蒋卫祥,李 功.基于一类神经网络的视频异常事件检测方法[J].电子测量与仪器学报,2021,35(7):60-65 |
基于一类神经网络的视频异常事件检测方法 |
One-class neural network for video anomaly detection and localization |
|
DOI: |
中文关键词: 视频监控 异常事件 一类神经网络 深度学习 自编码网络 |
英文关键词:video surveillance anomalous event one-class neural network deep learning auto-encoder |
基金项目:江苏省高等学校自然科学研究面上项目(19KJB520023)、常州信息职业技术学院智能制造边缘计算开放实验室项目(KYPT201802Z)资助 |
|
|
摘要点击次数: 236 |
全文下载次数: 1085 |
中文摘要: |
视频异常事件检测一直是一个具有挑战性的问题,现有的方法往往把视频特征提取和异常检测模型建立两个步骤独立
设计,导致方法无法达到最优。 针对该问题,设计了一种一类神经网络方法用于视频异常检测。 该方法结合了自编码器的逐层
数据表示形式能力以及一类分类能力,隐藏层的特征是针对异常检测的特定任务而构建的,从而获得了一个超平面以将所有正
常样本与异常样本分开。 实验结果表明,提出的方法在 PED 子集和 PED2 子集上分别达到了 94. 9%的帧级 AUC 和 94. 5%的帧
级 AUC,在 Subway 数据集上实现了 80 个正确事件检测,证实了该方法在工业和城市环境中的广泛适用性。 |
英文摘要: |
Due to the vague definition of abnormal events and the scarcity of its own samples, the detection of video abnormal events has
always been a challenging problem. Existing methods often separate the two steps of video feature extraction and anomaly detection model
establishment, it leads to the method that cannot reach the optimum. This paper follows the idea of distance-based anomaly detection,
and proposes a one-class neural network method for video anomaly detection. This method combines the layer-by-layer data representation
ability of the autoencoder and the one-class classification ability. The features of the hidden layer are constructed for the specific task of
anomaly detection, thereby obtaining a hyperplane to separate all normal samples from abnormal samples. The experimental results on
two benchmark data sets show that the proposed method achieves 94. 9% frame-level AUC and 94. 5% frame-level AUC on the PED
subset and PED2 subset, respectively, and achieves 80 correct event detections on the Subway dataset, confirming the wide applicability
of the method in industrial and urban environments. |
查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|