Kyeong Ok Kang

Video contents summary using the combination of multiple MPEG-7 metadata

We propose a content-based summary generation method using MPEG-7 metadata. In this paper, the important events of video are defined and subsequently shot boundary detection is carried out. Then, we analyze the video contents in the shot with multiple content features using multiple MPEG-7 descriptors. In experiments with a golf-video, we combined motion activity, edge histogram and homogeneous texture for the detection of event. Further, the extracted segments and key-frames of each event are described by XML document. Experimental result shows that the proposed method gives reliable summary generation with robust event detection.

A MPEG-7 and TV-anytime-based multiagents platform for interactive broadcasting system

We propose a multi-agents platform for an interactive broadcasting system based on the MPEG-7 and TV-anytime standards. In the system, an intelligent agent technique is adopted from FIPA that provides software standards for interacting heterogeneous agents. Using the MDS (Multimedia Description Scheme) of MPEG-7, TV-anytime standards and interactive functions such as a user preference and an audio/video contents summary, are applied. In this paper, we propose the technique to use multi-modal features as well as multiple MPEG-7 features. We evaluate a video summary and filtering based on MPEG-7 on top of intelligent agent.

Construction of a HATS and its HRTF measurement for 3‐D sound

Based on the anthropometric data on the head and torso dimensions in Korean male adults, a head and torso simulator (HATS) was constructed. Data, which have no counterparts in the Korean standards, were used with ANSI S3.36‐1985. Measuring microphones can be positioned at the eardrum or at the ear canal entrance according to measuring purposes. Head related transfer functions (HRTFs) for the HATS, i.e., binaural impulse responses, were measured at 710 points on a spherical surface of radius 1.55 m using a burst maximum length sequence (MLS) signal of 65 535 samples in an anechoic chamber. The measurement system consists of one part to generate the MLS signal and to drive a Boss 101A loudspeaker and another part to record the output signal of a microphone in the HATS and consequently to measure the impulse response. Also measured were the impulse responses of the driving loudspeaker and some headphones for 3‐D sound reproduction in order to get the exact HRTF of the HATS‐alone. The impulse‐version HRTFs at...