一种监控摄像机干扰检测模型

A surveillance camera tampering detection model

为减少监控干扰检测中因特殊场景引起的误检测,文中提出一种基于Siamese架构的SCG(Siamese with Convolutional Gated Recurrent Unit)模型,利用视频片段间的潜在相似性来区分特殊场景与干扰事件。通过在Siamese架构中融合改进ConvGRU网络,使模型充分利用监控视频的帧间时序相关性,在GRU单元间嵌入的非局部操作可以使网络建立图像空间依赖响应。与使用传统的GRU模块的干扰检测模型相比,使用改进的ConvGRU模块的模型准确率提升了4.22%。除此之外,文中还引入残差注意力模块来提高特征提取网络对图像前景变化的感知能力,与未加入注意力模块的模型相比,改进后模型的准确率再次提高了2.49%。

This paper proposes an SCG model based on Siamese network to reduce the detection error caused by some special scenes in camera tampering detection.The model can use the potential similarity between video clips to distinguish special scenes from tampering events.The improved ConvGRU network is integrated to capture the temporal correlation between the frames of surveillance video.We embed non-local blocks between GRU cells simultaneously,so the model can establish the spatial dependence of the image.The improved ConvGRU network improves model performance by 4.22%.We also add residual attention module to improve the perception ability of the model to the change of image foreground,this again improves the accuracy of the model by 2.49%.