Video Cut Detection using Frame Windows

Segmentation is the first step in managing data for many information retrieval tasks. Automatic audio transcriptions and digital video footage are typically continuous data sources that must be pre-processed for segmentation into logical entities that can be stored, queried, and retrieved. Shot boundary detection is a common low-level video segmentation technique, where a video stream is divided into shots that are typically composed of similar frames. In this paper, we propose a new technique for finding cuts — abrupt transitions that delineate shots — that combines evidence from a fixed size window of video frames. We experimentally show that our techniques are accurate using the well-known trec experimental testbed.