44 results
Search Results
Now showing 1 - 10 of 44
Item User-reconfigurable CAD Feature Recognition in 1- and 2-topologies with Reduction of Search Space via Geometry Filters(The Eurographics Association, 2019) Corcho, Juan Camilo Pareja; Acosta, Oscar Mauricio Betancur; Ruiz, Oscar E.; Cadavid, Carlos; Casas, Dan and Jarabo, AdriánIn the context of Computer-Aided Design and Manufacturing, the problem of feature recognition plays a key role in the integration of systems. Until now, compromises have been reached by only using FACE-based geometric information of prismatic CAD models to prune the search domain. This manuscripts presents a feature recognition method which more aggressively prunes the search space with reconfigurable geometric tests. This reconfigurable approach allows to enforce arbitrary confluent tests which are topologic and geometric, with enlarged domain. The test sequence is itself a graph (i.e. not a linear or total-order sequence). Unlike the existing methods which are FACE-based, the present one permits combinations of topologies whose dimensions are 2, 1 or 0. This system has been implemented in an industrial environment. The industrial incarnation allows industry-based customization and is faster when compared to topology-based feature recognition. Future work is required in improving robustness of search conditions and improving the graphic input interface.Item Cylindrical Transform Slicing of Revolute Parts with Overhangs for Laser Metal Deposition(The Eurographics Association, 2022) Montoya-Zapata, Diego; Moreno, Aitor; Ortiz, Igor; Ruiz-Salguero, Oscar; Posada, Jorge; Posada, Jorge; Serrano, AnaIn the context of Laser Metal Deposition (LMD), temporary support structures are needed to manufacture overhanging features. In order to limit the need for supports, multi-axis machines intervene in the deposition by sequentially repositioning the part. Under multi-axis rotations and translations, slicing and toolpath generation represent significant challenges. Slicing has been partially addressed by authors in multi-axis LMD. However, tool-path generation in multi-axis LMD is rarely touched. One of the reasons is that the required slices for LMD may be strongly non-developable. This fact produces a significant mismatch between the tool-path speeds and other parameters in Parametric space vs. actual Euclidean space. For the particular case of developable slices present in workpieces with cylindrical kernel and overhanging neighborhoods, this manuscript presents a methodology for LMD tool path generation. Our algorithm takes advantage of existing cylindrical iso-radial slicing by generating a path in the (?, z) parameter space and isometrically translating it into the R3 Euclidean space. The presented approach is advantageous because it allows the path-planning of complex structures by using the methods for conventional 2.5-axis AM. Our computer experiments show that the presented approach can be effectively used in manufacturing industrial/mechanical pieces (e.g., spur gears). Future work includes the generation of the machine g-code for actual LMD equipment.Item Recognising Specific Foods in MRI Scans Using CNN and Visualisation(The Eurographics Association, 2020) Gardner, Joshua; Al-Maliki, Shatha; Lutton, Évelyne; Boué, François; Vidal, Franck; Ritsos, Panagiotis D. and Xu, KaiThis work is part of an experimental project aiming at understanding the kinetics of human gastric emptying. For this purpose magnetic resonance imaging (MRI) images of the stomach of healthy volunteers have been acquired using a state-of-art scanner with an adapted protocol. The challenge is to follow the stomach content (food) in the data. Frozen garden peas and petits pois have been chosen as experimental proof-of-concept as their shapes are well defined and are not altered in the early stages of digestion. The food recognition is performed as a binary classification implemented using a deep convolutional neural network (CNN). Input hyperparameters, here image size and number of epochs, were exhaustively evaluated to identify the combination of parameters that produces the best classification. The results have been analysed using interactive visualisation. We prove in this paper that advances in computer vision and machine learning can be deployed to automatically label the content of the stomach even when the amount of training data is low and the data imbalanced. Interactive visualisation helps identify the most effective combinations of hyperparameters to maximise accuracy, precision, recall and F1 score, leaving the end-user evaluate the possible trade-off between these metrics. Food recognition in MRI scans through neural network produced an accuracy of 0.97, precision of 0.91, recall of 0.86 and F1 score of 0.89, all close to 1.Item Immersive WebXR Data Visualisation Tool(The Eurographics Association, 2023) Ogbonda, Ebube Glory; Vangorp, Peter; Hunter, DavidThis paper presents a study of a WebXR data visualisation tool designed for the immersive exploration of complex datasets in a 3D environment. The application developed using AFrame, D3.js, and JavaScript enables an interactive, device-agnostic platform compatible with various devices and systems. A user study is proposed to assess the tool's usability, user experience, and mental workload using the NASA Task Load Index (NASA TLX). The evaluation is planned to employ questionnaires, task completion times, and open-ended questions to gather feedback and insights. The anticipated results aim to provide insights into the effectiveness of the application in supporting users in understanding and extracting insights from complex data while delivering an engaging and intuitive experience. Future work will refine and expand the tool's capabilities by exploring interaction guidance, visualisation layout optimisation, and long-term user experience assessment. This research contributes to the growing field of immersive data visualisation and informs future tool design.Item Visualizing Usage Data from a Diabetes Management System(The Eurographics Association, 2020) Duce, David A.; Martin, Clare; Russell, Alex; Brown, Dan; Aldea, Arantza; Alshaigy, Bedour; Harrison, Rachel; Waite, Marion; Leal, Yenny; Wos, Marzena; Fernandez-Balsells, Mercè; Real, José Manuel Fernández; Nita, Lucian; López, Beatriz; Massana, Joaquim; Avari, Parizad; Herrero, Pau; Jugnee, Narvada; Oliver, Nick; Reddy, Monika; Ritsos, Panagiotis D. and Xu, KaiThis article explores the role for visualization