-
Proceedings of the IAPR Conference on Machine Vision Applications (IAPR MVA 2005), May 16-18, 2005, Tsukuba Science City, Japan; 01/2005
-
Proceedings of the 2004 IEEE International Conference on Multimedia and Expo, ICME 2004, 27-30 June 2004, Taipei, Taiwan; 01/2004
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper we propose a wearable vision interface system named “I’m Here!” to support a user’s remembrance of object location
in everyday life. The system enables users to retrieve certain information from a video database that has recorded a set of
the latest scenes of target objects which were held by the user and were observed from the users’ viewpoint. We propose the
object recognition method to associate the video database with the name of objects observed in the video. The offline experiments
demonstrate that the system is useful enough to recognize the objects.
09/2003: pages 422-427;
-
Human-Computer Interaction with Mobile Devices and Services, 5th International Symposium, Mobile HCI 2003, Udine, Italy, September 8-11, 2003, Proceedings; 01/2003
-
[show abstract]
[hide abstract]
ABSTRACT: This chapter introduces video data management techniques for computational augmentation of human memory, i.e., augmented memory, on wearable and ubiquitous computers used in our everyday life. The ultimate goal of augmented memory is to enable users to conduct themselves using human memories and multimedia data seamlessly anywhere, anytime. In particular, a user's viewpoint video is one of the most important triggers for recalling past events that have been experienced. We believe designing augmented memory systems is a practical issue for real world-oriented video data management. This chapter also describes a framework for an augmented memory albuming system named SARA, a (Sceneful Augmented Remembrance Album). In the SARA framework, we have developed three systems for retrieving, editing, transporting, and exchanging augmented memory. Both the Residual Memory system and the I'm Here! system enable a wearer to retrieve video data that he/she wants to recall in the real world. The Ubiquitous Memories system is proposed for editing, transporting, and exchanging video data via real world objects. Lastly, we discuss future works for the proposed framework and modules.
-
[show abstract]
[hide abstract]
ABSTRACT: This paper introduces a plan of an experiment to analyze relations among user experiences and real world objects on the Ubiquitous Memories system. By finding out the characteristics, we could develop functions for an automatic linking method among an experience and objects, and recommending experiences linked with several objects. In order to conduct this experiment, we attached 2,257 RFID tags to real world objects. We also categorized the objects into 21 purpose-based object types, and investigated share-ability of experiences by a questionnaire in advance. Both works are important for us to focus analyzation paramters in the experiment. In this paper we represent basic results of the categorization of the attached objects and the questionnaire.
-
[show abstract]
[hide abstract]
ABSTRACT: People tend to forget where they placed an object, which is necessary to achieve a certain task, in their everyday circumstances. To support a user’s object-finding tasks, we have proposed a wearable interface system named ”I’m Here!” The system manages Augmented Memories, a video database of the user’s viewpoint labeled with previously registered objects, to display the last video of the target object held by the user. In this paper we evaluate the function of the system with laboratory experiments, and discuss the positive and negative effect of the system with the experimental results. http://library.naist.jp/mylimedio/dllimedio/show.cgi?bookid=72524
-
Takahiro Ueoka
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, we present a useful histogram in order to reduce sensor noise effect and get to similar measures. This histogram is constructed in HSV color space using the probabilistic representation of color distribution. To prove the effectiveness of the approach, we conducted two experiments in comparison with the conventional one. http://library.naist.jp/mylimedio/dllimedio/show.cgi?bookid=71330
-
[show abstract]
[hide abstract]
ABSTRACT: We have developed a wearable vision interface system to aid users in remembering the location of objects used in daily life. Our system includes both registration and retrieval functions. Object identification is made through a novel camera device, which can easily extract only a region of a target object from an image. In addition, the identification of the object consists of two levels. The first level includes a rough identification which discriminates between similar objects. The second level includes identification with a subspace method from roughly identified candidate objects. http://library.naist.jp/mylimedio/dllimedio/show.cgi?bookid=65660
-
[show abstract]
[hide abstract]
ABSTRACT: The aim of this paper is to investigate an effective view angle of “a first-person video” when a user tries “an object-finding task”, a task to find a target object in his/her everyday environment. The first-person video means a video recorded by a head-mounted camera of a wearable system worn by the user. The objectfinding task can occur when the user forgets where he/she last placed the target object. The first-person video can include some contexts of the event. There are two important contexts required by the user to find the target object; one is “the action” that he/she placed the target object, and the other context is “the location” that the object was placed. The view angle of a lens, which is employed by the camera device, affects the width and the time length of the first-person video. It is important to investigate appropriate range of the angle so that the user can recognize those contexts by watching the first-person video. We conducted experiments that subjects evaluate videos in several width of the angle. We then found that the range of the view angle is from 115 to 125 in degree. http://library.naist.jp/mylimedio/dllimedio/show.cgi?bookid=80853
