Object-oriented conceptual modeling of video data

Abstract

In this paper, we propose a graphical data model for specifying spatio-temporal semantics of video data. The proposed model segments a video clip into subsegments consisting of objects. Each object is detected and recognized, and the relevant information of each object is recorded. The motions of objects are modeled through their relative spatial relationships as time evolves. Based on the semantics provided b y this model, a user can create his/her own object-oriented view of the video database. Using ihe propositional logic, we describe a methodology f o r specifying conceptual queries involving spatio-temporal semantics and expressing views f o r retrieving various video clips. Alternatively, a user can sketch the query, by examplifying the concept. The proposed methodology can be used to specify spatio-temporal concepts at various levels of information granularity.

Temporal Representation in Semantic Graphs

“…Later work used the MATM model as a data mining framework in order to extract information from traffic video sequences [13]. Much like the MATM model, the work of Day et al [17] proprosed an object-oriented approach to semantic modeling of video data, where a state in the transition network is represented by multiple nodes that represent objects in a video clip. In such a representation, queries posed on the graph deal with temporal interaction between objects in a video stream.…”

A Graph-Based Approach for Modeling and Indexing Video Data

“…[8,9,10,11,12,13,14,15,16,17]. Video data requires a pre-processing step before it is managed: for example, shot boundary detection, and region segmentation.…”

“…In order to address this issue, several efforts have been made to model video data using graph representation [10,13,14]. Graph is a powerful tool for data representation and classification in various fields, such as image processing, video analysis, and biomedical applications.…”

“…al. [14], which represents a semantically unbiased abstraction for video objects using a directed-graph model. In order to construct user-independent view and semantic heterogeneity of the video data, a VSDG is created to model spatio-temporal interactions among video objects.…”

Video event detection using motion relativity and visual relatedness

“…In [24], a motion pattern descriptor namely motion texture is proposed for video retrieval and the classification of simple camera and object motion patterns. In [8], spatio-temporal interactions between objects are expressed by predicate logic for video retrieval. This algorithm assumes the objects are correctly detected and located during video preprocessing.…”