Motion Compensated Video Shot Detection using Multiple Feature Experts

In this fast developing technical era of digital technology, there is an explosion of video data especially on the internet. Organizing video and locating required information effectively and accurately presents a great challenge to the researchers. This demands a tool which would break down the video into smaller and manageable units called shots. A wide range of approaches have been investigated for shot detection but the accuracies still remained low. A sophisticated method need to be developed for achieving better results. We proposed an effective method which uses blockbased approach with motion compensation for edge and colour feature. We have used edge feature to capture the spatial details and colour feature to combat some of the shortcomings of using edge features. The performance of proposed method on various video genre are compared against the four most cited methods and the results are reported in terms of recall and precision. From the results it can be concluded that the propose method performs better than the others.