Hierarchical crowd analysis and anomaly detection

ObjectiveThis work proposes a novel approach to model the spatiotemporal distribution of crowd motions and detect anomalous events.MethodsWe first learn the regions of interest (ROIs) which inform the behavioral patterns by trajectory analysis with Hierarchical Dirichlet Processes (HDP), so that the main trends of crowd motions can be modeled. Based on the ROIs, we then build a series of histograms both on global and local levels as the templates for the observed movement distribution, which statistically describes time-correlated crowd events. Once the template has been built hierarchically, we import real data containing the discrete trajectory observations from video surveillance and detect abnormal events for individuals and for crowds.ResultsExperimental results show the effectiveness of our approach, which is able to analyze and extract the crowd motion information from observed trajectory dataset, and achieve the anomaly detection at the hierarchical levels.ConclusionThe proposed hierarchical approach can learn the moving trends of crowd both in global and local area and describe the crowd behaviors in statistical way, which build a template for pedestrian movement distribution that allows for the detection of time-correlated abnormal crowd events.     

Vision-based analysis of small groups in pedestrian crowds

Building upon state-of-the-art algorithms for pedestrian detection and multi-object tracking, and inspired by sociological models of human collective behavior, we automatically detect small groups of individuals who are traveling together. These groups are discovered by bottom-up hierarchical clustering using a generalized, symmetric Hausdorff distance defined with respect to pairwise proximity and velocity. We validate our results quantitatively and qualitatively on videos of real-world pedestrian scenes. Where human-coded ground truth is available, we find substantial statistical agreement between our results and the human-perceived small group structure of the crowd. Results from our automated crowd analysis also reveal interesting patterns governing the shape of pedestrian groups. These discoveries complement current research in crowd dynamics, and may provide insights to improve evacuation planning and real-time situation awareness during public disturbances.     

Shadow obstacle model for realistic corner-turning behavior in crowd simulation

This paper describes a novel model known as the shadow obstacle model to generate a realistic corner-turning behavior in crowd simulation. The motivation for this model comes from the observation that people tend to choose a safer route rather than a shorter one when turning a corner. To calculate a safer route, an optimization method is proposed to generate the corner-turning rule that maximizes the viewing range for the agents. By combining psychological and physical forces together, a full crowd simulation framework is established to provide a more realistic crowd simulation. We demonstrate that our model produces a more realistic corner-turning behavior by comparison with real data obtained from the experiments. Finally, we perform parameter analysis to show the believability of our model through a series of experiments.     

Identifying and facilitating social interaction with a wearable wireless sensor network

We have designed a highly versatile badge system to facilitate a variety of interaction at large professional or social events and serve as a platform for conducting research into human dynamics. The badges are equipped with a large LED display, wireless infrared and radio frequency networking, and a host of sensors to collect data that we have used to develop features and algorithms aimed at classifying and predicting individual and group behavior. This paper overviews our badge system, describes the interactions and capabilities that it enabled for the wearers, and presents data collected over several large deployments. This data is analyzed to track and socially classify the attendees, predict their interest in other people and demonstration installations, profile the restlessness of a crowd in an auditorium, and otherwise track the evolution and dynamics of the events at which the badges were run.     

Visual data mining for crowd anomaly detection using artificial bacteria colony

This paper presents a novel method for global anomaly detection in crowded scenes. The optical flow of frames is used to extract the foreground of areas with people motions in the crowd in the form of layers. The optical flow between two frames generates one layer. The proposed method applies the metaheuristic of artificial bacteria colony as a robust algorithm to optimize the extracted layers. Artificial bacteria cover all regions of interest that have high movement between frames. The artificial bacteria colony adapts quickly to the most varied scenarios. Moreover, the algorithm has low sensibility to noise and to sudden changes in video lighting as captured by optical flow. The bacteria population of the colonies, its food storage and the colony’s centroid position regarding each optical flow layer, are used as input to train a Kohonen’s neural network. Once trained the network is able to detect specific events based on behavior patterns similarity, as produced by the bacteria colony during such events. Experiments are conducted on available public dataset. The achieved results show that the proposed method captures the dynamics of the crowd behavior successfully, revealing that the proposed scheme outperforms the available state-of-the-art algorithms for global anomaly detection.     

