Towards Scalable Automated Analysis of Digital Video Assets for Content Quality Control Applications

摘要

A significant component of typical post production workflows in current entertainment industry relies on expensive human involvement for spatio- temporal analysis of digital video assets. Hence there exists a well-befitting requirement for automating such workflows, so that human effort can be further channelized into the creative aspects of the post-production process. In this paper, we identify two such problems which video content quality inspectors frequently encounter. These are namely (a) Shot change detection, and (b) Dead or stuck pixel detection. The former involves identifying precise temporal boundaries of cinematographic content in order to analyze quality of cuts, while the latter is useful for localizing and correcting spatial anomalies that emerge during the image acquisition step due to faulty sensors. To address the aforementioned, we devise two novel data-driven approaches and demonstrate their portability, scalability and efficacy through two respective cloud computing based implementations. Our approaches show promising results on our in-house dataset of a large number of movie titles indicating their effectiveness.