Digital video segmentation

TLDR

Video segmentation has traditionally used data‑driven bottom‑up methods that ignore inherent video structure. This study adopts a model‑driven approach to digital video segmentation. The authors formulate mathematical models based on production techniques, classify edit effects, design feature detectors, and cast segmentation as a feature‑based classification problem. Experiments on cable TV programs show successful segmentation of cuts, fades, dissolves, and page‑translate edits.

Abstract

The data driven, bottom up approach to video segmentation has ignored the inherent structure that exists in video. This work uses the model driven approach to digital video segmentation. Mathematical models of video based on video production techniques are formulated. These models are used to classify the edit effects used in video and film production. The classes and models are used to systematically design the feature detectors for detecting edit effects in digital video. Digital video segmentation is formulated as a feature based classification problem. Experimental results from segmenting cable television programming with cuts, fades, dissolves and page translate edits are presented.