Detecting visual changes in environments is an important computation with many applications in robotics and computer vision. Security cameras, remotely operated vehicles, and sentry robots could all benefit from robus...
详细信息
ISBN:
(纸本)9781612844558
Detecting visual changes in environments is an important computation with many applications in robotics and computer vision. Security cameras, remotely operated vehicles, and sentry robots could all benefit from robust change detection capability. We conjecture that if one has a mobile camera system the number of visual scenes that are experienced is limited (compared to the space of all possible scenes) and that the scenes do not frequently undergo major changes between observations. These assumptions can be exploited to ease the task of change detection and reduce the computational complexity of processing visual information by utilizing memory to store previous computations. We demonstrate a method to learn the distribution of visual features in an environment via a self-organizing map. Additionally, the spatial distribution of these features can be learned if a positional signal is available. Our method uses a low dimensional representation of visual features to rapidly detect changes in current visual inputs. The model encodes spatially-distributed color histograms of real world visual scenes captured by a camera moved through an environment. The distribution of the color histograms is learned using a self-organizing map with location (when available) and color data. We present tests of the model on detecting changes in an indoor environment.
In this papar, we introduce a visualization method for acitivity information sharing system using Self-Organizing Map and the activity information sharing system "ALKAN2", which aims at gathering activity in...
详细信息
In this papar, we introduce a visualization method for acitivity information sharing system using Self-Organizing Map and the activity information sharing system "ALKAN2", which aims at gathering activity information for activity analysis. ALKAN2 gathers users' activity using sensor data and movie data. Moreover, ALKAN2 prepares display environment for users. A user mimics activities of other users, and a user sends the mimicked data to the server. As a result, the mimicked data can be objectively evaluated. In this papar, we explain visualization for sensor data of ALKAN2.
The proceedings contain 66 papers. The special focus in this conference is on Intelligent Content, Semantics, Knowledge Management, Business Intelligence and Innovation. The topics include: News article classification...
ISBN:
(纸本)9783642231629
The proceedings contain 66 papers. The special focus in this conference is on Intelligent Content, Semantics, Knowledge Management, Business Intelligence and Innovation. The topics include: News article classification based on a vector representation including words’ collocations;classification of online reviews by computational semantic lexicons;reason-able view of linked data for cultural heritage;semantic retrieval approach to factoid question answering for bulgarian;using semantic relations for representing long-term user interests;integrating internet protocol television and social networking;clustering and visualization of ecg signals;visualizing and presenting story maps in TM4Book;a fuzzy bat clustering method for ergonomic screening of office workplaces;the influence of global constraints on DTW and LCS similarity measures for time-series databases;social network analysis in professional e-recruitment;a system integrating agent services with jms for shared battlefield situation awareness;a model for fuzzy logic assessment of real estate investment risks;towards the foundation for read-write governance of civilizations;an analysis and forecast of software and services research in bulgaria;a fuzzy system model for task implementation in extreme programming process;integration of natural language processing chains in content management systems;supporting interactive IPTV apps with an enterprise resource bus and service oriented architecture applied to provide inter-operability between macedonian MoD and NATO.
Fuel gas (hydrogen gas) and oxidant gas (air) are supplied to a polymer electrolyte fuel cell (PEFC). Condensation may occur in the cathode side, since the air might be super-saturated by the fuel cell reactions. If c...
详细信息
Fuel gas (hydrogen gas) and oxidant gas (air) are supplied to a polymer electrolyte fuel cell (PEFC). Condensation may occur in the cathode side, since the air might be super-saturated by the fuel cell reactions. If condensed water exists in a gas diffusion layer (GDL) or the gas channels, it may affect the fuel cell performances because it blocks the oxygen from reaching the cathode reaction site. Thus, water management in the PEFC is important. In order to clarify water effects on performances of a PEFC, visualization and quantitative measurements of water distributions in a PEFC were carried out by means of neutron radiography. Two-dimensional water distributions were obtained, and water ejection was confirmed. It was found that the water easily accumulated in the GDL under the rib rather than under the channel at beginning of the operation. Furthermore, a network analysis of gas-velocity distribution is applied for the experimental results. It analyzes the gas-velocity distributions depending on the flow resistance, which is the pressure drop. Applying the measured data of water thickness, gas-velocity distributions were obtained in the channel and the GDL. From the calculation, air supply in the GDL dramatically decreased with increasing of water accumulation. (C) 2010 Elsevier B.V. All rights reserved.
Rod bundles are widely used in industry today with applications ranging from nuclear reactors, heat exchangers, and steam generators. Accurately modeling the inherently unsteady and turbulent flow within these rods is...
