基于双模型融合的监控视频人数统计

针对垂直角度监控视频下的人数统计任务所遇到的角度特殊、检测精度较低等问题,提出了一种基于双模型融合的监控视频人数统计方法。在基于COCO数据集的YOLOv3预训练模型上,加入了垂直角度的训练样本进行迁移学习。分别训练两个模型,一个检测俯视视频中的行人,另一个检测俯视视频中的人头。将迁移学习训练后的行人检测模型和人头检测模型的检测结果进行融合,并引入基于卡尔曼滤波的跟踪方法得到了运动轨迹,利用运动轨迹信息实现了人数统计。通过多次实验,验证了在垂直角度监控视频中双模型融合方法较单一检测模型和预训练模型能取得更好的检测效果,最终获得更准确的人数统计结果。     

极化辅助的非均匀场景空时自适应处理方法

空时自适应处理是强杂波背景下动目标检测的有效途径,实际检测环境中训练样本与待检测单元背景统计特性的不一致将恶化处理器的输出信杂噪比,需要结合样本挑选技术来改善非均匀场景的处理器性能.在建立机载多通道信号模型基础上,提出一种利用极化信息辅助的空时自适应处理方法,该方法通过极化分类和功率分组指导训练样本选择,利用同类样本估计待检测单元的统计特性并计算自适应权矢量,具有杂波相关矩阵估计准确度高的特点,可显著改善动目标检测的性能.最后结合国外NASA JPL AIRSAR实测数据的多通道仿真实验验证了所提方法的有效性.     

利用KPCA特征提取的Adaboost红外目标检测

针对传统红外目标检测算法中存在的不足,提出了一种基于核主成分分析(KPCA)特征提取的Adaboost分类器红外目标检测算法.首先,采用KPCA对目标训练样本进行特征提取,将背景训练样本和待检测样本在概率核空间中向目标样本特征量投影作为它们的特征量;然后,用目标和背景样本特征来训练Adaboost分类器;最后,用此分类...     

基于统计推断的行人再识别算法

行人再识别是指给定一张行人图像,在已有的可能来源于非交叠摄像机视场的行人图像库中,识别出与此人相同的图像。研究该问题有着非常重要的现实意义,同时也面临许多挑战。该文提出一种基于统计推断的行人再识别算法。该算法从统计推断的角度出发学习两幅行人图像的相似度度量函数,利用此函数从行人图像库中搜索待查询的人。在公共数据集VIPeR上的实验表明,该算法性能优于已有的行人再识别算法,学习相似度度量函数的时间花销明显少于已有的基于学习的算法,并且在只有少量训练样本时,缓解了学习相似度度量函数的过拟合问题。     

基于CUT自身先验知识的STAP

在空时自适应处理（STAP）中,通常使用训练样本来估计杂波协方差矩阵（CCM）。在本文中训练样本仅用来估计部分杂波协方差矩阵,大部分杂波协方差矩阵由待检测单元（CUT）计算。注意到CUT具有先验知识：只有待检测的频率通道可能包含目标信号,而其他频率通道只有杂波。因此,提出了一种基于CUT先验知识的STAP方法。这种方法将待检测单元的杂波分为两部分来重建：第一部分是待检测频率通道的杂波成分,该部分可能混有目标信号,因此通过训练样本来估计;第二部分是其他频率通道中的杂波,这部分可直接从CUT中提取,不需要估计。     

基于最稳定极值区域方法的目标检测与跟踪

针对非刚体目标的精确实时跟踪问题,提出了一种融合先验形状信患的基于最稳定极值区域(MSER)检测器的跟踪算法.首先,利用训练样本建立目标颜色特征的混合模型,生成目标统计颜色概率图,为最大稳定区域方法提供概率统计依据.其次,利用基于最稳定极值区域方法给出最稳定的分割结果.最后,利用训练样本得到目标的先验动态形状模型,并且融合目标形状信息与通过MSER算法生成的稳定区域信息,去除虚假分割结果,提高目标检测精度与跟踪性能.实验结果证明,该算法能在视频序列图像中有效检测并跟踪目标.     

一种基于节点实时流量的异常检测算法

针对无线传感器节点缺乏移动性和可预知的流量模式等特征,从而难以在传感器网络中进行异常检测的问题,该文提出了一种基于节点的实时异常检测算法.根据节点流量的到达过程,提出了一种新的节点流量到达模型,根据多层次的滑动窗口事件存储原理,将动态统计值进行短时间的保持,对不同时间段的到达过程指标进行比较,包括节点的可计算资源,低复杂度,融合特性等,以此来判别流量到达过程是否发生异常,从而对传感器网络进行有效的异常检测.     

