Towards Enhancing Keyframe Extraction Strategy for Summarizing Surveillance Video: An Implementation Study

The large amounts of surveillance video data are recorded, containing many redundant video frames, which makes video browsing and retrieval difficult, thus increasing bandwidth utilization, storage capacity, and time consumed. To ensure the reduction in bandwidth utilization and storage capacity to the barest minimum, keyframe extraction strategies have been developed. These strategies are implemented to extract unique keyframes whilst removing redundancies. Despite the achieved improvement in keyframe extraction processes, there still exist a significant number of redundant frames in summarized videos. With a view to addressing this issue, the current paper proposes an enhanced keyframe extraction strategy using k-means clustering and a statistical approach. Surveillance footage, movie clips, advertisements, and sports videos from a benchmark database as well as Compeng IP surveillance videos were used to evaluate the performance of the proposed method. In terms of compression ratio, the results showed that the proposed scheme outperformed existing schemes by 2.82%. This implies that the proposed scheme further removed redundant frames whiles retaining video quality. In terms of video playtime, there was an average reduction of 27.32%, thus making video content retrieval less cumbersome when compared with existing schemes. Implementation was done using MATLAB R2020b.