A robust multi-feature cut detection algorithm for video segmentation

Abstract

Video segmentation is the first task in almost all video analysis applications. It consists in identifying the boundaries of the meaningful video units (shots). Without a doubt, cuts are the most common among production effects that characterize the shot boundaries. In this paper we propose an algorithm for cut detection exploiting an innovative, robust frame difference measure. The measure is based on a combination of different visual features. To improve the precision of the cut detection algorithm, a temporal pattern analysis model, and a flashes removal are also proposed. Experimental results to prove the effectiveness of the proposed measure coupled with the temporal pattern analysis model on very heterogeneous and complex sets of videos are critically reported.

Temporal segmentation tool for high-quality real-time video editing software

“…In this way, by taking the advantages of each one of the combined techniques, high quality results are obtained [24].…”

Segmentación de Secuencias de Vídeo: análisis y desarrollo de estrategias para la detección de cambios de toma y para la detección de objetos móviles

“…Por último, otra de las alternativas utilizadas en otros trabajos es la que consiste en hacer uso de diferentes técnicas de forma simultánea (Lee et al, 2000) (Sánchez y Binefa, 2003) (Ciocca, 2010). De ese modo, al aprovechar las ventajas de cada una de las técnicas que combinan, se consiguen resultados de gran calidad.…”