详细信息
ISBN:
(纸本)9780791849309
Rod bundles are widely used in industry today with applications ranging from nuclear reactors, heat exchangers, and steam generators. Accurately modeling the inherently unsteady and turbulent flow within these rods is essential in order to design for optimal efficiency while controlling vibration, noise and heat transfer. The problem complicates further when spacer-grids are used within the rods to maintain separation and structural rigidity. Computational modeling can be a useful alternative to the costly process of manufacturing and testing prototypes, but its accuracy needs to be checked with detailed experimental data. This paper describes an experimental database obtained using two-dimensional Time Resolved Particle Image Velocimetry (TR-PIV) measurements within a 5 x 5 rod bundle with spacer-grids. One of the unique characteristic of this set-up is the use of the Matched Index of Refraction technique employed in this investigation which consists of immersing plastic rods with a similar index of refraction as the one for water to achieve optical transparency across the spacer grid. This unique feature allows flow visualization and measurement within the bundle without rod obstruction. This approach also allows the use of high temporal and spatial non-intrusive dynamic measurement techniques namely TR-PIV to investigate the flow evolution below and immediately above the spacer. The data base presented includes explanation of the various cases tested such as boundary conditions, rig dimensions, measurement zones, and the test equipment in order to provide a good base for Computational Fluid Dynamics (CFD) simulations. Turbulence analysis of the obtained data is provided in order to gain insight of the physical phenomena and to compare the possible results obtained from computational simulations.
Wireless capsule endoscopy (WCE) has been intensively researched recently due to its convenience for diagnosis and extended detection coverage of some diseases. Typically, a full recording covering entire human digest...
详细信息
ISBN:
(纸本)9780819485045
Wireless capsule endoscopy (WCE) has been intensively researched recently due to its convenience for diagnosis and extended detection coverage of some diseases. Typically, a full recording covering entire human digestive system requires about 8 to 12 hours for a patient carrying a capsule endoscope and a portable image receiver/recorder unit, which produces 120,000 image frames on average. In spite of the benefits of close examination, WCE based test has a barrier for quick diagnosis such that a trained diagnostician must examine a huge amount of images for close investigation, normally over 2 hours. The main purpose of our work is to present a novel machine vision approach to reduce diagnosis time by automatically detecting duplicated recordings caused by backward camera movement, typically containing redundant information, in small intestine. The developed technique could be integrated with a visualization tool which supports intelligent inspection method, such as automatic play speed control. Our experimental result shows high accuracy of the technique by detecting 989 duplicate image frames out of 10,000, equivalently to 9.9% data reduction, in a WCE video from a real human subject. With some selected parameters, we achieved the correct detection ratio of 92.85% and the false detection ratio of 13.57%.
Faced with a large, high-dimensional dataset, many turn to dataanalysis approaches that they understand less well than the domain of their data. An expert's knowledge can be leveraged into many types of analysis ...
详细信息
Faced with a large, high-dimensional dataset, many turn to dataanalysis approaches that they understand less well than the domain of their data. An expert's knowledge can be leveraged into many types of analysis via a domain-specific distance function, but creating such a function is not intuitive to do by hand. We have created a system that shows an initial visualization, adapts to user feedback, and produces a distance function as a result. Specifically, we present a multidimensional scaling (MDS) visualization and an iterative feedback mechanism for a user to affect the distance function that informs the visualization without having to adjust the parameters of the visualization directly. An encouraging experimental result suggests that using this tool, data attributes with useless data are given low importance in the distance function.
visualization technologies of complex power grid become more and more important because of the enlargement of grid scale. Combining the analysis processing of complex power grid with visualization technologies based o...
详细信息
ISBN:
(纸本)9781612848334
visualization technologies of complex power grid become more and more important because of the enlargement of grid scale. Combining the analysis processing of complex power grid with visualization technologies based on geographical information, visualizationanalysis model of flow calculation has been developed on the integrated development platform of PowerBuilder and MapInfo in this paper. Functions, system architecture and data structures of the analysis model were firstly designed, and the key technologies and their implementation were also discussed. According to the presented analysis model, the influence of power grid failure to urban power can be analyzed, and power supply states under different operation modes can also be dynamically and intuitively represented. The feasibility and practicality of the model was verified by giving an example of an IEEE 14-node grid.
Recent advances in computer technologies in terms of both hardware and software have already made the development of an interactive 3D medical visualization system viable. Volume rendering as an important visualizatio...
详细信息
Recent advances in computer technologies in terms of both hardware and software have already made the development of an interactive 3D medical visualization system viable. Volume rendering as an important visualization technique can truly represent the information within the 3D datasets. However, it lacks of desirable interactivity. In order to deal with this problem, we introduce an interactive framework which is capable of the medical image visualization based on high-quality volume rendering. The framework implements various interactive functions with volume rendering techniques, such as displaying arbitrary cross sections and picking objects in 3D space. The system is evaluated by 4 continuous clinical patient data from Computed Tomography Angiograph (CTA) scans, and its performance is estimated by sophisticated surgeons.
The workshop aims to bring together researchers and practitioners with interests and experience in complex dataanalysis and visualization to specifically discuss different approaches and trends in the research of sca...
The workshop aims to bring together researchers and practitioners with interests and experience in complex dataanalysis and visualization to specifically discuss different approaches and trends in the research of scalable network visualization.
暂无评论