FKM Based Approach for Hybrid Video Segmentation

Abstract

In digital storage media, Video segmentation is one of the popular and important techniques.The challenging problem in digital storage media is video segmentation. In this hybrid video segmentation technique, initially similar shots are segmented. Then subsequently the track frames in every shot are assorted using the extracted objects of every frame which highly mostly reduces the processing time. Here it yields the effective video segmentation results by performing intersection on the segmented results provided by both the frame difference method as well as consecutive frame intersection method. In frame difference method, it considers the key frame as background and it segments the dynamic objects whereas in the frame difference method, it segments the static and dynamic objects by intersection of objects in consecutive frames. This new hybrid video segmentation technique is developed using FKM clustering approach and is evaluated by varying video sequences and then efficiency is analyzed by calculating the statistical measures and kappa coefficient.