Anomaly3D: Video anomaly detection based on 3D-normality clusters

Abnormal behavior detection in surveillance videos is necessary for public monitoring and safety. In human-based surveillance systems, it requires continuous human attention and observation, which is a difficult task. The autonomous detection of such events is of essential significance. However, due to the scarcity of labeled data and the low occurrence probability of these events, abnormal event detection is a challenging vision problem. In this paper, we introduce a novel two-stage architecture for detecting anomalous behavior in videos. In the first stage, we propose a 3D Convolutional Autoencoder (3D-CAE) architecture to extract spatio-temporal features from normal event training videos. In 3D-CAE, the encoder and decoder architectures are based on 3D convolutions, which can learn both appearance and the motion features effectively in an unsupervised manner. In the second stage, we group the 3D spatio-temporal features into different normality clusters, and then remove the sparse clusters to represent a stronger pattern of normality. From these clusters, one-class SVM classifier is used to distinguish between normal and abnormal events based on the normality scores. Experimental results on four different benchmark datasets show significant performance improvement compared to state-of-the-art approaches while providing results in real-time.     

Human Detection for Video Surveillance in Hospital

This paper presents a human detection system in a vision-based hospital surveillance environment. The system is composed of three subsystems, i.e. background segmentation subsystem (BSS), human feature extraction subsystem (HFES), and human recognition subsystem (HRS). The codebook background model is applied in the BSS, the histogram of oriented gradients (HOG) features are used in the HFES, and the support vector machine (SVM) classification is employed in the HRS. By means of the integration of these subsystems, the human detection in a vision-based hospital surveillance environment is performed. Experimental results show that the proposed system can effectively detect most of the people in hospital surveillance video sequences.     

基于多特征融合的运动阴影去除算法研究

在自动视频监控系统中,阴影是影响目标检测和跟踪的主要因素之一。为了去除阴影的干扰,提出一种区域梯度、颜色和轮廓多特征融合的方法。改进轮廓计算方法,巧妙利用轮廓分割区域,合理使用轮廓填充区域,这些改进使本方法更具鲁棒性和更广适用范围。实验结果表明,该方法在不同场景下可以有效地去除阴影。     

Feature-based detection and correction of occlusions and split of video objects

This paper proposes a novel algorithm for the real-time detection and correction of occlusion and split in object tracking for surveillance applications. The paper assumes a feature-based model for tracking and is based on the identification of sudden variations of spatio-temporal features of objects to detect occlusions and splits. The detection is followed by a validation stage that uses past tracking information to prevent false detection of occlusion or split. Special care is taken in case of heavy occlusion, when there is a large superposition of objects. For the detection of splits, in addition to the analysis of spatio-temporal changes in objects’ features, our algorithm analyzes the temporal behavior of split objects to discriminate between errors in segmentation and real separation of objects, such as in a deposit event. Both objective and subjective experimental results show the ability of the proposed algorithm to detect and correct, both, split and occlusion of objects. The proposed algorithm is suitable in video surveillance applications due to its good performance in multiple, heavy, and total occlusions, its ability to differentiate between real object separation and faulty object split, its handling of simultaneous occlusion and split events, and its low computational complexity. The algorithm was integrated into an on-line video surveillance system and tested under several conditions with promising results. This work was partially supported by the National Science and Engineering Research Council of Canada (NSERC).     

视频监控图像的超分辨率复原研究

超分辨率复原技术是一种可用于提高图像细节辨识能力的有效方法。其在视频监控领域可望得到广泛应用。超分辨率图像处理技术通过融合多帧相似的低分辨率图像达到提高图像细节的目的。从而降低对监控视频采集硬件与后端辅助处理系统的要求,提高对特定目标的辨析能力。本文重点介绍了在视频监控领域较为实用的凸集投影算法、最大后验概率估计算法、基于对象的超分辨率复原方法、基于示例学习与多类预测器的超分辨率复原方法。对以上超分辨率复原方法实现流程的优缺点与其在视频图像监控领域的应用方法进行了相应分析。分析了超分辨率视频监控图像复原常用的基于块匹配与光流的对象运动估计方法。对超分辨率复原重建图像质量的评估标准也进行了相应讨论。     

基于内容的海量监控视频的多层次检索系统

设计和实现了一种基于内容的海量监控视频的多层次检索系统。该系统首先从监控视频中提取关键帧图像,其次利用行人检测、人脸识别及车辆检测等算法将关键帧中的行人图像、人脸图像和车辆图像等感兴趣目标提取出来,然后提取这些图像的颜色、纹理等特征,利用改进的LIRe(Lucene Image Retrieval)建立分布式的特征库,最终形成了多层次的信息数据库。实验表明,该系统具有较高的检索准确率和较快的检索速率,并支持海量监控视频的检索。     

