WSCG '2017: Short Papers Proceedings
Permanent URI for this collection
Browse
Recent Submissions
Item OpenLensFlare: an open-source, lens flare designing and rendering framework(Václav Skala - UNION Agency, 2017) Coba, István; Skala, VáclavLens flare rendering in computer games has always been lacking. While physically motivated solutions based on real camera systems exist, their inherent complexity makes them inappropriate for widespread use. Developers are not trained to work with these complicated imaging systems, and even if they were, artists and designers prefer intuitive parameters over these complicated optical system descriptions. More support is needed to start adopting to these advanced models, and to show that with an appropriate tool the situation can be vastly improved. This paper describes OpenLensFlare, an open-source C++ framework for rendering convincing physically-based lens flare effects. Additionally, a supporting optical system editor is also provided, which is capable of producing and visualizing optical systems and showing an example usage of the run-time library. Together, these two systems can be used to replace the existing naive algorithms, with small effort and low integration complexity.
Item CoUIM: crossover user interface model for inclusive computing(Václav Skala - UNION Agency, 2017) Almurayh, Abdullah; Semwal, Sudhanshu Kumar; Skala, VáclavPersons with disabilities can face considerable challenges accessing many computing systems, such as cloud computing. We created six low-cost user interfaces using: keyboard-based, touchable, speech-based, touch-less gesture, tactile, and then combined them all in one user interface termed Crossover User Interface Model (CoUIM). We measured inclusiveness, error occurrence, user performance, and user satisfaction though an IRB approved study of twenty-nine participants. We chose Xen cloud platform to evaluate our research. We focused on three groups of users: persons with no disability, persons with blind and visually impairment (B/VI), and persons with motor-impairment. When we combined several interactions in one user interface, results improved for persons with disability. Using CoUIM improved inclusiveness, error rate, user performance and even user satisfaction. Persons with motor disability needed a little more time to complete the same tasks in our study. In particular, we show that persons with blind and visually impairment (B/VI) can compete on equal footing with their sighted peers based on error rate and time to complete the tasks using CoUIM.Item Extraction of sliding collision area of knee-form for automobile safety inspections(Václav Skala - UNION Agency, 2017) Inui, Masatomo; Gunji, Kenta; Umezu, Nobuyuki; Skala, VáclavThe United Nations Economic Commission for Europe defines a safety regulation based on the possible collision between the driver’s knee and an automobile’s interior parts. The “knee-form” apparatus is used to evaluate compliance with this regulation. Current software for analyzing possible collisions of the knee-form is not applicable to the part whose surface is vertical and near parallel to the knee-form approaching direction. In this paper, we propose a novel algorithm named “push-and-slide” for extracting the knee-form colliding area on the console part and door panel. In the first step of the algorithm, the target surface of the part is transformed to gridlike points in a high resolution. The knee-form models in various positions and orientations are prepared in the second step. Each knee-form model is pushed to the grid-like points. The model is then moved along the part surface to detect possible collisions between the knee-form and the grid-like points. An experimental system is developed and some computational experiments are performed.Item Improving the ergonomics of hand tracking inputs to VR HMD’s(Václav Skala - UNION Agency, 2017) Devine, Scott; Nicholson, Chris; Rafferty, Karen; Herdman, Chris; Skala, VáclavThis study improves the ergonomics of using the Leap Motion hand tracking device with an Oculus Rift. The improvements were realised through the use of a 3D printed mount that angled the Leap Motion down by 30 degrees. This allowed for users to interact with a virtual environment in which their arms may be held in a biomechanically less stressful location, rather than up and in front of their face. To validate the configuration, 15 participants completed a specially designed task which involved pressing virtual buttons in a given location. The button pressing task was performed in three configurations that compared the angled mount against the standard forward facing mount. Results indicate that the angled mount eliminates tracking loses, whilst producing comparable accuracy against the control condition and allowing the participant to interact in a more natural arm posture.Item Support vector machine optimized by firefly algorithm for emphysema classification in lung tissue CT images(Václav Skala - UNION Agency, 2017) Tuba, Eva; Tuba, Milan; Simian, Dana; Skala, VáclavDigital images and digital image processing facilitated significant progress in numerous areas where medicine is an important one of them. Computer-aided detection and diagnostics systems