 1 shows different stages of the reconstruction process. Four cadaveric lumbar spine segments (total twelve lumbar vertebrae) were used to validate the technique. To evaluate the reconstruction accuracy, the surface models reconstructed from the lateral fluoroscopic images were compared to the associated ground truth data derived from a 3D CT-scan reconstruction technique. For each case, a surface-based matching was first used to recover the scale and the rigid transformation between the reconstructed surface model Results Our technique could successfully reconstruct 3D surface models of all twelve vertebrae. After recovering the scale and the rigid transformation between the reconstructed surface models and the ground truth models, the average error of the 2D/3D surface model reconstruction over the twelve lumbar vertebrae was found to be 1.0 mm. The errors of reconstructing surface models of all twelve vertebrae are shown in Fig. 2. It was found that the mean errors of the reconstructed surface models in comparison to their associated ground truths after iterative scaled rigid registrations ranged from 0.7 mm to 1.3 mm and the rootmean squared (RMS) errors ranged from 1.0 mm to 1.7 mm. The average mean reconstruction error was found to be 1.0 mm. Conclusion An accurate, scaled 3D reconstruction of the lumbar vertebra can be obtained from a single lateral fluoroscopic image using a statistical shape model based 2D/3D reconstruction technique. Future work will focus on applying the reconstructed model for 3D kinematic analysis of lumbar vertebrae, an extension of our previously-reported imagebased kinematic analysis. The developed method also has potential applications in surgical planning and navigation.

Mesh-based vs. Image-based Statistical Appearance Model of the Human Femur: a Preliminary Comparison Study for the Creation of Finite Element Meshes

Statistical models have been recently introduced in computational orthopaedics to investigate the bone mechanical properties across several populations. A fundamental aspect for the construction of statistical models concerns the establishment of accurate anatomical correspondences among the objects of the training dataset. Various methods have been proposed to solve this problem such as mesh morphing or image registration algorithms. The objective of this study is to compare a mesh-based and an image-based statistical appearance model approaches for the creation of nite element(FE) meshes. A computer tomography (CT) dataset of 157 human left femurs was used for the comparison. For each approach, 30 finite element meshes were generated with the models. The quality of the obtained FE meshes was evaluated in terms of volume, size and shape of the elements. Results showed that the quality of the meshes obtained with the image-based approach was higher than the quality of the mesh-based approach. Future studies are required to evaluate the impact of this finding on the final mechanical simulations.

A Survey of Image-based Relighting Techniques

Image-based Relighting (IBRL) has recently attracted a lot of research interest for its ability to relight real objects or scenes, from novel illuminations captured in natural/synthetic environments. Complex lighting effects such as subsurface scattering, interreflection, shadowing, mesostructural self-occlusion, refraction and other relevant phenomena can be generated using IBRL. The main advantage of image-based graphics is that the rendering time is independent of scene complexity as the rendering is actually a process of manipulating image pixels, instead of simulating light transport. The goal of this paper is to provide a complete and systematic overview of the research in Imagebased Relighting. We observe that essentially all IBRL techniques can be broadly classified into three categories (Fig. 9), based on how the scene/illumination information is captured: Reflectance function-based, Basis function-based and Plenoptic function-based. We discuss the characteristics of each of these categories and their representative methods. We also discuss about the sampling density and types of light source(s), relevant issues of IBRL.

An image-based method to automatically propagate bony landmarks: application to computational spine biomechanics.

In attempts to elucidate the underlying mechanisms of spinal injuries and spinal deformities, several experimental and numerical studies have been conducted to understand the biomechanical behavior of the spine. However, numerical biomechanical studies suffer from uncertainties associated with hard- and soft-tissue anatomies. Currently, these parameters are identified manually on each mesh model prior to simulations. The determination of soft connective tissues on finite element meshes can be a tedious procedure, which limits the number of models used in the numerical studies to a few instances. In order to address these limitations, an image-based method for automatic morphing of soft connective tissues has been proposed. Results showed that the proposed method is capable to accurately determine the spatial locations of predetermined bony landmarks. The present method can be used to automatically generate patient-specific models, which may be helpful in designing studies involving a large number of instances and to understand the mechanical behavior of biomechanical structures across a given population.

Image-based vs. mesh-based statistical appearance models of the human femur: Implications for finite element simulations.

