WSCG 2015: Poster Papers Proceedings
Permanent URI for this collection
Browse
Recent Submissions
Item Computer graphics and vision labs in Argentina(Václav Skala - UNION Agency, 2015) Giusti, Armando de; Abásolo, María José; Naiouf, Marcelo; Skala, VáclavThis article describes the Computer Graphics and Vision research that are being developed by three universities’ laboratories in Argentina: III-LIDI Institute of Computing Research at National University of La Plata, VyGLab Visualization and Computer Graphics Laboratory at South National University, and CGLab Computer Graphics Laboratory at National University of San Luis.
Item Signal and image processing in the Center of Cuba: center for studies on electronics and information technologies (CEETI)(Václav Skala - UNION Agency, 2015) Ferrer, Carlos A.; Taboada-Crispí, Alberto; Lorenzo-Ginori, Juan V.; Skala, VáclavA brief description of CEETI is given, addressing its history, research lines, main scientific results and current projects.Item Building 3D object representation using SURF local features(Václav Skala - UNION Agency, 2015) Jaszuk, Marek; Szostek, Grażyna; Starzyk, Janusz A.; Skala, VáclavThe paper discusses an approach to create 3D representation of physical objects. The aim is creating a visual representation of an object, which allows for robust recognition, irrespectively of the distance and the direction of observation. The approach uses a set of rotational views of an object, which are transformed into a set of keypoints using the SURF visual feature detector. The key points are then collected to build a 3D model of the object. Such representation allows both for recognizing the objects based on local characteristics, and distinguishing different global geometry transformations that are needed to recognize the object in its 3D environment.Item Feature based assessment of forming force behavior in incremental sheet forming(Václav Skala - UNION Agency, 2015) Priyadarshi, Satwik; Jain, Prashant K.; Roy, J. J.; Skala, VáclavForming forces and their behavior plays an important role in defining the mechanism of any sheet metal forming process. In Incremental sheet forming, due to inherent complexities, study of forming force behavior is a challenging task. In absence of geometry independent techniques, only studies specific to certain axisymmetric and planer symmetric geometries are available. Present work deals with development of a novel methodology for the study of behavior of forming forces in geometries with multiple features by mapping components of forming forces obtained with dynamometer readings to spatial coordinates of tool path coordinates. Techniques such as Nearest Neighbor Search, RANSAC and calculation of l2 norm are employed for this very purpose.Item Hough transform for the calculation of twist angle of aramid torsion(Václav Skala - UNION Agency, 2015) Perechesova, A. D.; Soloveva, G. A.; Kalapyshina, I. I.; Skala, VáclavAramid yarns are widely used for various technical applications. For example, they are used for creation of a magnetosensitive element of the torsion magnetometer, which is a part of the geophysical complex GI-MTS-1 (SPbF IZMIRAN). Such element is made of three microfilaments of aramid yarn. Study of such physicalmechanical characteristics of yarns as tensile, shear and torsion moduli, is necessary for improvement torsion magnetometer. This paper describes the preparatory phase of experimental study of yarn twist angle variation during tensile test. It includes equipment description, in particular, description of the scheme of video capture, and developed computer vision algorithm for determining an aramid torsion slope angles. Proposed scheme of video capture includes high-speed camera and allows precise focusing due to two-coordinate platform and avoiding of optical distortions. A special computer vision algorithm, which based on the Hough transform, was developed. This algorithm was tested on torsion images obtained with digital microscope. The algorithm works with different real yarns regardless of their color and twist type.Item Statistical solution of 3D transformation problem(Václav Skala - UNION Agency, 2015) Marek, Jaroslav; Rak, Josef; Jetensky, Pavel; Skala, VáclavObtaining the 3D model of an object is currently one of the most important issues that image processing is dealing with. Measurement of the points on 3D objects requires different scans from different positions in different coordinate systems. At our disposal are measured coordinates of an identical point, which can be obtained from a laser 3D scanner, depth sensor, or any motion input device as Microsoft Kinect. A point whose coordinates are known in both coordinate systems is called an identical point. Data transformation of identical points from one coordinate system to another coordinate system is therefore required. The aim of this contribution is to present a possible approach on how to estimate the unknown transformation parameters by regression models in a special transformation problem. This transformation in its standard version has been derived under the assumption that non-negligible random errors occur at points of that coordinate system into which the transformation is performed. Points of the inverse image coordinate system are assumed to be errorless.Item Computed tomography image analysis: the model of ribs-bounded contour(Václav Skala - UNION Agency, 2015) Bilinskas, Mykolas J.; Dzemyda, Gintautas; Trakymas, Mantas; Skala, VáclavIn this paper, a method for analyzing transversal plane images from computer tomography scans is presented. This method allows not only the approximation of ribs-bounded contour but also the evaluation of patient rotation around the vertical axis during a scan. A mathematical model that describes the ribs-bounded contour was created and the problem of approximation is solved by finding out the optimal parameters of the mathematical model using least-squares.Item Reasoning about graph algorithm visualization(Václav Skala - UNION Agency, 2015) Gordeev, Dmitry