Abnormal crowd behavior detection using size-adapted spatio-temporal features

Abnormal crowd behavior detection is an important research issue in computer vision. However, complex real-life situations (e.g., severe occlusion, over-crowding, etc.) still challenge the effectiveness of previous algorithms. Recently, the methods based on spatio-temporal cuboid are popular in video analysis. To our knowledge, the spatio-temporal cuboid is always extracted randomly from a video sequence in the existing methods. The size of each cuboid and the total number of cuboids are determined empirically. The extracted features either contain the redundant information or lose a lot of important information which extremely affect the accuracy. In this paper, we propose an improved method. In our method, the spatio-temporal cuboid is no longer determined arbitrarily, but by the information contained in the video sequence. The spatio-temporal cuboid is extracted from video sequence with adaptive size. The total number of cuboids and the extracting positions can be determined automatically. Moreover, to compute the similarity between two spatio-temporal cuboids with different sizes, we design a novel data structure of codebook which is constructed as a set of two-level trees. The experiment results show that the detection rates of false positive and false negative are significantly reduced. Keywords: Codebook, latent dirichlet allocation (LDA), social force model, spatio-temporal cuboid.     

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.     

门禁系统中的异常行为检测*

针对门禁系统中尾随、蛮力开门两种异常通过的行为,结合门禁系统的身份验证功能,采用图像处理技术对违规行为进行检测,以进一步提升门禁系统的安全性能。首先设计并使用了一种基于轨迹分析的人数统计方法,通过目标检测与跟踪算法得到目标在监控场景中的运动轨迹,根据轨迹判定目标进出门禁的情况;然后根据监控场景的特点,设计了一种基于计数线的目标计数规则,结合目标运动轨迹实现人数统计;最后结合门禁系统的身份验证功能,设定异常通过行为的检测规则,检测定义的异常行为。实验结果表明,该方法能够有效的检测通过门禁系统时发生的异常行为,尤其对于行人比较稀疏和没有明显遮挡的情况,具有很好的检测效果,该方法平均检测准确率能够达到90%。     

基于整体能量模型的异常行为检测

为了对少数人群间的突发异常行为进行检测,提出一种基于整体能量模型表示的方法来较准确地辨识正常行为中的异常行为。该整体能量特征算法不仅包括了行为发生双方的个体能量特征,还包括行为发生双方的交互能量特征,这两个因素构成异常行为的整体能量特征。而能量特征的基本参数则是在光流场特征的基础上增加了运动角度变化等特征来深入反映行为的激烈性。最后在不同行为类型视频上测试该算法,并与传统光流能量算法进行测试对比,实验结果展示了整体能量模型相比于传统光流能量算法的高效性以及准确性,能够达到预期目的。     

基于运动显著图的人群异常行为检测

针对公共场所中人群监控准确性和实时性低的问题,提出一种基于运动显著图的人群异常行为检测方法。该方法首先利用Lucas-Kanade法计算稀疏特征点的光流场,并对光流场进行时间和空间上的滤波处理,然后计算特征点的运动方向、速度和加速度。为了准确描述人群行为,将人群的速度幅值、运动方向变化量和加速度幅值分别映射为图像的R、G、B三个通道,并以此合成代表人群运动特征的运动显著图。最后,设计和训练面向人群运动显著图的卷积神经网络模型,并利用该模型检测人群中是否存在异常行为。实验结果表明,该方法能够有效、实时地检测人群异常行为,在UMN和PETS2009数据集的检测率均达到了97.9%以上。     

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。     

车道模型的高速公路车辆异常行为检测方法

针对高速公路上车辆的逆行、停车、轨迹异常等事件的检测问题,提出了一种基于车道模型知识的自底上向的车辆异常检测方法。首先由车道线的连续性、共线性的感知搜索出车道线和消失点,自动建立车道模型;然后在多车辆检测与跟踪时,通过目标运动位置预测和KLT特征点跟踪的方法建立表示目标区域交叠关系图,依据后验关系通过对图中节点对应目标区域的合并与拆分实现目标与实际车辆的一一对应,建立可靠的跟踪轨迹;最后基于消失点的坐标变换,计算车辆实际位置与速度,采用轨迹滑动窗口方法判断目标运动趋势并计算窗口内轨迹点平均速度,判断车辆的异常行为。实验结果表明,所提方法在不同天气、不同车流量环境中均有80%以上的事件检测率,同时算法简单,具有很好的实时性,能够适应实际高速公路智能检测设备的需求。     

