Ig-Jae Kim

A new approach for high level video structuring

The paper introduces a high level video structuring scheme using both color and motion features. Until now, color information has been used for video scene segmentation research. However, action movies with rapid motion of objects have characteristics of dynamic changes of color information. In this case, the traditional approach is not so appropriate. To overcome this drawback, a new criterion for video shot similarity using color and motion features is presented and discussed. Then, a new adaptive scene segmentation algorithm is proposed, of which the main features include adaptive weighting of color and motion similarity between two shots. Moreover, the improved overlapping links scheme is proposed for reducing the time cost for shot grouping. The proposed scheme is evaluated using the movie: Terminator II, together with implementing a prototype video browsing system using the structured video.

Virtual heritage system: modeling, database & presentation

This paper addresses three research issues for the virtual heritage system: 3D modeling, 3D media asset database management, and interactive presentation through networks. We first show art overview of our virtual heritage system and introduce our approaches on each research issue. We develop 3D modeling environment using both of two emerging techniques, i.e., image-based 3D modeling and 3D laser scanning-based 3D modeling techniques. Each technique captures range data of 3D objects using 3D input devices and uses 3D mesh modeling scheme. Our test results from both of these trials are shown. One of the important tasks for the virtual heritage system is how to manage the various kinds of cultural heritage assets. For this goal, our approach for an asset management is described. This includes the system configuration and asset creation method. Finally, we address how to present the virtual heritages. Here, we show two approaches, Web-based and virtual reality theater-based system. We also address the networking issues for transcontinental cultural heritage exchange and our future plan for the 3D cyber museum through the Trans-Eurasia Information Network.

Personalized life log media system in ubiquitous environment

In this paper, we propose new system for storing and retrieval of personal life log media on ubiquitous environment. We can gather personal life log media from intelligent gadgets which are connected with wireless network. Our intelligent gadgets consist of wearable gadgets and environment gadgets. Wearable gadgets include audiovisual device, GPS, 3D-accelerometer and physiological reaction sensors. Environment gadgets include the smart sensors attached to the daily supplies, such as cup, chair, door and so on. User can get multimedia stream with wearable intelligent gadget and also get the environmental information around him from environment gadgets as personal life log media. These life log media(LLM) can be logged on the LLM server in realtime. In LLM server, learning-based activity analysis engine will process logged data and create meta data for retrieval automatically. By using proposed system, user can log with personalized life log media and can retrieve the media at any time. To give more intuitive retrieval, we provide intuitive spatiotemporal graphical user interface in client part. Finally we can provide user-centered service with individual activity registration and classification for each user with our proposed system.

Multi-level Experience Retrieval for the Personal Lifelog Media System

Personal lifelog media system stores and retrieves userpsilas every day experiences in the form of multimedia data format. This system involves huge amount of data and requires a metadata database system to enable user to retrieve the desired media efficiently. This paper proposes a multi-level abstracted metadata DB design to retrieve every day experiences in various ways with a user-friendly web interface. The simulated performance with real lifelog media data shows that suggested multi-level metadata DB structure can retrieve experience media data around four times more efficient compared with usual single-level annotation-based metadata database in the sense of retrieval time.

3-dimensional voice communication system for two user groups

This paper proposes a 3-dimensional (3D) voice over IP (VoIP) system for two user groups with the smallest device requirements. It also presents design issues of the system and some experience in implementation of the system. The proposed system requires only a desktop computer with a multi-channel soundcard installed, USB microphones as many as the number of users, and 3D sound rendering system such as 5.1ch or 7.1ch loudspeaker system. It not only enables multiple users to communicate with a remote group using a single desktop computer, but also enriches the voice of each user with 3D spatial effect. Using the system, the participants can hear the voice of remote users through a 3D sound rendering system, as if each remote user speaks at his or her corresponding position. This system can be used for immersive teleconference system

Augmented telexistence in smart space

In this paper, we present the new environment for telexistence using our smart space which we have built for interactive space. Weve developed several component modules for telexistence, such as display module for large scale display system, interaction module for multimodal interaction, video module for streaming and rendering module for augmented composition in our smart space. Those systems are well-integrated and allow for augmented telexistence functionality which is more natural and also give a beyond face-to-face communication between remote users. Based on our proposed environment, we can create new possibilities for immersive and interactive communication across the space.

Large-Scale Stereo Display Wall Using Programmable Graphics Hardware

In this paper, we present an large-scale stereo display wall system for tangible telemeeting using programmable graphics hardware. For tangible telemeeting, it is important to provide immersive display with high resolution image to cover up the field of view and provide to the local user the same environment as that of remote site. To achieve these, a high resolution image needs to be transmitted for reconstruction of remote world, and it should be displayed using a large display. However, it is hard to transmit high resolution image in real time due to the limit of network bandwidth, and so we receive multiple images and reconstruct a remote world with received images in advance. Then, we update only a specific area where remote user exists by receiving low resolution image in real-time. We synthesize the transmitted image to the existing environmental map of remote world and display it as a stereo image. For this, we developed a new system which supports GPU based real time warping, blending and automatic feature extraction using machine vision technique.

Web-based 3D media information system

This paper introduces web-based 3D media information system. We first address two promising 3D modeling techniques, i.e., image-based 3D modeling and laser scanning based 3D modeling. Especially, we present two approaches of the image-based 3D modeling. One is an off-line approach using multiview images which is captured with single camera and a robot arm. The another one is an on-line approach that extends a commercial triclops camera system. We also utilize a 3D modeling scheme based on a laser scanner and a 3D reverse modeler. Using our 3D modeling environments, we construct several kinds of 3D models. We also implement web-based 3D media information management and retrieval system using XML data server, which provides services of 3D models. Our web-based 3D media information system has a goal of services of various types of 3D models and contents through WWW, which is currently focused on the development and management of 3D models of Korea cultural heritage.