基于时空关系网络的视频局部拷贝检测
首发时间:2019-03-08
摘要:视频局部拷贝检测任务旨在确定查询视频的一个或多个片段是否已在数据库中存在,同时给出相似部分的时间段信息。目前大多数有效的视频局部拷贝检测算法被设计为特征提取、特征匹配、时间对齐三个步骤,而特征匹配和时间对齐模块的分离一定程度上忽略了局部拷贝的时空相关信息,从而得不到满意的性能。为了减少这种损失,本文不是将其分解为两个独立的任务,而是在一个单一的卷积神经网络中联合处理这两个方面。首先,我们对视频帧采样并提取CNN特征,计算出源视频与查询视频的时空关系特征图,然后,将对该数组做图形化映射并训练基于RefineDet目标检测任务的卷积神经网络,最后,在查询阶段根据检测结果反推出局部拷贝的时间段。本文评估了该算法在真实复杂视频拷贝检测数据集VCDB上的性能指标,与现有的局部拷贝检测算法相比得到了明显的改善。
For information in English, please click here
Video partial copy detection based on spatio-temporal relationship network
Abstract:The task of partial copy detection in videos aims at determing if one or more segments of the query video are already present in the dataset,while giving the information of similar portion time period.At present, most effective algorithms of partial copy detection in videos are designed as three steps:feature extraction, feature matching and time alignment. The separation of feature matching and time alignment module ignores the spatio-temporal information of partial copy to some extent.Therefore, satisfactory performance is not obtained.In order to reduce this loss, this article does not decompose it into two separate tasks, but use a single convolutional neural network to solve these two aspects.First, we sample video frames and extract CNN features, calculate the spatio-temporal relationship matrix of the source video and the query video, and then graphically map the matrix and train the convolutional neural network based on the object detection task of the RefineDet model. Finally, In the query phase, the time period of the partial copy is deduced based on the detection result.In this paper,we evaluate the performance of the algorithm on the real complex video copy detection dataset VCDB which is significantly improved compared with the state-of-the-art partial copy detection algorithm.
Keywords: Partial copy detection in videos spatio-temporal relationship end to end
基金:
引用
No.****
动态公开评议
共计0人参与
勘误表
基于时空关系网络的视频局部拷贝检测
评论
全部评论0/1000