Mixed Reality commonly refers to the merging of real and virtual worlds to produce new visualization environments where physical and digital objects co-exist and interact in real time. Mixed Reality can also be used f...
详细信息
ISBN:
(纸本)9781424427932
Mixed Reality commonly refers to the merging of real and virtual worlds to produce new visualization environments where physical and digital objects co-exist and interact in real time. Mixed Reality can also be used for fusing sensor data into the existing user interface to efficiently improve situation awareness, to facilitate the understanding of surrounding environment, and to predict the future status. The work presented in this paper fuses and then represents the real video and complementary information into one single Mixed Reality interface. A simulation platform to test the Mixed Reality interface for teleoperation is also discussed in this paper.
The construction of an adaptive landscape visualization entails the representation of the higher dimensional chromosome space onto a two-dimensional plane from which a depiction of the landscape can be created. Althou...
详细信息
CNN image classifiers are widely used, thanks to their efficiency and accuracy However, they can suffer from biases that impede their practical applications. Most existing bias investigation techniques are either inap...
详细信息
ISBN:
(数字)9781665469463
ISBN:
(纸本)9781665469463
CNN image classifiers are widely used, thanks to their efficiency and accuracy However, they can suffer from biases that impede their practical applications. Most existing bias investigation techniques are either inapplicable to general image classification tasks or require significant user efforts in perusing all data subgroups to manually specify which data attributes to inspect. We present VISCUIT, an interactive visualization system that reveals how and why a CNN classifier is biased. VISCUIT visually summarizes the subgroups on which the classifier underperforms and helps users discover and characterize the cause of the underperformances by revealing image concepts responsible for activating neurons that contribute to misclassifications. VisCUIT runs in modern browsers and is opensource, allowing people to easily access and extend the tool to other model architectures and datasets. VISCUIT is available at the following public demo link: https://***/VisCUIT. A video demo is available at https://***/eNDbSyM4R_4.
So-called battle maps are an appropriate way to visually summarize the flow of battles as they happen in many team-based combat games. Such maps can be a valuable tool for retrospective analysis of battles for the pur...
详细信息
ISBN:
(纸本)9781728118840
So-called battle maps are an appropriate way to visually summarize the flow of battles as they happen in many team-based combat games. Such maps can be a valuable tool for retrospective analysis of battles for the purpose of training or for providing a summary representation for spectators. In this paper an extension to the battle map algorithm previously proposed by the author [1] and which addresses a shortcoming in the depiction of troop movements is described. The extension does not require alteration of the original algorithm and can easily be added as an intermediate step before rendering. The extension is illustrated using gameplay data from the team-based multiplayer game World of Tanks.
Various events, such as public gatherings, traffic accidents, and natural disasters, occur every day in mega-cities. Although understanding such ever-changing events over all these cities is important for urban planni...
详细信息
ISBN:
(纸本)9781467389426
Various events, such as public gatherings, traffic accidents, and natural disasters, occur every day in mega-cities. Although understanding such ever-changing events over all these cities is important for urban planning, traffic management, and disaster response, this is quite a huge challenge. This paper proposes a method of visualizing spatio-temporal events with a multi-layered geo-locational word-cloud representation from a geo-parsed microblog stream. Real-time geo-parsing first geo-locates posts in the stream, using geo-tags and mentioned places and facilities as clues. Temporal local events are then identified and represented by a set of words specifically observed in a certain location and time grid, and then displayed above a map as word-clouds. We detect the locality of events to split them into multiple layers to avoid occlusions between local (e.g., music concerts) and global (e.g., earthquakes and marathon races) events. Users can thereby distinguish local from global events, and see their interactions over the layered maps. We demonstrate the effectiveness of our method by applying it to real events extracted from our archive accumulated from five years of Twitter posts.
This study aims at providing a low-cost solution for telepresence where people are reconstructed as 3D avatars using an ordinary webcam, while still exhibiting abundant facial information (such as micro-expressions) t...