Multi-video synopsis for video representation

The world is covered with millions of cameras with each recording a huge amount of video. It is a time-consuming task to watch these videos, as most of them are of little interest due to the lack of activity. Video representation is thus an important technology to tackle with this issue. However, conventional video representation methods mainly focus on a single video, aiming at reducing the spatiotemporal redundancy as much as possible. In contrast, this paper describes a novel approach to present the dynamics of multiple videos simultaneously, aiming at a less intrusive viewing experience. Given a main video and multiple supplementary videos, the proposed approach automatically constructs a synthesized multi-video synopsis by integrating the supplementary videos into the most suitable spatiotemporal portions within this main video. The problem of finding suitable integration between the main video and supplementary videos is formulated as the maximum a posterior (MAP) problem, in which the desired properties related to a less intrusive viewing experience, i.e., informativeness, consistency, visual naturalness, and stability, are maximized. This problem is solved by using an efficient Viterbi beam search algorithm. Furthermore, an informative blending algorithm that naturalizes the connecting boundary between different videos is proposed.The proposed method has a wide variety of applications such as visual information representation, surveillance video browsing, video summarization, and video advertising. The effectiveness of multi-video synopsis is demonstrated in extensive experiments over different types of videos with different synopsis cases.     

基于ARM的视频监控系统

设计了一种基于三星ARM9的S3C2440芯片的视频监控系统.该系统通过摄像头采集图像并对图像进行运动检测和压缩编码.实验结果表明该系统保持了图像传输的流畅性,同时能够时运动的入侵目标进行闪烁标注,达到入侵、运动检测的目的.     

视频监控系统中的行人及其面部侦测研究

采用集成H．264硬件编解码视频处理单元Hi3512来设计视频监控系统。并探讨行人目标的自动侦测问题。在对视频图像进行形态学分析的基础上,利用背景差方法实现运动目标区域的粗提取,通过阴影去除算法实现运动目标的精确定位,再利用连续均值量化变换（SuccessiveMeanQuantizafionTransform,SMQT）算法实现运动区域灰度图像的增强处理,然后利用SNoW（SparseNetworkofWinnows）分类算法实现行人及其人脸部位的侦测。实验结果表明,所采用方法能够自动检测出监控区域的行人目标及其面部信息,可有效地应用于无人值守视频监控场合。     

Solar‐powered ZigBee‐based wireless motion surveillance: a prototype development and experimental results

This paper describes the design and implementation of a solar‐powered wireless motion sensor surveillance network. Commercially available systems with similar functionality which exist today have several disadvantages including single points of failure and requires (semi) constant personnel attention as well as an elaborate power system. These systems require a lot of time to set up, they cannot be used in remote areas where a main power supply is unavailable, and are quite costly. Therefore, there is a need to develop a system which is portable, easy to set up, and is energy efficient. The wireless motion surveillance network described in this paper is designed to be portable, economically inexpensive, and energy efficient. The network is created using the IEEE 802.15.4 ZigBee wireless standard by implementing multiple Microchip PICDEM Z nodes. Each node in the network is equipped with a Direction Sensing Infrared Motion Detector (DSIMD) and a solar power unit (SPU). The DSIMD allows for detection of humans and animals alike moving into or out of the network. The system is powered by solar energy that makes it quite adaptable for remote applications. The network is able to cover an area of radius 30 m. By developing a low‐cost system, which is portable, easy to set up, and has an unlimited power supply, this technology is made accessible to a wider range of applications. The implementation of a CMOS camera is discussed at the end which can be used to take a snapshot of the detected object. Copyright © 2007 John Wiley & Sons, Ltd.     

Coding of 12-bit video from thermal imaging systems

A number of advanced applications of digital video technology exist which require pixels to be represented with a resolution higher than the 8 bits that is used in most existing video coding standards. These applications include the video generated by many modern thermal imaging systems used in surveillance applications, which has a dynamic range of 12 bits. In this paper, we describe the modifications required to extend existing video coding standards to support surveillance applications, concentrating on applications with pixels whose dynamic range is up to 12 bits. We examine the tools necessary to implement directly a 12-bit coding algorithm, as well as a scalable coding approach using SNR scalability.     

