Development of a video database system with content-based indexing and retrieval capabilities

• Main Author: Zhu, Yong Wei.
• Other Authors: Chua, Hock Chuan
• Format: Theses and Dissertations
• Language: English
• Published: 2009
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• Online Access: http://hdl.handle.net/10356/19804
• Institution: Nanyang Technological University

This thesis describes the design and development of a video database system with content-based indexing and retrieval capabilities for generic video data management. The realization of the content-based indexing and retrieval capabilities is based on a proposed generic video data model. Through the use of the model, video contents are structured and represented by a set of entities in a hierarchical and object-oriented manner. To enable automatic feature extraction for content-based indexing, the model encompasses automatic detectable primitives at the lowest level (such as prominent region and motion vectors). At higher levels, relatively more abstract entities (such as object and scene)are linked to the entities at the lower level. The video data model facilitates automatic feature extraction based on low-level primitives, and at the same time, supports content-based query in a relatively high level of abstraction.