Gradual Transition Detection in Digital Videos using Area Correlation

Different research groups proposed numerous advancements in the field of video segmentation during last decade. Comparison of their work can be seen from TRECVID 2005. Most of the proposed methods are either computation intensive or too much false detection reduces their efficiency. In this work, a method based on region matching using area correlation is proposed. It can be used in prior to any other method to reduce the false detections. In this method, video frames are divided into different regions based on their statistical similarity. An area correlation energy function for each region in consecutive frames is used to detect the similarity among the regions. Weighted sum of correlation function in all the mismatched regions and location of these are used to classify the shots of video into different types such as hard cuts, fades, wipes etc,. This method is tested on different videos and reasonable performance is achieved