|Title:||Content description for video database dynamic object type and dynamic indexing|
Hong Kong Polytechnic University -- Dissertations
Department of Electronic Engineering
|Pages:||ii, 50 leaves : ill. ; 31 cm|
|Abstract:||Multimedia information management systems are experiencing rapid growth and development. This field span over a wide scope of research areas including signal processing, content descriptions, content-based indexing and retrieval, and query processing. This thesis concentrates on the area of video content descriptions. Because of the complex nature of video content descriptions, traditional Relational Database Management System (RDBMS) can no longer be able to manage these kinds of data. A dynamic object type and dynamic indexing methods are introduced in this thesis for describing video contents. The methods aim to enable systems to handle additional complex object types added to the system for representing video descriptions. Systems built with these features can evolve over time. A data model was built in this thesis for video description systems. The model includes a hierarchical data structure that contains videos, description categories belong to each video and actual descriptions of videos. A logical prototype of the proposed system has been built in this thesis to demonstrate the operation of the system. Sample videos have been used. Description categories such as person, colour, topics are employed for illustration. Pseudo codes that execute a few typical queries are used to explain how it is performed in the proposed system. In summary, the features and models introduced in this thesis solve some of the typical problems faced in the development of video content description systems.|
Files in This Item:
|b14854181.pdf||For PolyU Staff & Students||2.13 MB||Adobe PDF||View/Open|
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item: