| Static video summarization approach using Binary Robust Invariant Scalable Keypoints |
| Paper ID : 1016-ICCI2021 |
| Authors: |
|
Eman Morad1, Sameh Zarif2, Khalid Amin *1 1Information technology department, Faculty of Computers and Information, Menoufia University Menoufia, Egypt 2Information Technology department, Faculty of computers and information |
| Abstract: |
| In recent times, the continuous demand and the creation of digital video information have led to the increasing growth of digital video content. The need for rapid browsing of large amounts of data and content indexing and retrieval of video requires effective and advanced analysis techniques, due to the very slow presence in the browsing and retrieval of multimedia sources. Video summarization techniques have been proposed to rapidly browse, index, and access large video collections. In this paper, we propose a new video summarization method based on binary descriptors. The proposed method extracts key points and descriptors using a Binary Robust Invariant Scalable Keypoints (BRISK), a Brute-force method that is used for matching bit-string binary descriptors between two successive frames. And keyframes are extracted as the middle frame of each shot. Experiments were conducted on open video project data sets of various genres. The Comparison of User Summaries (CUS) evaluation metric is used to evaluate the proposed method by measuring the accuracy rate, error rate and compare it with other methods. Experimental results indicate that the proposed algorithm produces competitive results when compared with other methods. |
| Keywords: |
| Video summarization shot boundary detection, keyframe extraction, Binary Robust Invariant Scalable Keypoints (BRISK), |
| Status : Paper Accepted |
