Real time and non real time video shot boundary detection using dual tree complex wavelet transform

Abstract

The innovation being done in multimedia streams from last few years necessitates the development of efficient and more effective methodologies for storing information related to video, audio, text etc. Accessing of content based video data requires segmentation of each video stream into its primary blocks. The video stream consists of a number of shots, each sequence of frames are represented using a single camera. Switching from one frame to another indicates the transition from a shot to the next one. Therefore, the detection of these transitions, known as scene change or shot boundary detection, is the first step in any video-analysis system. A number of proposed techniques for solving the problem of shot boundary detection exist, but the major challenges to them are their ineffectiveness and lack of dependability. The reliability of the scene change detection stage is a very significant requirement because it is the initial stage in any video retrieval system. Thus, its performance has a direct impact on the performance of all other stages. On the other hand, efficiency is also crucial due to the voluminous amounts of information found in video streams. In this paper, a new robust and efficient paradigm capable of detecting transitions in AVI videos is tested.