Daisuke Kitayama

Interoperable augmented web browsing for exploring virtual media in real space

Although location-based information systems can now be accessed from mobile devices, searching for information from an outdoor environment requires a significant amount of effort given the time-consuming manipulations that need to be made. Augmented-Reality (AR) based systems can help resolve these issues by reducing the physical effort required to input keywords onto a small keyboard, and the mental effort necessary to review the search results. But most AR systems do not consider media sharing environments where individual systems are not interoperable in respect of their media and browsing abilities. In this paper, we focus on a media environment for interoperable augmented-reality systems, making the assumption that such devices will become more wide spread and that many people will share individual media in a real-world space. Furthermore, we describe such emerging scenarios and new research issues. We also present a model to manage the futuristic data, making it similar to existing physical media, and show a practical example using the system we have developed.

An Interval Ranking Method of Multimedia Presentation based on Relative Query Keyword Position

Presentation content can consist of heterogeneous media, such as videos and slides, which have been recorded and used. A variety of retrieval methods have been proposed for each kind of stored media. This paper proposes an extraction method using the features of each type of media. The proposed method specifically uses presentation video and slides. A user inputs query keywords, which are used to extract the most appropriate interval for the query according to appearance positions in the media. This enables the user to extract intervals that can be viewed more efficiently than when the interval depends only on the presence of query keywords.

Route recommendation method for car navigation system based on estimation of driver's intent

Nowadays, car navigation systems are widely used in cars to aid drivers by providing directions to a destination. However, these systems do not always recommend a route that perfectly matches the drivers intent. Even when drivers intentionally select a route that is different from the recommended one, the system leads them back to the original route. Such recommendations do not adequately reflect the drivers intent. This study proposes a route recommendation method for a car navigation system that estimates the drivers intent and rerecommends a route that matches this intent when the driver deviates from the originally recommended route. We developed a simulator based on the proposed method and used it to experimentally verify the effectiveness of the proposed method.

Automatic Generation of Learning Channels by Using Semantic Relations among Lecture Slides and Recorded Videos for Self-Learning Systems

We present a method of automatically generating learning channels by using the semantic relations that implicitly exist in slides of a lecture that has accompanying recorded video. These days, many lecture videos with presentation files are shared over the Web from many universities through their own public sites. Although these materials are useful and valuable to many potential students, their use of sequential static media for self-learning purposes means there is still a lack of support for self-learners seeking learning channels suitable for various levels of understanding. Our newly generated learning channels let users easily focus on either highly detailed slides or introductory slides without needing to examine all of the data. We describe a prototype system supported by this learning-channel construction method.

A Scene Extracting Method Based on Structural and Semantic Analysis of Presentation Content Archives

It has become easier for users to view presentation content consisting of synchronized heterogeneous media such as videos and slides. Users simply retrieve the stored content they wish to view. In most cases users are interested in viewing a specific portion of the content. Scenes extracted from a presentation, however, often do not help the user understand the content, even when those scenes contain the query key word. A method is needed for extracting viewing intervals from content which are meaningful to the user. In this paper, we propose a method to extract scenes according to their relation. These relations are decided at the point of change between scenes. In this paper we describe our method and subject it to evaluation.

Scene extraction system for video clips using attached comment interval and pointing region

A method was developed to enable users of video sharing websites to easily retrieve video scenes relevant to their interests. The system analyzes both text and non-text aspects of a user’s comment and then retrieves and displays relevant scenes along with attached comments. The text analysis works in tandem with non-text features, namely, the selected area and temporal duration associated with user comments. In this way, our system supports a better-organized retrieval of scenes that have been commented on with a higher degree of relevancy than conventional methods, such as using matching keywords. We describe our method and the relation between the scenes and discuss a prototype system.

Organizing User Comments in a Social Video Sharing System by Temporal Duration and Pointing Region

Recently, video sharing sites that allow visitors to attach comments to video have attracted a lot of attention. Video also provides a means of communication on social network sites. This kind of communication is expected to become even more popular in the future. One problem is that discussion jumps from one topic to another as users add their viewpoints. Also, conventional video sharing sites show, unsorted, all of a particular users attached comments. It is often difficult in such systems to identify and retrieve comments relevant to ones own interest. We have developed a method for determining comment relationship types on the basis of temporal duration and the pointing region. Our method can also be used for extracting comments related to other comments made by the user. In this paper we describe how our method classifies comment relationships and discuss our prototype system which uses the method.

A deformation analysis method for artificial maps based on geographical accuracy and its applications

Artificial maps are widely used for a variety of purposes, including as tourist guides to help people find geographical objects using simple figures. We aim to develop an editing system and a navigation system for artificial maps. Artificial maps made for tourists show suitable objects for traveling users. Therefore, if the artificial map has a navigation system, users can get geographical information such as object positions and routes without performing any operations. However, artificial maps might contain incorrect or superfluous information, such as some objects on the map being intentionally enlarged or omitted. For developing the system, there are two problems: 1. extraction of geographical information from the raster graphics of the artificial map and 2. revision of inaccurate geographical information on the artificial map. We propose a deformation-analyzing method based on geographical accuracy using optical character recognition techniques and comparing gazetteer information. That is, our proposed method detects the tolerance level for deformation according to the purpose of the artificial map. Then, we detect a certain position on the artificial map using deformation analysis. In this paper, we develop a prototype system and we evaluate the accuracy of extracting information from the artificial map and detecting positions.

Geographical information retrieval based on user's operation on both digital maps and directory services

Maps on the Internet are enhanced with many types of information and annotations. Searching these digital maps by directory sevices can yield more information about places and objects on the maps. However, when there is a large amount of information, the user difficult to find geographical objects according for users intention. In other words, searches by directory sevices do not always present the map information the user wants to retrieve. We propose a method that takes into account users digital map search history to recommend geographical information. The system we developed extracts the users intention and displays corresponding geographical information by analyzing the users operations on the maps and their directory services. Our method displays geographical information that is appropriate for the user by using the users extracted intention.

Web-based evidence excavation to explore the authenticity of local events

With the increasing employment of the Web in our daily lives, we often use it to find evidence of real-world events. The difference with normal web searches is that users want to reveal whether an event is true or false based on firm facts. In this paper, we propose a model to excavate real-world events from the Web, to manage the vestige in spatio-temporal space and to offer users reliable evidence of an event. We also describe a similarity measure between events to perform searching and clustering. A credibility estimation method, based on the trustworthiness of events and the authority of web sites, using a primary experiment is also presented.