Abnormal crowd behavior detection using high-frequency and spatio-temporal features

Abnormal crowd behavior detection is an important research issue in computer vision. The traditional methods first extract the local spatio-temporal cuboid from video. Then the cuboid is described by optical flow or gradient features, etc. Unfortunately, because of the complex environmental conditions, such as severe occlusion, over-crowding, etc., the existing algorithms cannot be efficiently applied. In this paper, we derive the high-frequency and spatio-temporal (HFST) features to detect the abnormal crowd behaviors in videos. They are obtained by applying the wavelet transform to the plane in the cuboid which is parallel to the time direction. The high-frequency information characterize the dynamic properties of the cuboid. The HFST features are applied to the both global and local abnormal crowd behavior detection. For the global abnormal crowd behavior detection, Latent Dirichlet allocation is used to model the normal scenes. For the local abnormal crowd behavior detection, Multiple Hidden Markov Models, with an competitive mechanism, is employed to model the normal scenes. The comprehensive experiment results show that the speed of detection has been greatly improved using our approach. Moreover, a good accuracy has been achieved considering the false positive and false negative detection rates.     

基于群体性行为模型的人群分析及其应用

基于视频分析的人群监控,涉及到获取人群行为和数量,这在智能监控领域具有重要的现实价值。本文建立基于运动特征的群体性行为模型,挖掘复杂人群场景中的群体行为,用于人群行为和数量的分析。群体性行为模型是一种主题模型（LDA）,通过样本学习,可以获得描述不同群体行为的特征集,用于人群分析。实验中,将群体性行为模型应用于挖掘监控场景下的不同人群行为及其特征集,并使用人工神经网络完成人数统计,统计正确率达到92.35%。     

Securing Cloud Computing from Flash Crowd Attack Using Ensemble Intrusion Detection System

Flash Crowd attacks are a form of Distributed Denial of Service (DDoS) attack that is becoming increasingly difficult to detect due to its ability to imitate normal user behavior in Cloud Computing (CC). Botnets are often used by attackers to perform a wide range of DDoS attacks. With advancements in technology, bots are now able to simulate DDoS attacks as flash crowd events, making them difficult to detect. When it comes to application layer DDoS attacks, the Flash Crowd attack that occurs during a Flash Event is viewed as the most intricate issue. This is mainly because it can imitate typical user behavior, leading to a substantial influx of requests that can overwhelm the server by consuming either its network bandwidth or resources. Therefore, identifying these types of attacks on web servers has become crucial, particularly in the CC. In this article, an efficient intrusion detection method is proposed based on White Shark Optimizer and ensemble classifier (Convolutional Neural Network (CNN) and LighGBM). Experiments were conducted using a CICIDS 2017 dataset to evaluate the performance of the proposed method in real-life situations. The proposed IDS achieved superior results, with 95.84% accuracy, 96.15% precision, 95.54% recall, and 95.84% F1 measure. Flash crowd attacks are challenging to detect, but the proposed IDS has proven its effectiveness in identifying such attacks in CC and holds potential for future improvement.     

人群异常状态检测的图分析方法

提出一种图分析方法用于动态人群场景异常状态检测. 使用自适应Mean shift算法对场景速度场进行非参数概率密度估计聚类, 聚类结果构成以聚类中心为顶点、各聚类中心之间距离为边权重的无向图. 通过分析图顶点的空间分布及边权重矩阵动态系统的预测值与观测值之间的离散程度,对动态场景中的异常事件进行检测和定位. 使用多个典型动态场景视频数据库进行对比实验,结果表明图分析方法适应性强、可有效监控动态人群场景中的异常状态.     