详细信息
ISBN:
(纸本)9781665484022
This study aims at providing a low-cost solution for telepresence where people are reconstructed as 3D avatars using an ordinary webcam, while still exhibiting abundant facial information (such as micro-expressions) that are critical for face-to-face communication. We estimate the basic 3D shape and texture of the body from a set of video frames, and then subsequently update its body pose, facial expression, and facial texture in each frame. Our method is expected to reduce the entry barrier of VR systems and create an embodied telecommunication that conveys rich information and subtle emotional changes to deepen mutual understanding at a distance.
The investigation of the VAST Contest collection provided a valuable test for text mining techniques. Our group has focused on creating analytical tools to unveil relevant patterns and to aid with the content navigati...
详细信息
ISBN:
(纸本)9781424416592
The investigation of the VAST Contest collection provided a valuable test for text mining techniques. Our group has focused on creating analytical tools to unveil relevant patterns and to aid with the content navigation in such text collections. Our results show how such an approach, in combination with visualization techniques, can ease the discovery process especially when multiple tools founded on the same approach to data mining are used in complement to and in concert with one another.
Data visualization is created due to the need to show vast amount of data in a more transparent way. Data visualization often contains key information that is not listed anywhere in the text and allows the reader to f...
详细信息
ISBN:
(纸本)9781728132273
Data visualization is created due to the need to show vast amount of data in a more transparent way. Data visualization often contains key information that is not listed anywhere in the text and allows the reader to find out important information and longer-term memory. On the other hand, Internet search engines have a problem with filtering data visualization and associating visualization and query that the user has entered. With the use of data visualization, all blind people and people with impaired vision are left off. This paper uses machine learning for classifying charts into 10 categories. The total accuracy achieved across all categories is 81.67%.
Recently, convolutional neural networks (CNNs) have shown great success on the task of monocular depth estimation. A fundamental yet unanswered question is: how CNNs can infer depth from a single image. Toward answeri...
详细信息
ISBN:
(纸本)9781728148038
Recently, convolutional neural networks (CNNs) have shown great success on the task of monocular depth estimation. A fundamental yet unanswered question is: how CNNs can infer depth from a single image. Toward answering this question, we consider visualization of inference of a CNN by identifying relevant pixels of an input image to depth estimation. We formulate it as an optimization problem of identifying the smallest number of image pixels from which the CNN can estimate a depth map with the minimum difference from the estimate from the entire image. To cope with a difficulty with optimization through a deep CNN, we propose to use another network to predict those relevant image pixels in a forward computation. In our experiments, we first show the effectiveness of this approach, and then apply it to different depth estimation networks on indoor and outdoor scene datasets. The results provide several findings that help exploration of the above question.
We present a new technique for visualizing surfaces from 3D ultrasound data. 3D ultrasound datasets are typically fuzzy, contain a substantial amount of noise and speckle, and suffer from several other problems that m...
详细信息
ISBN:
(纸本)078037200X
We present a new technique for visualizing surfaces from 3D ultrasound data. 3D ultrasound datasets are typically fuzzy, contain a substantial amount of noise and speckle, and suffer from several other problems that make extraction of continuous and smooth surfaces extremely difficult. We propose a novel opacity classification algorithm for 3D ultrasound datasets, based on the variational principle. More specifically, we compute a volumetric opacity function that optimally satisfies a set of simultaneous requirements, One requirement makes the function attain nonzero values only in the vicinity of a user-specified value, resulting in soft shells of finite, approximately constant thickness around isosurfaces in the volume. Other requirements are designed to make the function smoother and less sensitive to noise and speckle. The computed opacity function lends itself well to explicit geometric surface extraction, as well as to direct volume rendering at interactive rates. We also describe a new splatting algorithm that is particularly well suited for displaying soft opacity shells, Several examples and comparisons are included to illustrate our approach and demonstrate its effectiveness on real 3D ultrasound datasets.
暂无评论