Matrix encoding for data hiding using multilayer video coding and transcoding solutions

摘要

This paper proposes a multitier data hiding solution in MPEG video using matrix encoding. In the first tier of the proposed solution, raw video is encoded into two layers using multilayer Signal to Noise Ratio (SNR) encoding. During the multilayer encoding process, the quantization scales and coding parameters are stored. In the second tier, message bits are embedded in the stored quantization scales using matrix encoding. In the third and last tier, the raw video is encoded again into two layers using the modulated quantization scales and coding parameters of the first encoder. The proposed multitier solution is extended by replacing the multilayer encoder with a multilayer transcoder to accommodate situations in which the video exists in pre-coded format only. By the use of multilayer encoder or transcoding, we show that the message payload can be doubled without adversely affecting the coding quality or bitrate of the host video. We also show that message embedding using matrix encoding can be extended to modulate motion vectors. The paper also proposes two solutions for motion vector modulation based on the availability of the raw video. In comparison to existing work, the proposed solutions have higher message payloads, lower degradation in video quality and result in reduced excessive bitrate.