复杂条件下多层建筑人员协作疏散仿真

研究具有复杂多层协作过程条件下的人员疏散控制系统,就能够比较准确地模拟突发情况下人员的疏散情况。本文对元胞自动机进行了改进,综合人员个体特征和从众心理等各种复杂因素,对具有复杂障碍物的多层建筑中人员疏散过程进行了计算机仿真分析,并给出了人员疏散效率与人员的从众系数、障碍物及出口位置等因素的关系。该仿真能够很好地模拟大型公共场所发生突发事件时人员疏散的情况,对在复杂地理环境及人员特性条件下的多层建筑突发事件疏散策略制定具有一定的实际参考意义。     

Emerging opinion leaders in crowd unfollow crisis: a case study of mobile brands in Twitter

Recent years have witnessed the increasing consequences of social networks. For companies, followers in social networks are wealthy because they help to cultivate brand popularity and build well-targeted communities. However, people unfollow sometimes, which indicates a sign of breaking relationships and even losing potential customers. In spite of the fact that unfollow behavior happens frequently, we perceieve that something might be wrong when a unusual large number of unfollows happen simultaneously within a specific window, termed as crowd unfollow. To this end, in this paper we study on the problem of emerging opinion leaders in crowd unfollow and hypothesize that opinion leaders have an impact on the unfollow decision of others. Specifically, given a target brand, we propose a framework to detect crowd unfollow event in real-time and discover opinion leaders within a unfollow social network. Experiments are conducted on the Twitter accounts of three mobile brands. From the empirical results, we have two observations: (1) crowd unfollow could be either durable long-last or short-lived peak shaped; (2) opinion leaders could emerge in crowd unfollow event, which leads to crowd unfollow crisis.     

生物启发的人群突发局部聚集感知神经网络

公共场所中的人群突发局部聚集常是异常事件发生的先兆,由于其随机性强,前兆特征不明显,现有的传统计算机视觉技术较难对其有效检测。基于蝗虫视觉系统的神经结构特性与小叶巨型运动检测器（lobula giant movement detector,LGMD）危险感知机理,提出一种人群突发局部聚集行为检测的LGMD改进型神经网络模型。该模型感知人群活动在视野域中引发的视觉信号,基于哺乳动物视网膜视觉信号处理机制整合视觉运动线索,借助LGMD神经元危险感知机理构建尖峰阈值机制调谐神经网络输出,以感知人群活动中的突发聚集行为。不同场景下的人群活动视频实验结果表明,提出的神经网络能有效检测视野域中人群突发局部聚集行为并对其预警。该文涉及生物视神经机理启发的人群活动动态视觉信息加工处理,可为智能视频监控中的人群活动检测与行为分析提供新思想、新方法。     

考虑分类人群行为的建筑疏散模型研究

人员行为决定了应急疏散时人群的时空分布,是研究疏散动力学的关键。考虑疏散时人员的心理特性与身份状态,将人群分为恐慌人群、易感人群、冷静人群和管理人群四类,基于社会力模型表达各类人群的疏散行为特征,并开展不同情境的疏散动力学过程分析。研究发现行人的恐慌心理具有传播作用,对其他行人的疏散行为有明显的影响,而管理人员的引导作用对疏散有积极影响,当其比例在10%~15%的时候效果显著,且合适的位置更易提高疏散效率;人员的服从水平越大,疏散效率越高。提出的分类人群疏散行为模型能为建筑安全疏散评估与优化提供理论支持。     

建筑物火灾中的人群疏散研究

建筑物火灾是我国频发的安全事故,所以应研究建筑物火灾人群安全疏散问题。由于在建筑物火灾中,人群疏散时出现拥堵,存在不安全因素,造成人员伤亡。针对在现有的研究中未考虑人员行为的影响,提出了智能体(Agent)的人群行为建模技术在建筑物火灾中的人群疏散仿真中的应用方法。仿真结果显示基于Agent的行为模型可以仿真出人员特性及决策过程对人群疏散的影响,弥补现有的人群疏散模型的不足。仿真结果证明,Agent的行为建模技术具有仿真火灾全过程中人员疏散行为的功能,适用于建筑物火灾中的人群优化疏散策略。     

