Representation and Retrieval of Video Data in Multimedia Systems

Pirmais vāks
HongJiang Zhang, Philippe Aigrain, Dragutin Petkovic
Springer Science & Business Media, 2007. gada 23. nov. - 84 lappuses
Representation and Retrieval of Video Data in Multimedia Systems brings together in one place important contributions and up-to-date research results in this important area.
Representation and Retrieval of Video Data in Multimedia Systems serves as an excellent reference, providing insight into some of the most important research issues in the field.

No grāmatas satura

Lietotāju komentāri - Rakstīt atsauksmi

Ierastajās vietās neesam atraduši nevienu atsauksmi.

Atlasītās lappuses

Saturs

The Application of Video Semantics and Theme Representation in Automated Video Editing
57
Autortiesības

Citi izdevumi - Skatīt visu

Bieži izmantoti vārdi un frāzes

Populāri fragmenti

7. lappuse - Department of Computer Science Hong Kong University of Science and Technology Clear Water Bay, Kowloon, Hong Kong Email: {zhangfan, chanson} @cs.ust.hk Abstract Multimedia applications over the Internet are becoming increasingly popular.
55. lappuse - OVID: design and implementation of a video-object database system," IEEE Transactions on Knowledge and Data Engineering, vol.
53. lappuse - JR Bach, S. Paul, and R. Jain, "A Visual Information Management System for the Interactive Retrieval of Faces," IEEE Transactions on Knowledge and Data Engineering.
9. lappuse - Little et al. [15] implemented a system that supports content-based retrieval of video footage. They define a specific data schema composed of movie, scene, and actor relations with a fixed set of attributes. The system requires manual feature extraction, and then fits these features into the data schema. Their data model and virtual video browser do not support queries related to the temporal ordering of scenes. • Smoliar and Zhang [22] used a frame-based knowledge base method to support retrieval.
9. lappuse - Tanaka [18] proposed a schemeless object-oriented model. Their model allows users to (1) identify an arbitrary video frame sequence (a meaningful scene) as an independent object, (2) describe its contents in a dynamic and incremental way, (3) share descriptional data among video objects, and (4) edit author and abstract video objects. As their model is schemeless, the traditional class hierarchy of the object-oriented approach is not assumed as a database schema.
53. lappuse - F. Arman, A. Hsu, and MY Chiu, "Image processing on compressed data for large video database,
53. lappuse - Chabot: Retrieval from a Relational Database of Images", em IEEE Computer Magazine, September 1995, pp40-48. [5] E. Ardizzone, M. La Cascia and D. Molinelli, "Motion and Color Based Video Indexing and Retrieval", Intl.
27. lappuse - W. Xiong, JCM Lee, and RH Ma, "Automatic video data structuring through shot partitioning and key frame selection," Machine Vision and Application: Special issue on Storage and Retrieval for Still Image and Video Databases (1996), (submitted), (Technical Report HKUST-CS96-13). 26. M. Yeung, BL Yeo, W. Wolf, and B. Liu, "Video browsing using clustering and scene transitions on compressed sequences,
9. lappuse - Bimbo et al. [2] used Spatio-Temporal Logic to support the retrieval by content of video sequences through visual interaction. Temporal Logic is a language for the qualitative representation of ordering properties in the execution sequences of temporal systems. In their database, video sequences are stored along with a description of their contents in Spatio-Temporal Logic. Retrieval is supported through a 3D iconic interface. • Little et al.
26. lappuse - A. Nagasaka, T. Miyatake, and H. Ueda, "Video retrieval method using a sequence of representative images in a scene," in Proceedings of IAPR Workshop on Machine Vision Applications, Kawasaki, Japan, Dec.

Atsauces uz šo grāmatu

Bibliogrāfiskā informācija