in interpreting data collected by a customised analytics framework within a healthcare technology project. It draws on the work of the EU-funded PEPPER project, which has created a personalised decision-support system for people with type 1 diabetes. Our approach was an exercise in exploratory visualization, as described by Bergeron's three category taxonomy. The charts revealed different patterns of interaction, including variability in insulin dosing schedule, and potential causes of rejected advice. These insights into user behaviour are of especial value to this field, as they may help clinicians and developers understand some of the obstacles that hinder the uptake of diabetes technology.Item Medical Ultrasound Training in Virtual Reality(The Eurographics Association, 2020) Elliman, James P.; Bethapudi, Sarath; Koulieris, George Alex; Ritsos, Panagiotis D. and Xu, KaiIn this work we propose a novel training solution for learning and practising the core psychomotor skills required in Diagnostic Ultrasound examinations with a computer-based simulator. This is in response to the long-standing challenges faced by educators in providing regular training opportunities as a shortage of equipment, staff unavailability and cost, hamper the current training model. We propose an alternative, VR-based model with a highly realistic 3D environment. To further realism of the experience, 3D printed props that work in conjunction with the simulation software will be designed. Our approach further extends previous work in generative model-based US simulation by developing a ray-tracing algorithm for use with the recently released NVidia RTX technology.Item Towards Ceramics Inspired Physiotherapy for Recovering Stroke Patients(The Eurographics Association, 2023) Hajzer, Sándor P.; Jones, Andra; Jones, David E.; Miles, Helen C.; Ellis, Victoria; Povina, Federico V.; Sganga, Magalí; Swain, Martin T.; Bennett-Gillison, Sophie; Vangorp, Peter; Hunter, DavidPeople prescribed physiotherapy exercises can struggle to engage with exercises due to a lack of mental stimulation in the repetitive tasks. The introduction of VR to motion-based physiotherapy can be beneficial, however, currently available physiotherapy applications are focused on gaming and the gamification of physiotherapy, something that will not appeal to all patients. This project presents work in-progress towards a VR ceramics painting inspired physiotherapy application, where patients are guided to perform a series of simple motion exercises under the supervision of physiotherapists. Literature shows that art-based therapy can improve patient outcome, and ceramics involves a range of 3D movements that can be aligned with physiotherapy exercises. The work presented is intended to inform future research and development efforts.Item Using The Barnes-Hut Approximation for Fast N-Body Simulations in Computer Graphics(The Eurographics Association, 2023) Dravecky, Peter; Stephenson, Ian; Vangorp, Peter; Hunter, DavidParticle systems in CG often encounter performance issues when all the particles rely on mutual influence, producing an O(N2) performance. The Barnes-Hut approximation is used in the field of astrophysics to provide sufficiently accurate results in O(Nlog(N)) time. Here we explore a hardware accelerated implementation of this algorithm, implemented within SideFX Houdini - the commercial tool typically used for particle work in film. We are able to demonstrate a workflow with integrates into the existing artist friendly environment, with performance improved by orders of magnitudes for typically large simulations, and negligible visual change in results.Item Perfect Spatial Hashing for Point-cloud-to-mesh Registration(The Eurographics Association, 2019) Mejia-Parra, Daniel; Lalinde-Pulido, Juan; Sánchez, Jairo R.; Ruiz-Salguero, Oscar; Posada, Jorge; Casas, Dan and Jarabo, AdriánPoint-cloud-to-mesh registration estimates a rigid transformation that minimizes the distance between a point sample of a surface and a reference mesh of such a surface, both lying in different coordinate systems. Point-cloud-to-mesh-registration is an ubiquitous problem in medical imaging, CAD CAM CAE, reverse engineering, virtual reality and many other disciplines. Common registration methods include Iterative Closest Point (ICP), RANdom SAmple Consensus (RANSAC) and Normal Distribution Transform (NDT). These methods require to repeatedly estimate the distance between a point cloud and a mesh, which becomes computationally expensive as the point set sizes increase. To overcome this problem, this article presents the implementation of a Perfect Spatial Hashing for point-cloud-to-mesh registration. The complexity of the registration algorithm using Perfect Spatial Hashing is O(NYxn) (NY : point cloud size, n: number of max. ICP iterations), compared to standard octrees and kd-trees (time complexity O(NY log(NT)xn), NT : reference mesh size). The cost of pre-processing is O(NT +(N3H )2) (N3H : Hash table size). The test results show convergence of the algorithm (error below 7e-05) for massive point clouds / reference meshes (NY = 50k and NT = 28055k, respectively). Future work includes GPU implementation of the algorithm for fast registration of massive point clouds.Item Where's Wally? A Machine Learning Approach(The Eurographics Association, 2021) Barthelmes, Tobias; Vidal, Franck; Xu, Kai and Turner, MartinObject detection has been implemented in all sorts of real-life scenarios such as facial recognition, traffic monitoring and medical imaging but the research that has gone into object detection in drawings and cartoons is not nearly as extensive. The Where's Wally puzzle books give a good opportunity to implement some of these real-life methods into the fictional world. The Wally detection framework proposed is composed of two stages: i) a Haar-cascade classifier based on the Viola-Jones framework, which detects possible candidates from a scenario from the Where'sWally books, and ii) a lightweight convolutional neural network (CNN) that re-labels the objects detected by the cascade classifier. The cascade classifier was trained on 85 positive images and 172 negative images. It was then applied to 12 test images, which produced over 400 false positives. To increase the accuracy of the models, hard negative mining was implemented. The framework achieved a recall score of 84.61% and an F1 score of 78.54%. Improvements could be made to the training data or the CNN to further increase these scores.