Video Shot Boundary Detection Based on Color Histogram

In TREC 2003 Video Track, the Digital Television Center of La Salle School of Engineering, Ramon Llull University, participated in the shot boundary detection task. In this paper we present a method for video shot boundary detection based on color histogram differences. The technique is able to differentiate abrupt shot boundaries by the analysis of color histogram differences and smooth shot boundaries by temporal color variation. The aim of the method is to provide a simple and fast algorithm able to work in real-time with reasonable high performances in a video indexing tool. In this paper we give an overview of the approaches and a summary of the results. The obtained results show that although the computational cost is reduced this fact does not prevent the method from having an overall precision of 84.7% and a recall of 80.6%.