基于图像处理的人员异常行为监测设计

通过对人员异常行为有效的监测算法设计,提高视频监控和异常事故的智能识别能力。传统的人员异常行为监测算法采用视频步进跟踪学习方法,由于人员的随机性和不确定性,导致视觉识别效果不好。基于图像处理理论,提出一种基于视频帧图像阵列像素检测的人员异常行为监测算法,进行了人员异常行为特征数据采集模型设计,得到基于双相机视频监控的人员异常行为视觉特征采集模型,采用视频帧图像阵列像素检测算法,进行异常行为特征提取,得到邻域灰度值向量之间像素点为平均结构相似性聚类中心,计算人员异常行为检测全图所有像素点的加权平均位置的估计值,实现人员异常行为监测算法改进。仿真结果表明,采用该算法进行人员异常行为特征监测,能实现对特定异常人员的准确定位和清晰识别,异常检测概率较高,性能优越,在安防监控系统设计等领域具有较好的应用价值。     

基于视频车辆运动轨迹场的交通事件检测方法*

针对现有交通事件检测算法存在的模型复杂、运算量大,并且检测结果滞后的缺点,提出了一种基于视频车辆运动轨迹场的交通事件检测方法.该方法以基于视频的车辆跟踪轨迹为基础,形成正常车辆运动轨迹场,进而将当前车辆轨迹矢量与正常轨迹场矢量比较,最终实现了对超速、慢行、变道和逆行的异常交通事件的检测.研究结果表明,与传统方法相比,该方法算法简单,并且可以快速、准确地对异常交通事件进行检测.     

基于像素分析的轨迹异常车辆的识别法

交通异常情况检测一直是交通管理中的重要任务,其在智能交通系统中显得尤为重要。传统的检测方法首先对目标物体(行人和车辆)进行区分,然后再对提取的车辆进行轨迹异常判断。在车流量日益加剧的今天,此种方法增加了计算机的运算复杂度。针对上述算法计算量过于复杂的问题,本文提出了基于像素点的背景方法,首先结合隐含马尔可夫模型(Hidden Markov Model)和共发模型(Co-occurences model),对视频中的异常像素点进行判断,然后通过仿三维模型车辆进行识别的方法,对由异常像素点组成的车辆进行最终的识别。实验结果表明该算法具有较强的有效性和在智能交通系统中有较好的应用。     

基于3D卷积自编码器的视频异常行为检测

视频异常行为检测是目前计算机视觉领域的热点问题之一.然而,由于异常行为难以具体定义,使得基于监督学习的二类分类方法难以应用在该领域.本文提出了一种无监督的视频异常检测模型,称之为基于时空特征融合的3D自编码器模型(ST-3DCAE).模型采用PWCNet提取场景光流特征图,并与原视频帧融合作为基本单元,由多个基本单元组成连续基本单元作为模型的输入;利用3DConv和ConvLSTM模块进行时空特征的自主提取,3DSEblock模块进行重要特征的筛选;最终,通过输入数据和自编码器重建视频块之间的重建误差,来判断视频是否出现异常行为.通过在UCSD、Avenue等公开数据集上进行验证,实验结果的定性和定量分析证明了本方法具有较好的性能.     

基于异常检测与双流编码的视频监控系统设计

介绍了一种基于异常检测与双流编码的无线智能视频监控系统的设计方案.该系统首先基于对采集视频的分析,实现非法入侵等异常事件的自动检测,同时通过对同一路视频采用两个编码器进行双流编码,产生两路不同质量和码率的视频流.在此基础上,基于异常事件检测的结果,在有异常事件时触发高质量图像的本地保存和低码率图像的实时无线传输.在蜂窝...     

基于双流网络与多示例学习的异常事件检测

面对当前复杂场景下异常事件检测算法过度依赖帧级别标记,以及I3D模型耗时长、内存占用大等问题,设计了一种基于I3D的M-I3D模型并将其作为特征提取器,提出一种了基于深度时空特征和多示例学习的异常检测方法.所提方法将正常视频和异常视频作为包,并将视频片段作为多示例学习中的示例.利用M-I3D模型提取每个视频片段的特征,并将提取到的特征向量输入到三层全连接层中,进而自动学习一个深度异常排序模型,该模型可以预测异常视频片段的分数.此外,为了在训练过程中较好地定位异常,在排序损失函数中引入稀疏函数和约束性函数.结果 表明,与其他方法相比,所提算法在UCF-Crime数据集上具有更高的准确率和更好的实时性.     