利用红外温升多特征矢量提升电子装备热像异常检测性能的方法

针对传统的接触式电参数故障检测方法 难以满足日益复杂的电子装备的检修需要问题,提出了一种基 于红外热像的可提升非接触式电子装备异常 检测性能的温升多特征方法。在红外与光学异源配准的基础上,获得电子 装备各元件的精确位置。然后基于红外观测图像获取 各个标准和待测元件中心区域的温升均值曲线。在对这些曲线进行全帧 程分段后,精细化地提取温升统计矢量。接着计算待测温升统计 矢量与标准温升统计矢量的差异并对其进行归一化处理,从而构建温升多特 征矢量。最后根据该矢量,通过分段表决和异常 量化实现电子装备热像异常的整体态势感知。与传统的热像 异常检测方法相比,本文所构建的温升多特征矢量可以更精细、更 稳健地描述温升变化。通过分段表决和异常量化实现了温升全程表征,为后续的电路 故障智能推理奠定了基础。实验结果表 明,本文方法具有检测准确率高、实时性好等优点。     

强杂波中双波段目标检测新算法

对海空背景下的电视和3～5(m红外目标提出了一种采用多向梯度表决融合的检测方法:依据背景图像中点目标的奇异特性,得到图像的多向剃度检测结果,并进行表决融合.通过实测的电视和红外图像仿真,结果表明,采用\     

基于联合注意力机制和一维卷积神经网络-双向长短期记忆网络模型的流量异常检测方法

针对流量数据集中类别不平衡限制了分类模型对少数类攻击流量的检测性能这一问题,该文提出一种基于联合注意力机制和1维卷积神经网络-双向长短期记忆网络(1DCNN-BiLSTM)模型的流量异常检测方法。首先在数据预处理过程中利用BorderlineSMOTE方法对流量数据不平衡训练样本预处理,使得各类流量数据均衡,有助于后续模型对各类数据的充分训练。然后设计联合注意力机制和1DCNN-BiLSTM的模型对流量数据进行训练,提取流量数据的局部和长距离序列特征并进行分类,通过注意力机制将对分类有用的特征按其重要性赋予权值,提高对少数攻击类的检出率。实验结果表明,同几种现有方法相比,该文方法对NSL-KDD和CICIDS2017数据集的检测准确率最高(可达93.17%和98.65%),对NSL-KDD数据集中的提权攻击(U2R)攻击流量的检出率至少提升13.70%,证明了该文方法提升少数类攻击流量检出率的有效性。     

An experiment on the security of the Norwegian electronic voting protocol

Even when using a provably secure voting protocol, an election authority cannot argue convincingly that no attack that changed the election outcome has occurred, unless the voters are able to use the voting protocol correctly. We describe one statistical method that, if the assumptions underlying the protocol’s security proof hold, could provide convincing evidence that no attack occurred for the Norwegian Internet voting protocol (or other similar voting protocols). To determine the statistical power of this method, we need to estimate the rate at which voters detect possible attacks against the voting protocol. We designed and carried out an experiment to estimate this rate. We describe the experiment and results in full. Based on the results, we estimate upper and lower bounds for the detection rate. We also discuss some limitations of the practical experiment.     

一种投票权值调整的神经网络集成增量学习方法

针对神经网络集成增量学习中集成输出投票权值的设定问题,给出了一种投票权值调整的神经网络集成增量学习方法。该方法定义了神经网络集成中子神经网络训练集的类核函数,通过计算待识样本与类核函数之间的核函数距离得到集成输出中子神经网络的投票权值。这种投票权值设定方法可以根据子神经网络分类器对待识样本的分类性能自适应地调整集成输出的投票权值,是一种更加合理的集成输出投票权值设定方法。仿真实验表明,这种投票权值调整的神经网络集成增量学习方法比投票权值固定的方法增量学习性能更优。      

网络流量特征选择方法中的分治投票策略研究

特征选择作为机器学习过程中的预处理步骤,是影响分类性能的关键因素.网络流量具有数据量大,特征维度高的特点,如何快速提取特征子集,并提高分类效率对于基于机器学习的流量分类方法具有重要意义.本文提出基于分治与投票策略的特征提取方法,将数据集分裂为多个子集,分别执行特征提取算法,利用投票方法获得最后的特征子集.实验表明可有效提高特征提取的时间效率,同时使分类器取得良好的分类准确率.     

Modeling heterogeneous network traffic in wavelet domain

Heterogeneous network traffic possesses diverse statistical properties which include complex temporal correlation and non-Gaussian distributions. A challenge to modeling heterogeneous traffic is to develop a traffic model which can accurately characterize these statistical properties, which is computationally efficient, and which is feasible for analysis. This work develops wavelet traffic models for tackling these issues. We model the wavelet coefficients rather than the original traffic. Our approach is motivated by a discovery that although heterogeneous network traffic has the complicated short- and long-range temporal dependence, the corresponding wavelet coefficients are all “short-range” dependent. Therefore, a simple wavelet model may be able to accurately characterize complex network traffic. We first investigate what short-range dependence is important among the wavelet coefficients. We then develop the simplest wavelet model, i.e., the independent wavelet model for Gaussian traffic. We define and evaluate the (average) autocorrelation function and the buffer loss probability of the independent wavelet model for fractional Gaussian noise (FGN) traffic. This assesses the performance of the independent wavelet model, and the use of which for analysis. We also develop (low-order) Markov wavelet models to capture additional dependence among the wavelet coefficients. We show that an independent wavelet model is sufficiently accurate, and a Markov wavelet model only improves the performance marginally. We further extend the wavelet models to non-Gaussian traffic through developing a novel time-scale shaping algorithm. The algorithm is tested using real network traffic and shown to outperform FARIMA in both efficiency and accuracy. Specifically, the wavelet models are parsimonious, and have a computational complexity O(N) in developing a model from a training sequence of length N, and O(M) in generating a synthetic traffic trace of length M     

