Large-scale, Fast and Accurate Shot Boundary Detection through Spatio-temporal Convolutional Neural Networks

TL;DR

This paper introduces a fast, accurate shot boundary detection method using spatio-temporal CNNs, trained on a large synthetic dataset, outperforming existing methods in accuracy and speed.

Contribution

The paper presents a novel CNN-based SBD technique, a large synthetic dataset for training, and extensive evaluation demonstrating superior performance and speed.

Findings

Outperforms state-of-the-art in dissolve gradual detection

Achieves up to 11 times faster processing

Provides a large synthetic dataset for training CNNs

Abstract

Shot boundary detection (SBD) is an important pre-processing step for video manipulation. Here, each segment of frames is classified as either sharp, gradual or no transition. Current SBD techniques analyze hand-crafted features and attempt to optimize both detection accuracy and processing speed. However, the heavy computations of optical flow prevents this. To achieve this aim, we present an SBD technique based on spatio-temporal Convolutional Neural Networks (CNN). Since current datasets are not large enough to train an accurate SBD CNN, we present a new dataset containing more than 3.5 million frames of sharp and gradual transitions. The transitions are generated synthetically using image compositing models. Our dataset contain additional 70,000 frames of important hard-negative no transitions. We perform the largest evaluation to date for one SBD algorithm, on real and synthetic data, containing more than 4.85 million frames. In comparison to the state of the art, we outperform dissolve gradual detection, generate competitive performance for sharp detections and produce significant improvement in wipes. In addition, we are up to 11 times faster than the state of the art.