Gradual shot transition detection based on multidimensional clustering

Detection of shot transitions in video material is a process intended to ease the automatic extraction of video features for later use in indexing and retrieval purposes. While abrupt shot transitions are discontinuities quite easy to detect, the gradual ones are highly masked by and confused with object motion, camera operation, and other disturbing effects. Current approaches to detecting gradual transitions are based on the calculation of several inter-frame distances, and on the compensation and detection of the aforementioned causes of disturbance. This article presents an innovative detection method based on a multi-parameter modeling of the patterns that these transitions produce over a simple inter-frame distance, which opens the possibility of a later multi-dimensional classification of the desired transitions into a single cluster.