基于非局部3D残差网络的视频指纹算法  

Video Fingerprinting Algorithm Based on Non-local 3D Residual Network

作　　者：郭辰 李新伟[1] 杨艺[1] 徐良浩 GUO Chen;LI Xinwei;YANG Yi;XU Lianghao(School of Electrical Engineering and Automation,Henan Polytechnic University,Jiaozuo,Henan 454000,China)

机构地区：[1]河南理工大学电气工程与自动化学院,河南焦作454000

出　　处：《计算机工程与应用》2020年第19期216-223,共8页Computer Engineering and Applications

基　　金：国家自然科学基金(No.61402152,No.61403130);河南理工大学博士基金(No.B2013-022);河南省科技攻关项目(No.192102210099)。

摘　　要：为了实现视频拷贝的快速准确检索,提出一种基于非局部3D残差网络的紧凑视频指纹。该算法以三胞胎网络架构为基础,采用非局部模块3D残差网络同时捕获视频的全局与局部时空信息,在特征提取部分末端加入量化编码层,实现了原始视频数据到离散指纹码的端到端映射;设计了由角度关系三元组损失和量化误差损失组成的网络目标函数。大量的实验结果表明,与对比算法相比,该算法在保持紧凑的同时鲁棒性与独特性均表现突出,查准率与查全率有明显提升。In order to realize fast and accurate retrieval of video copies, this paper proposes a compact video fingerprint based on non-local 3 D residual network. Based on the triplet network architecture, the algorithm uses the non-local block3 D residual network to simultaneously capture the global and local spatio-temporal information of the video, and adds the quantization coding layer at the end of the feature extraction part to realize end-to-end mapping of raw video data to discrete fingerprint codes. A large number of experimental results show that compared with the comparison algorithm, the algorithm is outstanding in terms of robustness and uniqueness while maintaining compactness, and the precision and recall rate are significantly improved.

关 键 词：视频指纹 非局部模块 3D残差网络 三元组损失 量化误差损失 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TP183[自动化与计算机技术—控制科学与工程]