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 seg- mentation. 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 pro- duction. The classes and models are used to systematically design the feature detectors for detecting edit effects in digi- tal video. Digital video segmentation is formulated as a fea- ture based classification problem. Experimental results from segmenting cable television programming with cuts, fades, dissolves and page translate edits are presented.