联合加权重构轨迹与直方图熵的异常行为检测

为解决多目标打斗、抢劫等异常行为检测精度不高的问题,提出一种联合加权重构轨迹与直方图熵的异常行为检测算法。首先,采用背景相减法结合宽高比提取行人目标;然后将卡尔曼滤波器及HOG特征融入时空上下文算法中,实现短时间内被完全遮挡行人的鲁棒跟踪;最后对跟踪轨迹进行训练,构造正常行为字典并稀疏重构待检测轨迹,通过联合加权最小重构残差和直方图熵,实现对异常行为的有效检测。通过对比实验,表明该算法对于打斗和抢劫等异常行为具有较好的检测效果,在静态背景且无遮挡的情况下,检测率可达92%以上。     

On edge detection of x-ray images using fuzzy sets

The effectiveness of the theory of fuzzy sets in detecting different regional boundaries of X-ray images is demonstrated. The algorithm includes a prior enhancement of the contrast among the regions (having small change in gray levels) using the contrast intensification (INT) operation along with smoothing in the fuzzy property plane before detecting its edges. The property plane is extracted from the spatial domain using S, ? and (1 ?) functions and the fuzzifiers. Final edge detection is achieved using max or min operator. The system performance for different parameter conditions is illustrated by application to an image of a radiograph of the wrist.     

Abnormal driving behavior detection based on kernelization-sparse representation in video surveillance

The detection of abnormal driving behaviors based on video surveillance systems is an important part of Intelligent Transportation System (ITS), which can help reduce disturbances on traffic flow and improve traffic safety. First, the study proposes a novel nonlinear sparse reconstruction method for abnormal driving behavior detection in video surveillance. A hybrid kernel function formed by convexly combining a local kernel of radial basis function (RBF) and a global kernel of homogeneous polynomial is been applied in sparse reconstruction method. Then, a novel Hybrid Kernel Orthogonal Matching Pursuit (HKOMP) algorithm is designed to solve the proposed sparse reconstruction model. Finally, the performance of the abnormal detection method is tested on two datasets i.e. stop sign dataset and car parking dataset. In addition, comparative experiments with five classical methods are carried out. The experimental results indicate that the proposed method outperforms other five comparison methods in terms of accuracy.

     

基于图像处理的公交车内人群异常情况检测

为有效地监控公交车这一特定环境中人群的异常行为,提出一种公交车内人群异常情况检测的方法。对视频图像确立感兴趣区域,进行预处理;通过改进Vi Be算法提取运动目标,引入多尺度滑窗算法确定识别区域;结合连续多帧识别区域进行改进卷积神经网络算法的异常行为识别,通过识别结果判断公交车内人群是否异常。与传统方法的比较结果表明,该算法的检测正确率较高,可达93.5%,误检率较低,仅为1.6%,在实际应用中具有较高的参考价值。     

基于角点动能模型的电梯轿厢内异常行为检测*

针对电梯轿厢内安全,为避免发生打架、抢劫、施暴等行为,通过视频信息分析,提出了一种基于角点动能的异常行为检测模型,以达到实时安全监控的目的。提出一种采用Hausdorff距离匹配背景边缘模型的前景目标提取方法,通过检测目标边缘的角点并计算角点的光流,根据角点光流包含的速度矢量信息建立目标的动能模型,用于异常行为判断。实验结果表明,该方法能有效地检测出电梯轿厢内的异常行为,且实现简单、算法复杂度低、能够实时报警。     

Event detection using user interaction behavior models

In information exchange networks such as email or blog networks, most processes are carried out using exchange of messages. The behavioral analysis in such networks leads to interesting insight which would be quite valuable for organizational or social analysis. In this paper, we investigate user engagingness and responsiveness as two interaction behaviors that help us understand an email network which is one of information exchange networks. Engaging actors are those who can effectively solicit responses from other actors. Responsive actors are those who are willing to respond to other actors. By modeling such behaviors, we are able to measure them and to identify high engaging or responsive actors. We systematically propose novel behavior models to quantify the engagingness and responsiveness of actors in the Enron email network. Furthermore, as one of case studies, we study an event detection problem, based on our proposed behavior models, in the Enron emails. According to our empirical study, we found out meaningful events in Enron. For details, see Sect. 5.     

