| 基于空间转换网络的视频盲水印方法 |
| |
| 作者姓名： | 胡 海 李叶凡 王 晗 邹 玲 |
| |
| 作者单位： | (1. 武警部队参谋部作战勤务保障大队，北京 100089；
2. 北京林业大学信息学院，北京 100083；
3. 北京电影学院数字媒体学院，北京 100088) |
| |
| 基金项目： | 北京市教育委员会科研计划项目(KM201910050001)；国家自然科学基金项目(61902201) |
| |
| 摘 要： | 提出并实现了一种基于空间转换网络(STN)的视频盲水印方法。针对目前视频水印
不能同时抵抗噪声、压缩等信号处理攻击和缩放、剪切等几何攻击的问题，设计一个子块水印
嵌入机制，并依赖 STN 确定水印嵌入子块区域以及空间变换系数。选择变换域中的中频系数作
为嵌入通道，通过空间变换系数矫正旋转和缩放后的图像已获得鲁棒视频水印方法。实验结果
表明，基于 STN 的视频盲水印方法具有较高的视觉隐蔽性以及较强的稳定性和鲁棒性，同时嵌
入水印容量达到 256 位以上。
|
| 关 键 词： | 版权保护 空间转换网络 数字水印 离散余弦变换 视频盲水印 |
Video blind watermarking via spatial transformer networks |
| |
| Authors: | HU Hai LI Ye-fan WANG Han ZOU Ling |
| |
| Affiliation: | (1. Operations and Services Group of PAP Staff, Beijing 100089, China;
2. Beijing Forestry University, School of Information Science and Technology, Beijing 100083, China;
3. Digital Media School, Beijing Film Academy, Beijing 100088, China) |
| |
| Abstract: | This paper presented a novel adaptive video watermarking algorithm based on spatial
transformer networks. An adaptive video watermarking was embedded into a block detected by the
attention model from spatial transformer networks to resist noise and compress attacks, as well as the
geometric attack. According to the attention mechanism derived from the masking behavior of the
human perceptual model, a visual saliency block was extracted for further watermarking embedding.
Experimental results show that the watermarked video is highly imperceptible and resistant to many
degradations and distortions of video, and reaches over 256 bits in watermark capacity. |
| |
| Keywords: | copyright protection space transformation network digital watermarking discrete cosine transform video blind watermarking |
|
| 点击此处可从《》浏览原始摘要信息 |
|
点击此处可从《》下载全文 |