Statistical appearance models have recently been introduced in bone mechanics to investigate bone geometry and mechanical properties in population studies. The establishment of accurate anatomical correspondences is a critical aspect for the construction of reliable models. Depending on the representation of a bone as an image or a mesh, correspondences are detected using image registration or mesh morphing. The objective of this study was to compare image-based and mesh-based statistical appearance models of the femur for finite element (FE) simulations. To this aim, (i) we compared correspondence detection methods on bone surface and in bone volume; (ii) we created an image-based and a mesh-based statistical appearance models from 130 images, which we validated using compactness, representation and generalization, and we analyzed the FE results on 50 recreated bones vs. original bones; (iii) we created 1000 new instances, and we compared the quality of the FE meshes. Results showed that the image-based approach was more accurate in volume correspondence detection and quality of FE meshes, whereas the mesh-based approach was more accurate for surface correspondence detection and model compactness. Based on our results, we recommend the use of image-based statistical appearance models for FE simulations of the femur.

Image-based biomechanical assessment of vertebral body and intervertebral disc in the human lumbar spine

Life expectancy continuously increases but our society faces age-related conditions. Among musculoskeletal diseases, osteoporosis associated with risk of vertebral fracture and degenerative intervertebral disc (IVD) are painful pathologies responsible for tremendous healthcare costs. Hence, reliable diagnostic tools are necessary to plan a treatment or follow up its efficacy. Yet, radiographic and MRI techniques, respectively clinical standards for evaluation of bone strength and IVD degeneration, are unspecific and not objective. Increasingly used in biomedical engineering, CT-based finite element (FE) models constitute the state-of-art for vertebral strength prediction. However, as non-invasive biomechanical evaluation and personalised FE models of the IVD are not available, rigid boundary conditions (BCs) are applied on the FE models to avoid uncertainties of disc degeneration that might bias the predictions. Moreover, considering the impact of low back pain, the biomechanical status of the IVD is needed as a criterion for early disc degeneration. Thus, the first FE study focuses on two rigid BCs applied on the vertebral bodies during compression test of cadaver vertebral bodies, vertebral sections and PMMA embedding. The second FE study highlights the large influence of the intervertebral disc’s compliance on the vertebral strength, damage distribution and its initiation. The third study introduces a new protocol for normalisation of the IVD stiffness in compression, torsion and bending using MRI-based data to account for its morphology. In the last study, a new criterion (Otsu threshold) for disc degeneration based on quantitative MRI data (axial T2 map) is proposed. The results show that vertebral strength and damage distribution computed with rigid BCs are identical. Yet, large discrepancies in strength and damage localisation were observed when the vertebral bodies were loaded via IVDs. The normalisation protocol attenuated the effect of geometry on the IVD stiffnesses without complete suppression. Finally, the Otsu threshold computed in the posterior part of annulus fibrosus was related to the disc biomechanics and meet objectivity and simplicity required for a clinical application. In conclusion, the stiffness normalisation protocol necessary for consistent IVD comparisons and the relation found between degeneration, mechanical response of the IVD and Otsu threshold lead the way for non-invasive evaluation biomechanical status of the IVD. As the FE prediction of vertebral strength is largely influenced by the IVD conditions, this data could also improve the future FE models of osteoporotic vertebra.

Real-time computer-based visual feedback improves visual acuity in downbeat nystagmus - a pilot study.

BACKGROUND Patients with downbeat nystagmus syndrome suffer from oscillopsia, which leads to an unstable visual perception and therefore impaired visual acuity. The aim of this study was to use real-time computer-based visual feedback to compensate for the destabilizing slow phase eye movements. METHODS The patients were sitting in front of a computer screen with the head fixed on a chin rest. The eye movements were recorded by an eye tracking system (EyeSeeCam®). We tested the visual acuity with a fixed Landolt C (static) and during real-time feedback driven condition (dynamic) in gaze straight ahead and (20°) sideward gaze. In the dynamic condition, the Landolt C moved according to the slow phase eye velocity of the downbeat nystagmus. The Shapiro-Wilk test was used to test for normal distribution and one-way ANOVA for comparison. RESULTS Ten patients with downbeat nystagmus were included in the study. Median age was 76 years and the median duration of symptoms was 6.3 years (SD +/- 3.1y). The mean slow phase velocity was moderate during gaze straight ahead (1.44°/s, SD +/- 1.18°/s) and increased significantly in sideward gaze (mean left 3.36°/s; right 3.58°/s). In gaze straight ahead, we found no difference between the static and feedback driven condition. In sideward gaze, visual acuity improved in five out of ten subjects during the feedback-driven condition (p = 0.043). CONCLUSIONS This study provides proof of concept that non-invasive real-time computer-based visual feedback compensates for the SPV in DBN. Therefore, real-time visual feedback may be a promising aid for patients suffering from oscillopsia and impaired text reading on screen. Recent technological advances in the area of virtual reality displays might soon render this approach feasible in fully mobile settings.