基于贝叶斯融合的时空流异常行为检测模型

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。     

显著性光流直方图字典表示的群体异常事件检测

在视频监控系统已被广泛应用的今天,基于监控视频的群体异常事件检测已成为保障社会安全的迫切需要,越来越受到人们的重视。该文基于这一现状,提出了一个新的群体异常事件检测方案,实现对监控视频自动高效的检测。在特征提取方面,提出了显著性光流直方图特征描述符,并利用该特征描述符构建字典;在字典优化方面,提出了基于聚类的多字典组合学习框架,将原始的大字典分为多个子字典;最后,对于测试样本,找出最适合的子字典并计算测试样本在该子字典下的重建误差,即可判断测试样本是否异常。在两个数据集上的实验表明,与其它方法相比,该文提出的方法对拥挤场景下监控视频中的群体异常事件检测取得了较好的检测性能。      

一种基于光流法的逆行异常事件检测方法

机场大厅、公路等公共场合,经常需要行人或车辆单向运动,以保障开放环境的安全性及秩序性.对监控视频中的逆行异常事件进行检测,便于管理人员及时对可疑事件做出处理.提出了一种逆行异常事件的检测算法,它基于图像中特征点的光流场以及空间分布特性对特征点进行聚类,然后通过计算符合逆行条件的特征点数量实现对逆行异常事件的检测.理论分...     

基于注意力机制的高光谱图像异常目标检测

在航拍视频运动目标检测中，受到场景复杂度和目标多元化因素影响，导致目标检测精度受限，提出基于注意力机制的高光谱图像异常目标检测方法。建立多背景建模约束下的高光谱视频图像采集和参数识别模型，采用场景变化自适应跟踪方法分析目标运动特征参数，提取运动目标高光谱图像的感知场景背景信息、孤立像素点以及边缘特征量，根据孤立像素点的离群特性，采用注意力机制融合判断方法，提取高光谱图像异常目标点的差异性特征值，采用模糊度特征匹配和场景稠密度色彩分割方法，实现高光谱图像异常目标的动态检测和分离。仿真测试结果表明，采用该方法进行高光谱图像异常目标检测，在虚警率为0.09,检测概率0.94时达到了最好的检测效果，检测的平均耗时为16.34 s。     

面向异常检测的人体行为聚类

We presented a novel framework for automatic behavior clustering and unsupervised anomaly detection in a large video set. The framework consisted of the following key components: 1) Drawing from natural language processing, we introduced a compact and effective behavior representation method as a stochastic sequence of spatiotemporal events, where we analyzed the global structural information of behaviors using their local action statistics. 2) The natural grouping of behavior patterns was discovered through a novel clustering algorithm. 3) A run-time accumulative anomaly measure was introduced to detect abnormal behavior, whereas normal behavior patterns were recognized when sufficient visual evidence had become available based on an online Likelihood Ratio Test (LRT) method. This ensured robust and reliable anomaly detection and normal behavior recognition at the shortest possible time. Experimental results demonstrated the effectiveness and robustness of our approach using noisy and sparse data sets collected from a real surveillance scenario.     

Detecting spatiotemporal irregularities in videos via a 3D convolutional autoencoder

Spatiotemporal irregularities (i.e., the uncommon appearance and motion patterns) in videos are difficult to detect, as they are usually not well defined and appear rarely in videos. We tackle this problem by learning normal patterns from regular videos, while treating irregularities as deviations from normal patterns. To this end, we introduce a 3D fully convolutional autoencoder (3D-FCAE) that is trainable in an end-to-end manner to detect both temporal and spatiotemporal irregularities in videos using limited training data. Subsequently, temporal irregularities can be detected as frames with high reconstruction errors, and irregular spatiotemporal patterns can be detected as blurry regions that are not well reconstructed. Our approach can accurately locate temporal and spatiotemporal irregularities thanks to the 3D fully convolutional autoencoder and the explored effective architecture. We evaluate the proposed autoencoder for detecting irregular patterns on benchmark video datasets with weak supervision. Comparisons with state-of-the-art approaches demonstrate the effectiveness of our approach. Moreover, the learned autoencoder shows good generalizability across multiple datasets.     

Unsupervised learning and mapping of active brain functional MRI signals based on hidden semi-Markov event sequence models

In this paper, a novel functional magnetic resonance imaging (fMRI) brain mapping method is presented within the statistical modeling framework of hidden semi-Markov event sequence models (HSMESMs). Neural activation detection is formulated at the voxel level in terms of time coupling between the sequence of hemodynamic response onsets (HROs) observed in the fMRI signal, and an HSMESM of the hidden sequence of task-induced neural activations. The sequence of HRO events is derived from a continuous wavelet transform (CWT) of the fMRI signal. The brain activation HSMESM is built from the timing information of the input stimulation protocol. The rich mathematical framework of HSMESMs makes these models an effective and versatile approach for fMRI data analysis. Solving for the HSMESM Evaluation and Learning problems enables the model to automatically detect neural activation embedded in a given set of fMRI signals, without requiring any template basis function or prior shape assumption for the fMRI response. Solving for the HSMESM Decoding problem allows to enrich brain mapping with activation lag mapping, activation mode visualizing, and hemodynamic response function analysis. Activation detection results obtained on synthetic and real epoch-related fMRI data demonstrate the superiority of the HSMESM mapping method with respect to a real application case of the statistical parametric mapping (SPM) approach. In addition, the HSMESM mapping method appears clearly insensitive to timing variations of the hemodynamic response, and exhibits low sensitivity to fluctuations of its shape.     