基于智能监控的中小人群异常行为检测

针对人群异常行为检测实时性较差、分类算法识别率不高、特征量较少的问题,提出一种基于智能监控的中小人群异常行为检测算法。首先,利用快速群体密度检测算法,提取人群数量变化信息;其次,利用改进的Lucas-Kanande光流法提取视频中人群的平均动能、人群方向熵、人群距离势能;最后,利用极限学习机(ELM)算法对人群行为进行分类。使用UMN公共数据集进行测试,ELM算法对中小人群异常行为分析比中高密度人群异常行为检测算法和基于KOD能量特征的群体异常行为检测算法识别率分别高出7.13个百分点和5.89个百分点,并且人数密度估计部分平均每帧图像处理耗时相比中高密度人群异常行为检测算法减少了106 ms(近1/3)。实验结果表明:基于智能监控的中小人群异常行为检测算法能有效提高异常帧识别率和实时性。     

基于深度时空卷积神经网络的人群异常行为检测和定位

针对公共场合人群异常行为检测准确率不高和训练样本缺乏的问题,提出一种基于深度时空卷积神经网络的人群异常行为检测和定位的方法。首先针对监控视频中人群行为的特点,综合利用静态图像的空间特征和前后帧的时间特征,将二维卷积扩展到三维空间,设计面向人群异常行为检测和定位的深度时空卷积神经网络;为了定位人群异常行为,将视频分成若干子区域,获取视频的子区域时空数据样本,然后将数据样本输入设计的深度时空卷积神经网络进行训练和分类,实现人群异常行为的检测与定位。同时,为了解决深度时空卷积神经网络训练时样本数量不足的问题,设计一种迁移学习的方法,利用样本数量多的数据集预训练网络,然后在待测试的数据集中进行微调和优化网络模型。实验结果表明,该方法在UCSD和subway公开数据集上的检测准确率分别达到了99%和93%以上。     

区间二型模糊集彩色遥感图像边缘检测方法

针对一型模糊集其隶属度函数是确定的,不具有柔性,很难满足图像的多方面边缘检测要求,及传统PalKing算法采用单一阈值对图像进行增强难以满足灰度变化丰富且含大量信息的彩色遥感图像处理的要求。提出了一种新的基于区间二型模糊集的彩色遥感图像边缘检测方法。实验结果表明,它能较好地检测出彩色遥感图像边缘,因此是一种实用有效的彩色遥感图像边缘检测方法。     

基于轨迹分段LDA主题模型的视频异常行为检测方法

基于目标轨迹的异常行为检测算法忽略了轨迹内部信息,容易导致异常检测虚警率偏高。为解决该问题,提出一种基于轨迹分段主题模型的视频异常行为检测方法。首先将目标原始轨迹根据轨迹转角分段,然后采用分段量化的方式提取轨迹片段中包含的行为特征信息,接着通过潜在狄利克雷分配(LDA)主题模型建模发掘目标轨迹之间的时空关系,最后通过学习所构建的模型并结合贝叶斯理论进行行为模式分析和异常行为检测。分别对两个视频场景进行了目标行为模式分析和异常行为检测的仿真实验,检测出了场景内多种异常行为模式。实验结果表明,通过结合轨迹分段与LDA主题模型,该算法能够充分挖掘目标轨迹内部的行为特征信息,识别多种异常行为模式,并且能提高对异常行为检测的准确率。     

Colonic fold detection from computed tomographic colonography images using diffusion-FCM and level sets

Colon cancer is the second major cause of cancer related deaths in industrial nations. Computed tomographic colonography (CTC) has emerged in the last decade as a new less invasive colon diagnostic alternative to the usually practiced optical colonoscopy. The overall goal is to increase the effectiveness of virtual endoscopic navigation of the existing computer-aided detection (CAD) system. The colonic/haustral folds serve as important landmarks for various associated tasks in the virtual endoscopic navigation like prone–supine registration, colonic polyp detection and tenia coli extraction. In this paper, we present two different techniques, first in isolation and then in synergism, for the detection of haustral folds. Our input is volumetric computed tomographic colonography (CTC) images. The first method, which uses a combination of heat diffusion and fuzzy c-means algorithm (FCM), has a tendency of over-segmentation. The second method, which employs level sets, suffers from under-segmentation. A synergistic combination, where the output of the first is used as an input for the second, is shown to improve the segmentation quality. Experimental results are presented on digital colon phantoms as well as real patient scans. The combined method has a total erroneous (over-segmentation plus under-segmentation) detection of (6.5 ± 2)% of the total number of folds per colon as compared to (12.5 ± 5)% for the diffusion-FCM-based method and (11.5 ± 3)% for the level set-based method. The p-values obtained from the associated ANOVA tests indicate that the performance improvements are statistically significant.     

A new extension of fuzzy sets using rough sets: R-fuzzy sets

This paper presents a new extension of fuzzy sets: R-fuzzy sets. The membership of an element of a R-fuzzy set is represented as a rough set. This new extension facilitates the representation of an uncertain fuzzy membership with a rough approximation. Based on our definition of R-fuzzy sets and their operations, the relationships between R-fuzzy sets and other fuzzy sets are discussed and some examples are provided.