结合模式记忆和自监督注意力的人群异常行为检测方法
Method of crowd anomaly behavior detection combining pattern memory and self-supervised attention mechanism
宁冬梅 1梁莉2
作者信息
- 1. 南昌理工学院计算机信息工程学院,江西南昌 330029
- 2. 成都理工大学 数理学院,四川 成都 610059
- 折叠
摘要
为实现复杂环境下监控视频中异常事件的快速检测和准确定位,提出一种结合正常模式记忆和自监督注意力机制的异常检测框架.记忆机制综合考虑正常模式的多样性和差异性,解决卷积神经网络(CNN)泛化性过强的问题.自监督模块包含遮罩卷积层和通道注意力层,通过遮罩信息预测的自监督训练,提高模型对全局特征结构的理解.公开数据集的实验结果表明,所提方法的曲线下面积(AUC)指标分别达到92.6％和82.7％,性能优于当前其它先进的视频异常检测方法,在轨迹检测标准(TBDC)和区域检测标准(RBDC)指标中表现出优秀的异常跟踪和定位能力.
Abstract
To achieve fast detection and accurate localization of abnormal events in surveillance videos in complex environments,an anomaly detection framework combining normal pattern memory and self-supervised attention mechanism was proposed.The memory mechanism comprehensively considered the diversity and difference of normal patterns,and limited the generalization ability of convolutional neural network(CNN).The self-supervised module consisted of a masked convolutional layer and a chan-nel attention layer,and improved the understanding of global feature hierarchy through self-supervised training of masked infor-mation prediction.Experimental results on public datasets show that the area under the curve(AUC)performance of the pro-posed method reaches 92.6％and 82.7％,respectively,outperforming other state-of-the-art anomaly detection methods,and the trajectory-based detection criterion(TBDC)and region-based detection criterion(RBDC)results validate that the proposed method has excellent anomaly tracking and localization ability.
关键词
人群异常行为检测/自监督注意力/卷积神经网络/遮罩卷积/全局特征结构/轨迹检测标准/区域检测标准Key words
crowd anomaly behavior detection/self-supervised attention/convolutional neural network/masked convolution/global feature hierarchy/trajectory-based detection criterion/region-based detection criterion引用本文复制引用
基金项目
江西省科技厅科学技术研究基金项目(GJJ212111)
出版年
2024
NETL
NSTL
万方数据