一种结合了纹理和颜色的运动目标跟踪算法

运动目标跟踪是智能视频监控中的关键技术之一,怎样描述运动目标是该技术的一个关键问题。提出一种新的运动目标跟踪算法,结合改进的LBP纹理和色度来描述运动目标,并采用Camshift算法的思想进行目标跟踪。为了降低算法的复杂性,在保证跟踪精确度的前提下,LBP纹理和色度的种类被极大地精简。实验证明提出的方法能有效地跟踪运动目标,在常规的视频分辨率下能达到实时性,比同类的其它算法性能更好。     

窄带同步相位检测在商品电子防窃系统中的应用

给出了一种基于同步相位窄带检测电路实现的EAS系统检测器,并给出了原理和实现方法。     

基于运动矢量交点密集度的人群恐慌行为检测

为了更准确有效的识别人群恐慌行为,本文提出了一种利用视频中人群运动矢量的交点密集度来判断人群恐慌异常的新算法.该算法以LK光流法为基础来提取运动人群的运动矢量信息,接着通过获得的信息求取运动矢量间的两两交叉点,然后运用分块法求得区域交叉点密集度,并以此来识别人群异常.对多个视频进行测试,测试结果表明:该算法能够以较高正确率识别视频中人群的恐慌行为.     

H.264帧内预测算法的优化及应用

现存的视频压缩方法, 大多为提高视频的压缩效果和减少压缩时间, 而采用电路复杂并且造价高昂硬件电路. 针对该情况, 文章根据帧内预测算法的准确性与高效性, 采用H.264帧内预测算法并对其进行优化, 在此基础上设计硬件电路, 后结合JPEG图像压缩算法对视频进一步压缩,从而达到简化硬件电路、缩短编码时间、提高数据的传输速率与可靠性的目的. 测试表明, 研究能够达到上述目的且具有相对成本低廉的市场优势, 在无线视频监控领域上具有较好的发展前景.     

A new paradigm for urban surveillance with vehicular sensor networks

We consider a new application paradigm of vehicular sensor networks (VSN). Currently, vehicles are equipped with forward facing cameras to assist forensic investigations of events by proactive image-capturing from streets and roads. Due to content redundancy and storage imbalance in this in-network distributed storage system, how to maximize its storage capacity becomes a nontrivial challenge. In other words, how to maximize the average lifetime of sensory data (i.e., images generated by cameras) in the network is a fundamental problem to be solved. This paper presents, VStore, a cooperative storage solution in vehicular sensor networks for mobile surveillance, which has been designed to support redundancy elimination and storage balancing throughout the network. Compared with existing works, we propose a novel storage architecture for urban surveillance and deal with challenges in a mobile scenario. Field testing was carried out with a trace-driven simulator, which utilized about 500 taxis in Shanghai. The testing results showed that VStore can largely prolong the average lifetime of sensory data by cooperative storage.     

Abnormality detection using low-level co-occurring events

We propose in this paper a method for behavior modeling and abnormal events detection which uses low-level features. In conventional object-based approaches, objects are identified, classified, and tracked to locate those with suspicious behavior. We proceed directly with event characterization and behavior modeling using low-level features. We first learn statistics about co-occurring events in a spatio-temporal volume in order to build the normal behavior model, called the co-occurrence matrix. The notion of co-occurring events is defined using mutual information between motion labels sequences. Then, in the second phase, the co-occurrence matrix is used as a potential function in a Markov random field framework to describe, as the video streams in, the probability of observing new volumes of activity. The co-occurrence matrix is thus used for detecting moving objects whose behavior differs from the ones observed during the training phase. Interestingly, the Markov random field distribution implicitly accounts for speed, direction, as well as the average size of the objects without any higher-level intervention. Furthermore, when the spatio-temporal volume is sufficiently large, the co-occurrence distribution contains the average normal path followed by moving objects. Our method has been tested on various indoor and outdoor videos representing various challenges.     

Multi‐agent system for knowledge‐based event recognition and composition

This work presents a multi‐agent system for knowledge‐based high‐level event composition, which interprets activities, behaviour and situations semantically in a scenario with multi‐sensory monitoring. A perception agent (plurisensory agent and visual agent)‐based structure is presented. The agents process the sensor information and identify (agent decision system) significant changes in the monitored signals, which they send as simple events to the composition agent that searches for and identifies pre‐defined patterns as higher‐level semantic composed events. The structure has a methodology and a set of tools that facilitate its development and application to different fields without having to start from scratch. This creates an environment to develop knowledge‐based systems generally for event composition. The application task of our work is surveillance, and event composition/inference examples are shown which characterize an alarming situation in the scene and resolve identification and tracking problems of people in the scenario being monitored.     

面向空间监视应用的空间目标数据库的建立

阐述了面向空间监视应用的空间目标数据库的建立技术与方法,并给出了它在空间监视的目标分类、识别应用中的样例。     

融合运动和统计特征的静态目标检测

为了解决大部分时间处于相对静止状态目标的智能监控,提出一种融合运动和统计特征的静态目标检测方法.该方法采用行列错位减图像的帧差来提取目标运动特征,根据目标模型和候选区域的统计特征匹配检测目标,利用运动特征和模板的相似性度量动态更新模板.通过积分图优化特征提取及对强光抑制,提高了算法的实时性和鲁棒性.     

Sink placement on a 3D terrain for border surveillance in wireless sensor networks

With their distributed nature and redundant operation capability, wireless sensor networks are very suitable for border surveillance scenarios that track intruders trying to breach to a safe side. In such scenarios, keeping the operation going on for as long as possible is the most important aspect of the network. We propose that by placing sink at a carefully selected coordinate will results in a longer living network. We also place restrictions on the candidate locations so that the sensing quality of the network is above a useful predetermined value and the sink is placed in a relatively safe location to avoid destruction. In order to find the suitable coordinates we propose a modified lifetime metric which takes quality and safety measures into account. We also propose a genetic algorithm which uses a discrete event simulator-in-the-loop over a three dimensional terrain to find locations for the sink that fits the given quality and safety restrictions. Using a three dimensional underlying terrain makes the proposed approach more realistic. The results obtained for various sensor network scenarios indicate that the proposed algorithm can find locations that increase the lifetime by also considering the sensing quality and safety.