are used to assist specialists in interpretation of medical digital images. One of the important research issues is detection and classification of the chronic obstructive pulmonary disease in lung CT images. In this paper we proposed a method for emphysema classification based on texture and intensity features. Only six different characteristics of the uniform local binary pattern and intensity histogram were used as input vector for support vector machine that was used as classifier. Feature vector was significantly reduced compared to the other state-of-the-art methods while the classification accuracy was increased. On images from standard dataset global accuracy of our proposed algorithm was 98.18% compared to 95.24% and 93.9% of two other compared algorithms.Item MAELab: a framework to automatize landmark estimation(Václav Skala - UNION Agency, 2017) Le Van, Linh; Beurton-Aimar, Marie; Krahenbuhl, Adrien; Parisey, Nicolas; Skala, VáclavIn biology, the morphometric analysis is widely used to analyze the inter-organisms variations. It allows to classify and to determine the evolution of an organism’s family. The morphometric methods consider features such as shape, structure, color, or size of the studied objects. In previous works [8], we have analyzed beetle mandibles by using the centroid as feature, in order to classify the beetles. We have shown that the Probabilistic Hough Transform (PHT) is an efficient unsupervised method to compute the centroid. This paper proposes a new approach to precisely estimate the landmark geometry, points of interest defined by biologists on the mandible contours. In order to automatically register the landmarks on different mandibles, we defined patches around manual landmarks of the reference image. Each patch is described by computing its SIFT descriptor. Considering a query image, we apply a registration step performed by an Iterative Principal Component Analysis which identify the rotation and translation parameters. Then, the patches in the query image are identified and the SIFT descriptors computed. The biologists have collected 293 beetles to provide two sets of mandible images separated into left and right side. The experiments show that, depending on the position of the landmarks on the mandible contour, the performance can go up to 98% of good detection. The complete workflow is implemented in the MAELab framework, freely available as library on GitHub.Item fastGCVM: a fast algorithm for the computation of the discrete generalized cramér-von mises distance(Václav Skala - UNION Agency, 2017) Meyer, Johannes; Längle, Thomas; Beyerer, Jürgen; Skala, VáclavComparing two random vectors by calculating a distance measure between the underlying probability density functions is a key ingredient in many applications, especially in the domain of image processing. For this purpose, the recently introduced generalized Cramér-von Mises distance is an interesting choice, since it is well defined even for the multivariate and discrete case. Unfortunately, the naive way of computing this distance, e.g., for two discrete two-dimensional random vectors ˜x; ˜y 2 [0; : : : ;n1]2;n 2 N has a computational complexity of O(n5) that is impractical for most applications. This paper introduces fastGCVM, an algorithm that makes use of the well known concept of summed area tables and that allows to compute the generalized Cramér-von Mises distance with a computational complexity of O(n3) for the mentioned case. Two experiments demonstrate the achievable speed up and give an example for a practical application employing fastGCVM.Item Screen-space ambient occlusion for light field displays(Václav Skala - UNION Agency, 2017) Doronin, Oleksii; Kara, Peter A.; Barsi, Attila; Martini, Maria G.; Skala, VáclavIn this paper, we discuss the challenge of generating the screen-space ambient occlusion (SSAO) visual effect on the state-of-the-art HoloVizio light field display. We detail the main features of modern SSAO techniques that are currently being applied during visualization on conventional 2D displays, and describe difficulties that potentially can appear when implementing this visual effect on 3D light field or similar systems. The main contribution of this paper is our own modification of the SSAO algorithm for light field displays. The paper also includes suggestions on the possible ways to improve its visual quality and performance.Item CUDA-based SeqSLAM for real-time place recognition(Václav Skala - UNION Agency, 2017) Ouerghi, Safa; Boutteau, Remi; Tlili, Fethi; Savatier, Xavier; Skala, VáclavVehicle localization is a fundamental issue in autonomous navigation that has been extensively studied by the Robotics community. An important paradigm for vehicle localization is based on visual place recognition which relies on learning a database, then consecutively trying to find matchings between this database and the actual visual input. An increasing interest has been directed to visual place recognition in varying conditions like day and night cycles and seasonal changes. A major approach dealing with such challenges is Sequence SLAM (SeqSLAM) based on matching a sequence of images to the database instead of a single image. This algorithm allows