ビデオデータにおける指定人物の検出と追跡 : 音声部分を用いた処理

概要

論文の詳細を見る
Multimedia database management and retrieving are on a world-wide demand. In particular, Object Location and Tracking (OLT) technology in time-space is a core in a search engine of a huge multimedia database and has wide applications. The final target of our research is to establish technologies which enables to locate and track specified objects in video data from the combination of audio and visual cues. As human being is one of the typical objects, as the first step of our research this paper will be focused on location and tracking of a specified person in the audio domain. This paper describes OLT project, the speaker-based segment detection and junction algorithms and evaluation experiments using the simulated dialogue data, and segment Fuzzy search algorithm and its application to detection of variable length segment.
一般社団法人映像情報メディア学会の論文
1998-11-20