Reduction of False Alarm Signals for PIR Sensor in Realistic Outdoor Surveillance

A passive infrared or pyroelectric infrared (PIR) sensor is mainly used to sense the existence of moving objects in an indoor environment. However, in an outdoor environment, there are often outbreaks of false alarms from environmental changes and other sources. Therefore, it is difficult to provide reliable detection outdoors. In this paper, two algorithms are proposed to reduce false alarms and provide trustworthy quality to surveillance systems. We gather PIR signals outdoors, analyze the collected data, and extract the target features defined as window energy and alarm duration. Using these features, we model target and false alarms, from which we propose two target decision algorithms: window energy detection and alarm duration detection. Simulation results using real PIR signals show the performance of the proposed algorithms.     

基于android移动视频监控系统客户端的研究与设计

移动视频监控技术是无线网络技术、流媒体技术以及视频监控技术等多种技术融合的产物.在多种技术融合的背景下,提出一种面向智能交通的移动视频监控系统的设计方案,侧重对Android平台视频监控客户端进行研究与设计,并对涉及到关键技术展开研究.最后,在Android 2.3平台上进行测试,结果表明,该客户端能够满足远程视频监控的需求.     

基于上下文信息的监控场景行人检测方法

为了提高监控场景中行人检测的准确度,提出了一种基于上下文信息的行人检测方法.该方法将监控场景的上下文信息融入到卷积神经网络中,选择性地学习对行人检测有帮助的上下文信息.首先,利用一个截断的卷积神经网络提取输入图像的多张特征图.然后,将多张特征图通过两个包含上下文信息的卷积层,形成一张掩码图.最后,通过在掩码图上估计行人的边界框,获得行人检测的结果.实验表明,该方法能实现监控场景中准确且快速的行人检测.     

空间碎片监测技术研究

结合空间目标环境,阐述了空间碎片监测的重要性。对国外空间碎片地基和天基监测手段(雷达、光学望远镜)进行了综述,并分析了相应的监测效能。通过对国外空间碎片监测技术的研究,指出了空间碎片监测的发展方向。该文对空间碎片监测发展具有重要的指导意义。     

夜视成像技术在长江航道视频监视中的应用

为了保障长江航道的安全畅通,结合长江航道上已建设的视频监视系统,对远距离红外夜视技术在航道视频监视中的作用、应用环境、技术需求以及实用效果进行了分析。长江航道夜视监控处于野外工作状态,受自然环境的影响大。同时,在航道应用中,人们对航标标位、灯光、船舶以及航标结构损坏情况都有不同的监控要求。基于监控需求和对已建系统实际使用效果的考量,提出了航道视频监视系统中的红外夜视设备的配置要求。该系统由激光照明系统、信号采集系统、控制系统和信号传输系统等四部分组成。给出了各个部分的具体参数。随着内河航道的逐步现代化,夜视系统在航道视频监视中的应用范围必将逐渐扩大,在航道维护管理中也将发挥重要作用。     

视频监控网络中目标特征的虚拟同步

视频监控网络已经成为计算机视觉的研究热点之一。文章分析了视频监控网络中数据不同步的原因．提出了使用目标缓冲池链进行虚拟同步的方法。在此基础上讨论了对目标特征数据进行处理的三层结构．解决了视频监控网络系统中的数据不同步问题。实验结果表明得到的虚拟同步数据真实可靠，实现简单，具有较强的实用性。     

特殊环境嵌入式智能监测平台研究

在野外露天或环境恶劣的监测现场，使用计算机和数据采集卡来实现监测任务是相当危险和不可靠的。针对监测环境中可能存在易燃易爆条件，湿度大，灰尘多，监测场所分散，距离较远等特殊问题，分析了特殊监测环境中的平台选择，讨论了监测平台的通信方式和监测数据的压缩编码标准，提出了建立特殊环境嵌入式智能监测平台的思想，介绍了智能监测平台的设计与实现。     

基于QoS策略的视频监控系统的设计

网络化视频监控系统是集网络、通信以及视频编解码等多项技术的整合系统。文章先提出了网络化视频监控系统的系统结构，接着重点介绍了网络化视频监控系统中如何有效的应用QoS策略来优化多媒体流的传输和视频的质量。     

智能视频监控技术研究及应用

传统的工业电视监控存在报警精确度差等缺点,智能视频监控的提出从很大程度上弥补这些缺陷。本文对智能视频监控技术的工作原理进行了分析。针对煤矿安全生产环境,提出了采用智能视频监控技术的煤矿安全生产智能视频联动监控系统。该系统能够在很大程度上提高报警准确度,为煤矿安全生产提供更可靠的保障。