Robust Video Watermarking Approach Based on Crowdsourcing and Hybrid Insertion

Abstract

A novel robust video watermarking scheme is proposed in this paper, in which crowdsourcing technique is used to extract the most important regions from the original video. In fact, these regions are obtained by interacting with users and analyzing their behaviors while using an interactive interface where the summaries of the videos are given. The obtained regions are then detected in the mosaic frame of the video and merged with the region covered by all the moving objects in the mosaic. For the embedding step, a hybrid multi-signatures algorithm is proposed based on the two transforms DWT-SVD and the LSB method. Experimental results showed a high level of the visual quality of the watermarked videos thanks to the efficient choice of the embedded target, a good capacity, as well as a good robustness against the most important attacks like collusion and compression. In more, the comparative study carried out showed that the proposed algorithm exceeds the state of the art.