S.; Skala, VáclavA method of graph algorithm visualization based on an implicit visual effect generation approach is described. The approach develops an idea to establish an algorithm as an input as well as input graph. Visualization of algorithms is carried out by means of a set of configurable visual effects. We consider a class of hierarchical graphs as a class of input graphs. This allows using wide set of input graphs and presenting additional data appearing during the algorithm work as part of a single visualized graph model. Described approach is be used both in research and education.Item A novel retinex model based on sparse source separation(Václav Skala - UNION Agency, 2015) Choi, Jangwon; Kim, Yong-Goo; Choe, Yoonsik; Skala, VáclavRetinex was introduced by E.Land to explain and solve a problem of color constancy in human visual system (HVS). In this paper, we propose a novel Retinex model based on sparse source separation problem. Different from the existing models, we can explain a relation between the modeling and the effectiveness of Retinex decomposition with the proposed model. We demonstrate the performance of our model by experimental results.Item Detection and tracking of vehicles based on the videoregistration information(Václav Skala - UNION Agency, 2015) Kopenkov, V. N.; Myasnikov, V. V.; Skala, VáclavThis paper describes the technology of detection and tracing vehicles on the sequence of images based on digital video stream analysis in the real-time mode. Such technology can be used for car identification, license plates recognition, and for defining of car traffic parameters: the cars speed and average speed of car traffic, the traffic density, et cetera. One of the main advantages of the presented technology is the simplicity of realization and the possibility of making a cheap solution based on it (cheap camera and a ordinary PC), in contrast to most of the specialized solutions with a high price, and requirements of high-performance hardware components as usual.Item Conditional random fields for web user task recognition based on human computer interaction(Václav Skala - UNION Agency, 2015) Elbahi, Anis; Omri, Mohamed Nazih; Skala, VáclavIn this paper we apply the Conditional Random Fields approach for modeling human navigational behavior based on mouse movements to recognize web user tasks. In fact, inferring activity of web users is an important topic of Human Computer Interaction. To improve the interaction process, many studies have been performed for understanding how users interact with web interfaces in order to perform a given activity. The Experimental evaluation and analysis of the results of the model we present in this paper demonstrate the efficiency of our model in human tasks recognition.Item Improving situational awareness in military operations using augmented reality(Václav Skala - UNION Agency, 2015) Mitaritonna, Alejandro; Abásolo, María José; Skala, VáclavDuring military operations, the battlefields become fractured zones where the level of confusion, noise and ambiguity impact on achieving tactical objectives. Situational Awareness (SA) becomes a challenge because the unstable perception of the situation leads to a degraded understanding that disables the soldier in projecting the proper results. To meet this challenge various military projects have focused their efforts on designing integrated digital system to support decision-making for military personnel in unknown environments. This paper presents the state of art of military systems using Augmented Reality (AR) in the battlefield.Item The creating serious games for historical subjects at the 1st level of primary school and such as a part of exhibition chosen historical buildings(Václav Skala - UNION Agency, 2015) Chadimová, Lenka; Skala, VáclavThe aim of the study was create serious games for historical buildings which are important for each region of Czech Republic. These games are making guide to historical building and give to pupils the information about architecture, history of building and eventually about surroundings of historical building and the like. For creating serious games are using tools of 3D graphic software 3Ds MAX in combination with developing software UNITY 3D. In the modelling software 3Ds MAX were creation 3D models of historical buildings. The gaming environment was creating in UNITY 3D with programming language C#.Item Virtual museum as an environment for visual representation of urban planning concepts and lost architectural objects(Václav Skala - UNION Agency, 2015) Petrova, Yulia; Skala, VáclavIntensive development of the Web has significant influence on social communication processes. New trends of information distribution demand new approach as being involved in on-line communication. Social institutions, including museums and exhibition centers, aim to develop their presence on the Web, searching for ways to engage bigger number of visitors by offering them new experience. A phenomenon of the virtual museum is studied in the paper as an online representation of a tangible museum collections and as an information resource that has no physical analogue. The target is to analyze the potential and relative advantages and disadvantages of virtual museums. The main subject of the research is effectiveness of online tools for representation of large architectural and urban objects, unimplemented projects and lost monuments. Virtual exhibition is often based on the products of virtual reconstruction. It is very important to formulate strict methods of this approach, to develop a methodology and establish a practice of visual distinction between true (and/or relatively true) parts of a virtual model and its authorial parts.Item A COM-based toolkit for real time visualization(Václav Skala - UNION Agency, 2015) Maas, Stefan; Overhoff, Heinrich Martin; Skala, VáclavCollaborative software development in different languages is not unusual, but leads to minor resource utilization during collaboration as a result of porting or reprogramming needs. Additionally