Extraction of Semantic Video Content using Ontology Model
N. H. Angela Lincy, K. Selva · 2014
Video-based applications has recently revealed the need for extracting the content in videos. Raw data and low-level features alone are not sufficient to fulfill the user 's needs; that is, a deeper understanding of the content at the semantic level is required. Currently, manual techniques, which are inefficient, subjective and costly in time and limit the querying capabilities, are being used to bridge the gap between low-level representative features and high-level semantic content. In this proposal, a semantic content extraction system that allows the user to query and retrieve objects, events, and concepts are extracted. An ontology-based video semantic content model that uses spatial/temporal relations in event and concept definition is introduced here. This metaontology definition provides a wide-domain applicable rule construction standard that allows the user to construct an ontology for a given domain. In addition to domain ontologies, additional rule definitions (without using ontology) are used to lower spatial relation computation cost and to be able to define some complex situations more effectively. Genetic Algorithm-based object extraction method is integrated to capture and classify the semantic content. Thus by using this proposal, the objects, events and concepts of videos are extracted more accurately.