Shot boundary detection method based on a new extensive dataset and mixed features

TL;DR

This paper introduces a new shot boundary detection method utilizing multiple video features, tested on an extensive dataset, achieving high accuracy and outperforming existing methods.

Contribution

The paper presents a novel shot boundary detection algorithm based on combined features and validated on a larger, more diverse dataset than previous benchmarks.

Findings

Achieved a final F-score of 0.9794 in shot boundary detection.

Outperformed existing methods on multiple datasets.

Utilized a diverse dataset exceeding TRECVID in size.

Abstract

Shot boundary detection in video is one of the key stages of video data processing. A new method for shot boundary detection based on several video features, such as color histograms and object boundaries, has been proposed. The developed algorithm was tested on the open BBC Planet Earth [1] and RAI [2] datasets, and the MSU CC datasets, based on videos used in the video codec comparison conducted at MSU, as well as videos from the IBM set, were also plotted. The total dataset for algorithm development and testing exceeded the known TRECVID datasets. Based on the test results, the proposed algorithm for scene change detection outperformed its counterparts with a final F-score of 0.9794.