global pose recovery at the expense of a higher computational time. To solve this problem with a certain amount of speedup, we propose in this work, a CUDA-based solution for real-time place recognition with SeqSLAM. We design a mapping of SeqSLAM to CUDA architecture and we describe, in detail, our hardware-specific implementation considerations as well as the parallelization methods. Performance analysis against existing CPU implementation is also given, showing a speedup to six times faster than the CPU for common sized databases. More speedup could be obtained when dealing with bigger databases.Item Volume estimation of biomedical objects described by multiple sets of non-trimmed Bézier triangles(Václav Skala - UNION Agency, 2017) Sisojevs, Aleksandrs; Kovalovs, Mihails; Krutikova, Olga; Skala, VáclavEstimating the volume of a 3D model of an object is an actual task in many scientific and engineering fields (for example, CAD systems, biomedical engineering tasks etc.). Spline surfaces is one of the most powerful and flexible methods used to describe a 3D model. At the same time, it is rather difficult to estimate the volume of an object described by spline surfaces. A model of a Bézier triangle is a simple type of a spline surface, but it is practically advantageous. This paper describes a method of estimating the volume for 3D objects that are described by a set of Bézier triangles. The proposed method was tested on 3D models of objects of biomedical origin. A theorem is presented in this paper for volume estimation, based on different properties of researched models, acquired by a projection of a set vertices of a Bézier triangle onto a coordinate system axis. The proposed approach is based on using methods of differential geometry: surface integrals of scalar fields, Euler’s integral of the first kind and Beta functions. Experimental results prove the accuracy of presented theorems. The proposed method can be successfully used to calculate the volume of different 3D models, including objects of biomedical origin.Item Parameterization of unorganized cylindrical point clouds for least squares B-spline surface fitting(Václav Skala - UNION Agency, 2017) Moon, Seonghyeon; Park, Jin-Eon; Ko, Kwanghee; Skala, VáclavIn this study, a method for parameterizing unorganized cylindrical point clouds is suggested. The proposed method creates an initial base surface onto which points are projected to estimate parameter values for each point. To produce an initial base surface, we suggest the concept of a virtual turntable and apply multilevel B-splines. Grid points are projected to the point cloud to increase the accuracy of the initial base surface. During the projection process, a modified weight factor is introduced. Lastly, global B-spline surface interpolation is executed to generate an initial base surface, which undergoes a process of refinement and relaxation. Parameter values are then obtained by projecting the point cloud onto the surface orthogonally. Experiments show that the proposed method successfully estimates parameters and solves the problems of self-loop and crossover. Furthermore, the results of experiment show that the proposed weight factor is more effective than the existing weight factor for point directed projection.Item Anisotropic octrees: a tool for fast normals estimation on unorganized point clouds(Václav Skala - UNION Agency, 2017) Ravaglia, Joris; Bac, Alexandra; Fournier, Richard A.; Skala, VáclavWith the recent advances in remote sensing of objects and environments, point cloud processing has become a major field of study. Three-dimensional point cloud collected with remote sensing instruments may be very large, containing up to several tens of billions of points. This imposes the use for efficient and automatic algorithms to extract geometric or structural elements of the scanned surfaces. In this paper, we focus on the estimation of normal directions in an unorganized point cloud and provide a curvature indicator. We avoid point-wise operations to accelerate the running time for normals estimation. Instead, our method rely on an innovative anisotropic partitioning of the point cloud using an octree structure guided by the geometric complexity of the data and generates patches of points. These patches are then approximated by a quadratic surface in order to estimate the normal directions and curvatures. Our method has been applied to six models of various types presenting different characteristics and performs, in average, 2.65 times faster than multi-threads implementations available in current pieces of software. The results obtained are a compromise between running time efficiency and normals accuracy. Moreover, this work opens up promising perspectives and can be easily inserted in wide range of workflows.Item Unlimited object instancing in real-time(Václav Skala - UNION Agency, 2017) Jabłoński, Szymon; Martyn, Tomasz; Skala, VáclavIn this paper, we propose a novel approach to efficient rendering of an unlimited number of 3D objects in real-time. We present a rendering pipeline that is based on a new computer graphics programming paradigm implementing a holistic approach to the virtual scene definition. Using Signed Distance Functions (SDF) for a virtual scene representation, we managed to control the content and complexity of the virtual scene with the use of mathematical equations. In order to solve the limited hardware problem, especially the limited capacity of the GPU memory, we propose a scene element repository which extends the idea of the data based amplification. The content of the repository strongly depends on a 3D object visualization method. One of the most important requirements of the developed pipeline is the possibility to render 3D objects created by artists. In order to achieve that, the object visualization method uses Sparse Voxel Octree (SVO) ray casting. The developed rendering pipeline is fully compatible with the available SVO algorithms. We show how to avoid occlusion errors which can occur in the SDF and SVO integration single-pass rendering pipeline. Finally, in order to control the content and complexity of the virtual scenes in an unlimited way, we propose a collection of global operators applicable to the virtual scene distance function. Developed Unlimited Object Instancing rendering pipeline can be easily integrated with traditional visualization methods, e.g. the triangle rasterization. The only hardware requirement for our approach is the support for compute shaders or any GPGPU API.Item Automatic plant recognition system for challenging natural plant species(Václav Skala - UNION Agency, 2017) Kazerouni, Masoud Fathi; Schlemper, Jens; Kuhnert, Klaus-Dieter; Skala, VáclavPhotosynthesis is one of turning points to shape the world. Plants use this process to convert light energy into chemical energy. Some of the early microorganisms evolved a way to use the energy from sunlight to make sugar out of simpler molecules, but unlike green plants today, the first photosynthesizing organisms did not release oxygen as waste product, so there was no oxygen in the air. Plants are very busy factories and leaves are the main place for production. A useful plant recognition system is capable of identification of different species in natural environment. In natural environment, plants and leaves grow in different regions and climates. During day, variation of light intensity can be considered as an important factor. Thus, recognition of species in different conditions is a real need as plants are ubiquitous in human life. A dataset of natural images has been utilized. The dataset contains four different plant species of Siegerland, Germany. Modern combined description algorithms, SURF, FAST-SURF, and HARRIS-SURF, have been carried out to implement a reliable system for plants species recognition and classification in natural environment. One of well known methods in machine learning community, Support Vector Machine, has been applied in the implemented systems. All steps of system’s implementation are described in related sections. The highest obtained accuracy belongs to the implemented system by means of SURF algorithm and equals to 93.9575.Item Line segment similarity criterion for vector images(Václav Skala - UNION Agency, 2017) Jelínek, Aleš; Žalud, Luděk; Skala, VáclavVector representation of the images, maps, schematics and other information is widely used, and in computer processing of these data, comparison and similarity evaluation of two sets of line segments is often necessary. Various techniques are already in use, but these mostly rely on the algorithmic functions such as minimum/maximum of two or more variables, which limits their applicability for many optimization algorithms. In this paper we propose a novel area based criterion function for line segment similarity evaluation, which is easily differentiable and the derivatives are continuous in the whole domain of definition. The second important feature is the possibility of preprocessing of the input data. Once finished, it takes constant time to evaluate the criterion for different transformations of one of the input sets of line segments. This has potential to greatly speed up iterative matching algorithms. In such case, the computational complexity is reduced from O(pt) to O(p+t), where p is the number of line segment pairs being examined and t is the number of transformations performed.Item Application of vision-based particle filter and visual odometry for UAV localization(Václav Skala - UNION Agency, 2017) Jurevičius, Rokas; Marcinkevičius, Virginijus; Skala, VáclavConventional UAV (abbr. Unmanned Air Vehicle) auto-pilot systems uses GPS signal for navigation. While the GPS signal is lost, jammed or the UAV is navigating in GPS-denied environment conventional autopilot systems fail to navigate safely. UAV should estimate it’s own position without the need of external signals. Localization, the process of pose estimation relatively to known environment, may solve the problem of navigation without GPS signal. Downward looking camera on a UAV may be used to solve pose estimation problem in combination with visual odometry and other sensor data. In this paper a vision-based particle filter application is proposed to solve GPS-denied UAV localization. The application uses visual odometry for motion estimation, correlation coefficient for apriori known map image matching with aerial imagery, KLD (abbr. Kueller-Leiblach