Indexing and retrieval of video based on spatial relation sequences

Abstract

An important aspect of video data is its spatio-temporal aemantics. The relative positions and movements of the “interesting” objects in a video segment constitute a crucial component of the information to be retrieved in a multimedia database system. This is due to the dependency of the complex content descriptions on the apatio-temporal features. This paper addresses this challenge and provides an efficient technique for video data retrieval using descriptions of relative object movements. Such descriptions are used for content-baaed retrieval processing baaed on a graphical representation, named Coordinate Valued Neighborhood Graph.