Paper Info
Title
A Knowledge-Based Approach To Domain-Specific Compressed Video Analysis
Abstract
In this paper, a novel approach to domain-specific video analysis is proposed. The proposed approach is based oil exploiting domain-specific knowledge in the form of in ontology to detect video object, corresponding to the semantic concepts defined in the ontology. The association between the Visual objects and the defined semantic concepts is performed by taking into account both qualitative attributes of the semantic objects (e.g. color homogeneity), indicating necessary preprocessing methods (color clustering respectively), and numerical data generated via training (e.g. color models, also defined in the ontology). To enable fast and efficient processing, this methodology is applied to MPEG-2 video, requiring only its partial decoding. The proposed approach is demonstrated in the domain of Formula-1 racing video and shows promising results.
Year
DOI
Venue
2004
10.1109/ICIP.2004.1418760
ICIP: 2004 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOLS 1- 5
Keywords
Field
DocType
knowledge base,knowledge based systems,learning artificial intelligence,data compression,color model
Computer vision,Block-matching algorithm,Video post-processing,Pattern recognition,Computer science,Motion compensation,Multiview Video Coding,Knowledge-based systems,Video tracking,Artificial intelligence,Smacker video,Video compression picture types
Conference
ISSN
Citations 
PageRank 
1522-4880
1
0.35
References 
Authors
12
3
Name
Order
Citations
PageRank
Vasileios Mezaris180381.40
Ioannis Kompatsiaris21404197.36
Michael Gerasimos Strintzis31171104.83