POMDP-Based Coding Rate Adaptation for Type-I Hybrid ARQ Systems over Fading Channels with Memory

We address the issue of optimal coding rate scheduling for adaptive type-I hybrid automatic repeat request wireless systems. In this scheme, the coding rate is varied depending on channel, buffer and incoming traffic conditions. In general, we consider the hidden Markov model for both time-varying flat fading channel and bursty correlated incoming traffic. It is shown that the appropriate framework for computing the optimal coding rate allocation policies is partially observable Markov decision process (POMDP). In this framework, the optimal coding rate allocation policy maximizes the reward function, which is a weighted sum of throughput and buffer occupancy with appropriate sign. Since polynomial amount of space is needed to calculate the optimal policy even for a simple POMDP problem, we investigate maximum-likelihood, voting and Q-MDP policy heuristic approaches for the purpose of efficient and real-time solution. Our results show that three heuristics perform close to completely observable system state case if the fading and/or traffic state mixing rate is slow. On the other hand, when the channel fading is fast, Q-MDP heuristic is the most throughput-efficient among considered heuristics. Also, its performance is close to the optimal coding rate allocation policy of fully observable system state case. We also explore the performances of the proposed heuristics in the bursty correlated traffic case and show that maximum-likelihood and voting heuristics consistently outperform the non-adaptive case     

On the predictability of next generation mobile network traffic using artificial neural networks

Though the introduction of the new 4th Generation mobile access technologies promises to satisfy the increasing bandwidth demand of the end‐users, it poses in parallel the need for novel resource management approaches at the side of the base station. To this end, schemes that try to predict the forthcoming bandwidth demand using supervised learning methods have been proposed in the literature. However, there are still open issues concerning the training phase of such methods. In the current work, the authors propose a novel scheme that dynamically selects a proper training set for artificial neural network prediction models, based on the statistical characteristics of the collected data. It is demonstrated that an initial statistical processing of the collected data and the subsequent selection of the training set can efficiently improve the performance of the prediction model. Finally, the proposed scheme is validated using network traffic collected by real, fully operational base stations. Copyright © 2013 John Wiley & Sons, Ltd.     

Intelligent detection method on network malicious traffic based on sample enhancement

To address the problem that the existing methods of network traffic anomaly detection not only need a large number of training sets,but also have poor generalization ability,an intelligent detection method on network malicious traffic based on sample enhancement was proposed.The key words were extracted from the training set and the sample of the training set was enhanced based on the strategy of key word avoidance,and the ability for the method to extract the text features from the training set was improved.The experimental results show that,the accuracy of network traffic anomaly detection model and cross dataset can be significantly improved by small training set.Compared with other methods,the proposed method can reduce the computational complexity and achieve better detection ability.     

Efficient image gradient based vehicle localization

This paper reports novel algorithms for the efficient localization and recognition of traffic in traffic scenes. The algorithms eliminate the need for explicit symbolic feature extraction and matching. The pose and class of an object is determined by a form of voting and one-dimensional (1-D) correlations based directly on image gradient data, which can be computed "on the fly." The algorithms are therefore very well suited to real-time implementation. The algorithms make use of two a priori sources of knowledge about the scene and the objects expected: (1) the ground-plane constraint and (2) the fact that the overall shape of road vehicles is strongly rectilinear. Additional efficiency is derived from making the weak perspective assumption. These assumptions are valid in the road traffic application domain. The algorithms are demonstrated and tested using routine outdoor traffic images. Success with a variety of vehicles in several traffic scenes demonstrates the efficiency and robustness of context-based image understanding in road traffic scene analysis. The limitations of the algorithms are also addressed.     

按需路由协议不同业务模式下性能仿真与分析

目前对移动Ad hoc网络的研究主要集中在新的应用上,如联合计算、投票系统、资源管理、协作游戏等。新应用使得Ad hoc网络业务模式不再是点对点模式。使用OPENT软件,首先对按需路由协议进行点对点通信性能仿真,其次通过改变源业务模式对协议的网络性能进行仿真,最后对实验结果进行分析。     

基于神经网络的红绿灯识别研究

交通灯的识别对人工智能以及无人驾驶都有着举足轻重的作用,本文研究交通识别中的红绿灯判断,用于改善驾驶员疲劳以及维护交通秩序从而提高驾驶安全系数减少交通事故的发生.通过机器视觉采集红绿灯交通信号图,运用Mat-lab进行图片处理截取红绿灯区域,提取每张图片的121个像素点RGB值,运用1和2分别表示绿灯和红灯,建立红绿灯...