Abstract: Video content analysis is a system which can be used for retrieving the contents inside a video and indexing the video according to that. The advances in the data capturing, storage, and communication technologies have made vast amounts of video data available to consumer and enterprise applications. However, interacting with multimedia data, and video in particular, requires more than connecting with data banks and delivering data via networks to customers’ homes or offices. We still have limited tools and applications to describe, organize, and manage video data. The fundamental approach is to index video data and make it a structured media. Manually generating video content description is time consuming and thus more costly-to the point that it’s almost impossible. Moreover, when available, it’s subjective, inaccurate, and incomplete.We perceive a video program as a document. Video indexing should be analogous to text document indexing, where we perform a structural analysis to decompose a document into paragraphs, sentences, and words, before building indices. When someone authors a book, they create a table of contents for browsing the content’s order and a semantic index of keywords and phrases for searching by content. Similarly, to Facilitate fast and accurate content access to video data, we should segment a video document into shots and scenes to compose a table of contents, and we should extract key-frames or key sequences as index entries for scenes or stories. Therefore, the core research in content-based video retrieval is developing technologies to automatically parse video, audio, and text to identify meaningful composition structure and to extract and represent content attributes of any video sources.
Keywords: surveillance ,metadata,CBVR, skeletisation.