distance) sampling for particle filtering. Research using data collected during real UAV flight is performed to investigate: UAV heading influence on correlation coefficient values when matching aerial imagery with the map and measure localization accuracy compared to conventional GPS system and state-of-the-art odometry.Item Using genetic algorithms to estimate local shape parameters of RBFs(Václav Skala - UNION Agency, 2017) Bohdal, Róbert; Bohdalová, Mária; Kohnová, Silvia; Skala, VáclavEstimation of design rainfall in unobservable places is important in hydrological engineering. The aim of this paper is to use genetic algorithms to find the optimal global and local shape parameters of radial basis functions (RBFs) to create an interpolation model to estimate scaling exponents of short term rainfalls across selected regions of Slovakia. Scaling exponents can be used later to estimate rainfalls intensity in places without observations. In this paper, we have used interpolation methods based on RBFs to model interpolation surfaces. We investigate the properties of shape parameters in RBFs, and we test some methods for finding an optimal shape parameter. The choice of the best basis function along with the optimal shape parameter has a significant impact on the accuracy of the interpolation models which best approximate the real model. We have found that Hardy’s multiquadrics interpolant with the optimal local shape parameters can be used for estimation the rainfall intensities in areas without direct observation.Item A method of core wire extraction from point cloud data of rebar(Václav Skala - UNION Agency, 2017) Nishio, Koji; Nakamura, Noriyoshi; Muraki, Yuta; Kobori, Ken-ichi; Skala, VáclavIn recent years, reinforced concrete has been widely used as a building material having high strength. However, when the arrangement of the reinforcing bars embedded in the inside are not correct, there is a problem that the strength drops greatly. Therefore, when use reinforced concrete, it is necessary to confirm whether the reinforcing bars are correctly arranged. In this paper, we propose a method of thinning of point clouds scanned by range scanner from reinforcing bars, and extracting the core wires of point clouds by introducing a concentration distribution function. This process moves points according to a gradient field of a concentration field. In addition, we conducted an experiment to confirm the effectiveness of the proposed method. As a result of the experiment, it was confirmed that the core wires can be extracted from the point clouds of the reinforcing bars.Item Human action recognition in videos: a comparative evaluation of the classical and velocity adaptation space-time interest points techniques(Václav Skala - UNION Agency, 2017) Almeida, Ana Paula G S de; Espinoza, Bruno Luiggi M.; Barros Vidal, Flavio de; Skala, VáclavHuman action recognition is a topic widely studied over time, using numerous techniques and methods to solve a fundamental problem in automatic video analysis. Basically, a traditional human action recognition system collects video frames of human activities, extracts the desired features of each human skeleton and classify them to distinguish human gesture. However, almost all of these approaches roll out the space-time information of the recognition process. In this paper we present a novel use of an existing state-of-the-art space-time technique, the Space-Time Interest Point (STIP) detector and its velocity adaptation, to human action recognition process. Using STIPs as descriptors and a Support Vector Machine classifier, we evaluate four different public video datasets to validate our methodology and demonstrate its accuracy in real scenarios.Item Efficient pose deformations for human models in customized sizes and shapes(Václav Skala - UNION Agency, 2017) Zhu, Shuaiyin; Mok, P. Y.; Skala, VáclavModelling dynamic pose deformations of human subjects is an important topic in many research applications. Existing approaches of human pose deformations can be classified as volume-based, skeletal animation and example-based methods. These approaches have both strengths and limitations. However, for models in customized shapes, it is very challenging to deform these models into different poses rapidly and realistically. We 10 propose a conceptual model to realize rapid and realistic pose deformation to customized human models by the integration of skeletal-driven rigid deformation and example-learnt non-rigid surface deformation. Based on this framework, a method for rapid automatic pose deformation is developed to deform human models of various body shapes into a series of dynamic poses. A series of algorithms are proposed to complete the pose deformation automatically and efficiently, including automatic segmentation of body parts and skeleton embedding, skeletal15 driven rigid deformation, training of non-rigid deformation from pose dataset; shape mapping of non-rigid deformation, and integration of rigid and non-rigid deformations. Experiment has shown that the proposed method can customize accurate human models based on two orthogonal-view photos and also efficiently generate realistic pose deformations for the customized models.