基于深度学习的网络异常检测和智能流量预测方法

边缘计算场景下,边缘设备时刻产生海量蜂窝流量数据,在异常检测任务中针对直接对原始数据检测异常存在的计算冗余问题,提出基于特征降维的蜂窝流量数据异常检测方法.该方法在全局范围内利用LSTM自编码器提取流量数据特征和标识异常网格,然后在存在可疑异常的网格使用K?means聚类进行局部异常确认,结果表明可以更好地检测出不同活...     

A multistage system to detect epileptiform activity in the EEG

A PC-based system has been developed to automatically detect epileptiform activity in 16-channel bipolar EEGs. The system consists of 3 stages: data collection, feature extraction, and event detection. The feature extractor employs a mimetic approach to detect candidate epileptiform transients on individual channels, while an expert system is used to detect focal and nonfocal multichannel epileptiform events. Considerable use of spatial and temporal contextual information present in the EEG aids both in the detection of epileptiform events and in the rejection of artifacts and background activity as events. Classification of events as definite or probable overcomes, to some extent, the problem of maintaining high detection rates while eliminating false detections. So far, the system has only been evaluated on development data but, although this does not provide a true measure of performance, the results are nevertheless impressive. Data from 11 patients, totaling 180 minutes of 16-channel bipolar EEGs, have been analyzed. A total of 45-71% (average 58%) of epileptiform events reported by the human expert in any EEG were detected as definite with no false detections (i.e., 100% selectivity) and 60-100% (average 80%) as either definite or probable but at the expense of up to 9 false detections per hour. Importantly, the highest detection rates were achieved on EEGs containing little epileptiform activity and no false detections were made on normal EEGs     

An Efficient Network Attack Visualization Using Security Quad and Cube

Security quad and cube (SQC) is a network attack analyzer that is capable of aggregating many different events into a single significant incident and visualizing these events in order to identify suspicious or illegitimate behavior. A network administrator recognizes network anomalies by analyzing the traffic data and alert messages generated in the security devices; however, it takes a lot of time to inspect and analyze them because the security devices generate an overwhelming amount of logs and security events. In this paper, we propose SQC, an efficient method for analyzing network security through visualization. The proposed method monitors anomalies occurring in an entire network and displays detailed information of the attacks. In addition, by providing a detailed analysis of network attacks, this method can more precisely detect and distinguish them from normal events.     

Saliency Combined Particle Filtering for Aircraft Tracking

Multimedia event detection has become a popular research topic due to the explosive growth of video data. The motion features in a video are often used to detect events because an event may contain some specific actions or moving patterns. Raw motion features are extracted from the entire video first and then aggregated to form the final video representation. However, this video-based representation approach is ineffective when used for realistic videos because the video length can be very different and the clues for determining an event may happen in only a small segment of the entire video. In this paper, we propose using a segment-based approach for video representation. Basically, original videos are divided into segments for feature extraction and classification, while still keeping the evaluation at the video level. The experimental results on recent TRECVID Multimedia Event Detection datasets proved the effectiveness of our approach.     

A new non-invasive method for valve stiction dection using wavelet technology

In this letter, we present a novel approach of valve stiction detection using wavelet tech-nology. A new non-invasive method is developed with the closed-loop normal operating data. The redundant dyadic discrete wavelet transform is used to decompose the data at different resolution scales. Based on the Lipschitz regularity theory, wavelet coefficients analysis across scales is performed to detect the jumps in the controlled variables. Adaptive wavelet de-noising is then applied to the data.Features of the valve stiction patterns are extracted from the de-noised data and the valve stiction probability is calculated.     

Mahalanobis Distance Based Approach for Anomaly Detection of Analog Filters Using Frequency Features and Parzen Window Density Estimation

Analog filters play a very important role in insuring the availability of electronic systems. Early detection of anomalies of analog filters can prevent the impending failures and enhance reliability. The complex architecture and the tolerances of multiple components make it very difficult to detect anomalies in analog filters. To address this concern, A Mahalanobis distance (MD) based anomaly detection method for analog filters is proposed in this paper. The conventional frequency features and the moment of frequency response are selected as the feature vector. Mahalanobis distance is used to transform the frequency feature vector to one dimensional MD data. The anomaly detection threshold is obtained based on probability density of the health MD data sets which is estimated by Parzen window density estimation method. The efficiency of the proposed method has been verified by two case studies. In the case studies, a comprehensive indicator constructed by miss alarm and false alarm is used to obtain an optimal anomaly detection threshold. One class SVM (OCSVM) based anomaly detection method is used as a comparison with our approach. The results illustrate that: (1) the proposed frequency features can effectively clarify the degradation of analog filters; (2) the proposed MD based approach can detect anomalies in analog filters effectively at an early time stage. (3) the proposed MD based approach can detect anomalies in analog filters more accurately than OCSVM based method.