Visual Servoing for the Robotenis System: a Strategy for a 3 DOF Parallel Robot to Hit a Ping-Pong Ball

This article describes a new visual servo control and strategies that are used to carry out dynamic tasks by the Robotenis platform. This platform is basically a parallel robot that is equipped with an acquisition and processing system of visual information, its main feature is that it has a completely open architecture control, and planned in order to design, implement, test and compare control strategies and algorithms (visual and actuated joint controllers). Following sections describe a new visual control strategy specially designed to track and intercept objects in 3D space. The results are compared with a controller shown in previous woks, where the end effector of the robot keeps a constant distance from the tracked object. In this work, the controller is specially designed in order to allow changes in the tracking reference. Changes in the tracking reference can be used to grip an object that is under movement, or as in this case, hitting a hanging Ping-Pong ball. Lyapunov stability is taken into account in the controller design.

Soft-computing based visual control for unmanned vehicles

El objetivo principal de esta Tesis es extender la utilización del “Soft- Computing” para el control de vehículos sin piloto utilizando visión. Este trabajo va más allá de los típicos sistemas de control utilizados en entornos altamente controlados, demonstrando la fuerza y versatilidad de la lógica difusa (Fuzzy Logic) para controlar vehículos aéreos y terrestres en un abanico de applicaciones diferentes. Para esta Tesis se ha realizado un gran número de pruebas reales en las cuales los controladores difusos han manejado una plataforma visual “pan-and-tilt”, un helicoptero, un coche comercial y hasta dos tipos de quadrirotores. El uso del método de optimización “Cross-Entropy” ha sido utilizado para mejorar el comportamiento de algunos de los controladores borrosos. Todos los controladores difusos presentados en ésta Tesis han sido implementados utilizando un código desarrollado por el candidato para tal efecto, llamado MOFS (Miguel Olivares’ Fuzzy Software). Diferentes algoritmos visuales han sido utilizados para adquirir la informaci´on visual del entorno, “Cmashift”, descomposición de la homografía y detección de marcas de realidad aumentada, entre otros. Dicha información visual ha sido utilizada como entrada de los controladores difusos para comandar los vehículos en las diferentes applicaciones autonomas. El volante de un vehículo comercial ha sido controlado para realizar pruebas de conducción autónoma en condiciones de tráfico similares a las de una ciudad. El sistema ha llegado a completar con éxito pruebas de más de 6 km sin ninguna interacción humana, mediante el seguimiento de una línea pintada en el suelo. El limitado campo visual del sistema no ha sido impedimento para alcanzar velocidades de hasta 48 km/h y ser guiado autonomamente en curvas de radio reducido. Objetos estáticos y móviles han sido seguidos desde un helicoptero no tripulado, mediante el control de una plataforma visual “pan-and-tilt”. ´Éste mismo helicoptero ha sido controlado completamente para su aterrizaje autonomo, mediante el control del movimiento lateral (roll), horizontal (pitch) y de altitud. El seguimiento de objetos volantes ha sido resulto mediante el control horizontal (pitch) y de orientación (heading) de un quadrirotor. Para tareas de evitación de obstáculos se ha implementado un controlador difuso para el manejo de la orientación (heading) de un quadrirotor. En el campo de la optimización de controladores se ha aportado al estado del arte una extensión del uso del método “Cross-Entropy”. Está Tesis presenta una novedosa implementación de dicho método para la optimización de las ganancias, la posición y medida de los conjuntos de las funciones de pertenecia y el peso de las reglas para mejorar el comportamiento de un controlador difuso. Dichos procesos de optimización se han realizado utilizando “ROS” y “Matlab Simulink” para obtener mejores resultados para la evitación de colisiones con vehículos aéreos no tripulados. Ésta Tesis demuestra que los controladores implementados con lógica difusa son altamente capaces de controlador sistemas sin tener en cuenta el modelo del vehículo a controlador en entornos altamente perturbables con un sensor de bajo coste como es una cámara. El ruido presentes causado por los cambios de iluminación en la adquisición de imágenes y la alta incertidumbre en la detección visual han sido manejados satisfactoriamente por ésta técnica de de “Soft-Computing” para distintas aplicaciones tanto con vehículos aéreos como terrestres.

