Automated video production system and method

摘要

The invention provides a method and system for the automated post production of a single video file, the method comprising the steps of gathering video data from a plurality of camera sources; gathering audio data from a plurality of microphone sources; using an automated tracking offline algorithm to track a sound emitting from a moving target object in a 3D space, to provide localization data of said target object to identify an optimum camera source to provide video data of said target object; and composing a composite video sequence of said moving target from a plurality of identified optimum camera sources in a single video file. The algorithm relies on both video data from multiple camera views and audio data from multiple microphone arrays to infer the 3D position of the active speaker over the duration of the captured presentation.

主权项

1. A method for the automated production of a single video file from a multi-view video capture, the method comprising the steps of:
i) gathering video data from a plurality of camera sources; ii) gathering audio data from a plurality of microphone sources; iii) using audio and video information to automatically locate and track a moving target object in a 3D space, so as to determine the region occupied by the said target object in each available camera; iv) determining from the identified regions in each camera view, the most optimum view of said target object; v) modelling skin colour under varying illumination; vi) analysing 3D foreground denoting possible target object occupancy from which individual regions of the foreground can be determined through a 3D connect component and shape analysis; and vii) composing a single view video sequence consisting of a user defined main view and an automatically inserted optimum view of said target object over the duration of the video capture.