A new content-based access method for video databases

This paper presents a novel video data model and a nested annotation langua ge for describing complex information of video data. In contrast to convent ional approaches, the proposed model classifies different video materials o f interest to users into different representation frameworks according to t heir individual properties. It makes the model flexible and capable of shar ing video materials. The nested annotation language effectively describes s cenarios in video data and can be effectively analysed. With the assistance of domain knowledge and index organizations this investigaton also develop s algorithms to effectively process five types of familiar video queries: s emantic query, temporal quaery, similar query, fuzzy query and hybrid query . In addition, a SQL-like query language for video content retrival is prov ided. Experimental results indicate that combining the concepts of Bayesian networks and inheritance of attributes by context significantly improves t he content based retrieval of video data. Moreover a prototype system based on proposed model has been implemented. (C) 1999 Published by Elsevier Sci ence Inc. All rights reserved.