A novel video forgery detection algorithm for blue screen compositing based on 3-stage foreground analysis and tracking

Abstract

Blue screen compositing is one of the most common methods to do video forgery. However, few algorithms have been proposed to detect the forgery in this form. This paper presents a 3-stage Foreground Analysis and Tracking algorithm (3FAT) to detect blue screen compositing. The 3FAT algorithm contains three major stages: foreground block extraction, forged block detection and forged block tracking. The first stage extracts the foreground blocks by a multi-pass foreground locating method. In the second stage, a feature-comparison level fusion of local features consisting of luminance and contrast is put forward to seek out the tampered foreground block. In the last stage, a fast target search algorithm based on Compressive Tracking is used to track the tampered block of subsequent frames. Compared with previous algorithm, 3FAT can not only rule out the distractions of noise and other moving foregrounds, but also be applied to any video format, bit rate and encoding mechanism. The experiments show that the 3FAT algorithm has higher accuracy and performs well in terms of speed.