There is an urgent need to extract key information from video automatically
for the purposes of indexing, fast retrieval, and scene analysis. To suppo
rt this vision, reliable scene change detection algorithms must be develope
d. Several algorithms have been proposed for both sudden and gradual scene
change detection in uncompressed and compressed video. In this paper some c
ommon algorithms that have been proposed for scene change detection are rev
iewed. A novel algorithm for sudden scene change detection for MPEG-2 compr
essed video is then presented. This uses the number of interpolated macrobl
ocks in B-frames to identify the sudden scene changes. A gradual scene chan
ge detection algorithm based on statistical features is also presented.