in cooperative projects, frequently legal and market economic issues prohibit an exchange of source code between the project partners. Combining modules from different languages is possible using the Component Object Model (COM). Additionally COM offers an efficient way to combine modules from several development teams. To solve the common issues of collaborative software development and to fulfil the needs of a real time visualization toolkit, “RTVCOM” was designed and realized. To demonstrate the capability of this approach an example client was developed that combines COM components written in OpenCL C, OpenGLSL, C++ and C#. It that processes 3D+t ultrasound data at 45.2 MB/s reconstructs the associated volume data and visualizes them in real time. The visualization is fully interactive, and different pre- and post-processing filters can be applied.Item A new 6D ICP algorithm with color segmentation: based adaptive sampling(Václav Skala - UNION Agency, 2015) Kim, Eung-Su; Sung-In, Choi; Park, Soon-Yong; Skala, VáclavIn ICP-based algorithms, the closest points are considered as the corresponding points. However, this method fails to find matching points accurately when the initial position of the point clouds is not sufficiently close. In this paper, we propose a new method to solve this problem using six-dimensional (6D) distance, which consists of color information and three-dimensional (3D) distance, and color distribution matching. First, before finding the corresponding points using this method, a Gaussian filter is applied on the input color image. A color based image segmentation is done on that image and then 𝑛 number of samples are randomly chosen from each segment. This process is applied in order to improve the computational time and performance. Second, corresponding point candidates are searched by solving a local minima problem using 6D distance. Then the color distribution matching is applied on these candidates to find the final corresponding point. Several experiments are conducted to evaluate the proposed method and the experimental results prove it has improved over the conventional methods.Item Using intrinsic surface geometry invariant for 3D ear alignment(Václav Skala - UNION Agency, 2015) Taertulakarn, S.; Tosranon, P.; Pintavirooj, C.; Skala, VáclavIn this study we derive novel surface fiducial point’s detection that is computed from the differential surface geometry. The fiducial points are intrinsic, local, and relative invariants, i.e., they are preserved under similarity, affine, and nonlinear transformations that are piecewise affine. In our experiment, the fiducial points, computed from high order surface shape derivatives, are used in a non-iterative geometric-based method for 3D ear registration and alignment. The matching is achieved by establishing correspondences between fiducial points after a sorting based on a set of absolute local affine invariants derived from them. Experimental results showed that our purposed surface feature is suitable for further application to 3D ear identification because its robustness to geometric transformation.Item Automated detection of buildings on aero images(Václav Skala - UNION Agency, 2015) Novotortsev, Leonid; Voloboy, Alexey; Skala, VáclavOne of the challenging problems in photogrammetry is extracting of three-dimensional objects from aero images, in particular, extraction of different kinds of buildings. All methods that provide satisfactory results are rather time consuming and process data quite long. In the paper we propose a method that detects areas on aero images that might contain a building behind them. Our method allows reducing the amount of data which should be processed by more complex algorithms. This leads to reducing of the total time spent on extraction process.Item Efficient representation of range face images using vectorfaces(Václav Skala - UNION Agency, 2015) Ganguly, Suranjan; Bhattacharjee, Debotosh; Nasipuri, Mita; Skala, VáclavAdvancement in scientific representation should accelerate the processing of images if it is more relevant and worthy with the experiment. Scientific visualizing of data (here, face images) has an enormous impact on exploring detailed inner content of images. Hence, the quality of processing depends on the quantity and informative data that might be accumulated, preserved as well as visualized in a particular image. In this paper, authors have described a novel technique for representation of range face image by „Vectorfaces‟, which is proved to be more effective towards better recognition purpose in terms of recognition rate. Range face image is particularly important for 2D visual images for accomplishing depth data from 3D images. Other than an efficient representation of „Vectorfaces‟ images, authors have also emphasized its significance for selecting better features compared to conventional range images. The major goal of the present work reported in this article is to evaluate, visualize and compare the role of „Vectorfaces‟ over range face images. Change of tracks for different mathematical notations to visualize the images are noted. Moreover, Mean-Maximum curvature image pair is accumulated from range image as well as „Vectorfaces‟ for extraction of features. SVD, followed by a feed-forward backpropagation neural network have been used for recognition purpose. In this work, 3D face images from Frav3D database have been considered. A statistical evaluation of this investigation is also given in the case study section.Item Simulating small-scale object stacking using stack stability(Václav Skala - UNION Agency, 2015) Kronborg Thomsen, Kasper; Kraus, Martin; Skala, VáclavThis paper presents an extension system to a closed-source, real-time physics engine for improving structured stacking behavior with small-scale objects such as wooden toy bricks. The proposed system was implemented and evaluated. The tests showed that the system is able to simulate several common stacking scenarios, which the base physics engine cannot simulate.