Applications of image-based, multi-view stereo reconstruction methods = (Aplicaciones de los métodos de reconstrucción estéreo multivista)

These slides present several 3-D reconstruction methods to obtain the geometric structure of a scene that is viewed by multiple cameras. We focus on the combination of the geometric modeling in the image formation process with the use of standard optimization tools to estimate the characteristic parameters that describe the geometry of the 3-D scene. In particular, linear, non-linear and robust methods to estimate the monocular and epipolar geometry are introduced as cornerstones to generate 3-D reconstructions with multiple cameras. Some examples of systems that use this constructive strategy are Bundler, PhotoSynth, VideoSurfing, etc., which are able to obtain 3-D reconstructions with several hundreds or thousands of cameras. En esta presentación se tratan varios métodos de reconstrucción 3-D para la obtención de la estructura geométrica de una escena que es visualizada por varias cámaras. Se enfatiza la combinación de modelado geométrico del proceso de formación de la imagen con el uso de herramientas estándar de optimización para estimar los parámetros característicos que describen la geometría de la escena 3-D. En concreto, se presentan métodos de estimación lineales, no lineales y robustos de las geometrías monocular y epipolar como punto de partida para generar reconstrucciones con tres o más cámaras. Algunos ejemplos de sistemas que utilizan este enfoque constructivo son Bundler, PhotoSynth, VideoSurfing, etc., los cuales, en la práctica pueden llegar a reconstruir una escena con varios cientos o miles de cámaras.

Autonomous Landing of an Unmanned Aerial Vehicle using Image-Based Fuzzy Control

This paper presents a vision based autonomous landing control approach for unmanned aerial vehicles (UAV). The 3D position of an unmanned helicopter is estimated based on the homographies estimated of a known landmark. The translation and altitude estimation of the helicopter against the helipad position are the only information that is used to control the longitudinal, lateral and descend speeds of the vehicle. The control system approach consists in three Fuzzy controllers to manage the speeds of each 3D axis of the aircraft s coordinate system. The 3D position estimation was proven rst, comparing it with the GPS + IMU data with very good results. The robust of the vision algorithm against occlusions was also tested. The excellent behavior of the Fuzzy control approach using the 3D position estimation based in homographies was proved in an outdoors test using a real unmanned helicopter.

Image recognition: Visual grouping, recognition, and learning

Vision extracts useful information from images. Reconstructing the three-dimensional structure of our environment and recognizing the objects that populate it are among the most important functions of our visual system. Computer vision researchers study the computational principles of vision and aim at designing algorithms that reproduce these functions. Vision is difficult: the same scene may give rise to very different images depending on illumination and viewpoint. Typically, an astronomical number of hypotheses exist that in principle have to be analyzed to infer a correct scene description. Moreover, image information might be extracted at different levels of spatial and logical resolution dependent on the image processing task. Knowledge of the world allows the visual system to limit the amount of ambiguity and to greatly simplify visual computations. We discuss how simple properties of the world are captured by the Gestalt rules of grouping, how the visual system may learn and organize models of objects for recognition, and how one may control the complexity of the description that the visual system computes.

Targetless image-based method for measuring displacements and strains on concrete surfaces with a consumer camera

Measurement of concrete strain through non-invasive methods is of great importance in civil engineering and structural analysis. Traditional methods use laser speckle and high quality cameras that may result too expensive for many applications. Here we present a method for measuring concrete deformations with a standard reflex camera and image processing for tracking objects in the concretes surface. Two different approaches are presented here. In the first one, on-purpose objects are drawn on the surface, while on the second one we track small defects on the surface due to air bubbles in the hardening process. The method has been tested on a concrete sample under several loading/unloading cycles. A stop-motion sequence of the process has been captured and analyzed. Results have been successfully compared with the values given by a strain gauge. Accuracy of our methods in tracking objects is below 8 μm, in the order of more expensive commercial devices.

City appearance and the law : a manual to assist in the development of ordinance-based visual improvement programs in smaller cities /

Includes bibliography.