人群应急疏散可视仿真研究进展和问题

人群应急疏散可视仿真是用智能体来模拟具有自主感知、情绪和行为能力的人群个体,并采用3维可视的方式来直观呈现人群应急疏散情景,可以为制定人群应急预案提供形象直观的分析方法。本文从人群仿真数据的来源、人群导航模型的构建、人群行为模型、人群情绪感染、人群渲染5个方面概述目前研究的进展,然后从仿真模型的可验证性、人群疏散导航模型的构建、人与环境的物理模型、动物逃生实验与仿真、疏散中的社会行为表现以及人群情绪的可视计算6个角度讨论需要进一步研究的问题。针对需要深入研究的问题,指出借助于紧急事件的视频监控分析和虚拟人群情景的用户调查,有助于完善人群仿真模型。结合物理模型,可以更准确地描述人群应急疏散场景。开展动物逃生实验分析,有助于完善人群运动导航算法。建立人群社会行为模型,可以更详细描述疏散中人群行为的多样性。构建基于多通道感知的人群情绪感染计算方法,可以详尽描述情绪感染的过程。人群应急疏散行为的可视仿真研究在城市的安全管理方面具有重要的应用前景,但其研究仍存在很多亟待解决的问题,综合地运用多学科知识,完善实验手段是进一步推动研究的关键所在。     

KUMBH MELA: a case study for dense crowd counting and modeling

Dense crowd counting and modeling at different gatherings has ignited a new flame in the visual surveillance research community. There is a high possibility of mishappenings in the form of stampede, mob fighting at these gatherings and the administration is helpless in these scenarios. There is a requirement of analyzing the crowd to prevent these dangerous situations. The proposed work is a case study of Kumbh Mela which models the crowd counting in densely populated images. In the proposed work, the orthographic projection of the crowd is captured using a camera attached to a drone, to reduce the effect of occlusion and scaling which, otherwise, may get introduce during image acquisition process. The captured data is fed to a Convolutional Neural Network for training the model to count head of persons present in the frame. The results obtained from the trained model are validated using geometry and imaging techniques. The proposed model has achieved a mean-absolute-error of 94.3 and a mean-squared-error of 104.6 which seems to outperform the existing state-of-the-art models with respect to the reported performance parameters. The proposed model can be used as a viable solution in applications related to modeling the crowd behavior.

     

基于KOD能量特征的群体异常行为识别

在群体异常行为识别过程中, 针对传统特征易受目标遮挡影响导致其对群体行为的弱描述性问题, 提出一种基于KOD（kinetic orientation distance）能量特征的群体异常行为识别方法。该能量特征忽略群体中相互遮挡的个体的局部特征, 从群体行为整体上分别根据群体的运动剧烈程度、群体运动方向一致性和群体中个体的相对位置定义并提取群体动能、方向势能和距离势能构成群体行为高层KOD能量特征, 以此描述群体的运动状态变化, 最后通过构建隐马尔可夫模型实现群体异常行为检测及类型识别。在PETS和UMN公共数据集上进行实验并与传统光流特征进行对比, 实验结果表明, 使用KOD能量特征能够有效地检测出群体异常行为并识别出其类型, 且能够达到92%的准确率。     

Scene-adaptive accurate and fast vertical crowd counting via joint using depth and color information

Reliable and real-time crowd counting is one of the most important tasks in intelligent visual surveillance systems. Most previous works only count passing people based on color information. Owing to the restrictions of color information influences themselves for multimedia processing, they will be affected inevitably by the unpredictable complex environments (e.g. illumination, occlusion, and shadow). To overcome this bottleneck, we propose a new algorithm by multimodal joint information processing for crowd counting. In our method, we use color and depth information together with a ordinary depth camera (e.g. Microsoft Kinect). Specifically, we first detect each head of the passing or still person in the surveillance region with adaptive modulation ability to varying scenes on depth information. Then, we track and count each detected head on color information. The characteristic advantage of our algorithm is that it is scene adaptive, which means the algorithm can be applied into all kinds of different scenes directly without additional conditions. Based on the proposed approach, we have built a practical system for robust and fast crowd counting facing complicated scenes. Extensive experimental results show the effectiveness of our proposed method.     

基于光流计算的异常拥挤行为检测算法

面向人群场景中异常拥挤行为检测,提出基于光流计算的检测方法。该方法首先采用光流微粒矢量场提取人群运动特征;然后基于社会力模型计算光流微粒之间的相互作用力;最后对相互作用力进行直方图熵值处理来实现人群行为判别。仿真实验表明,本算法可以区分人群场景中异常区域内相互作用力的大小,对异常拥挤行为进行判别和定位。