Watermarking-based content authentication of motion-JPEG sequences

Content authentication has become an important issue for surveillance video. This paper presents a watermarking system based on Discrete Cosine Transform (DCT) for Motion-JPEG video authentication. To protect the integrity of the video object, a content-based watermark is embedded into the frames of the video. Robust watermark and semi-fragile watermark are used for temporal authentication and spatial authentication respectively. For analysis and evaluation, the system trades-off the robustness and the visual quality of the watermarked frames. The results show that the authentication rate almost reaches 100% in temporal authentication and is more than 98% in spatial authentication when the PSNR of watermarked frames is 36dB. It can robust to 55% JPEG compression and additive white Gaussian noise with variance of 0.002.