何丹丹
江南大学轻工过程先进控制教育重点实验室 ??无锡 ??214122
基金项目:国家自然科学基金(61573168)
详细信息
作者简介:陈莹：女，1976年生，教授，博士生导师，主要研究方向为信息融合、模式识别等
何丹丹：女，1993年生，硕士生，研究方向为异常行为检测
通讯作者:陈莹 chenying@jiangnan.edu.cn
中图分类号:TP391计量
文章访问数:2617
HTML全文浏览量:672
PDF下载量:70
被引次数:0
出版历程
收稿日期:2018-05-07
修回日期:2019-01-29
网络出版日期:2019-02-20
刊出日期:2019-05-01
Spatial-temporal Stream Anomaly Detection Based on Bayesian Fusion
Ying CHEN,,Dandan HE
Key Laboratory of Advanced Control Education in Light Industry Process, Jiangnan University, Wuxi 214122, China
Funds:The National Natural Science Foundation of China (61573168)
摘要
摘要:针对直接利用卷积自编码网络未考虑视频时间信息的问题，该文提出基于贝叶斯融合的时空流异常行为检测模型。空间流模型采用卷积自编码网络对视频单帧进行重构，时间流模型采用卷积长短期记忆(LSTM)编码-解码网络对短期光流序列进行重构。接着，分别计算空间流模型和时间流模型下每帧的重构误差，设计自适应阈值对重构误差图进行二值化，并基于贝叶斯准则对空间流和时间流下的重构误差进行融合，得到融合重构误差图，并在此基础上进行异常行为判断。实验结果表明，该算法在UCSD和Avenue视频库上的检测效果优于现有异常检测算法。
关键词:异常行为检测/
贝叶斯融合/
时空流
Abstract:Focusing on the problem that convolutional auto-encoder network based anomaly detection ignores time information, a novel anomaly detection model based on Bayesian fusion of spatial-temporal stream is proposed. A convolution auto-encoder network is used in spatial stream model to reconstructs video frames, and a convolutional Long Short-Term Memory (LSTM) encoder-decoder network is used to reconstruct short-term optical sequence in the temporal stream model. Then, the reconstruction errors under spatial and temporal stream are calculated separately. Meanwhile, an adaptive thresholds is designed to obtain the reconstruction binary error maps. Finally, the Bayesian fusion strategy is developed to combine the reconstruction error of spatial and temporal stream to obtain the final fusion reconstruction error map based on which the abnormal behavior can be determined. Experimental results show that the proposed algorithm is superior to the existing anomaly detection algorithms in UCSD and Avenue datasets.
Key words:Anomaly detection/
Bayesian fusion/
Spatial-temporal stream
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=82328c83-9a67-4289-90a0-19235df1e1ff
