Multisensor data fusion for surface land-mine detection

Receiver operating characteristic (ROC) curves have been used to examine a novel target recognition system using a number of knowledge-based techniques to automatically detect surface land mines that are present in 30 sets of thermal and multispectral images. A summary of the results, graphed at a probability of detection greater than or equal to 96%, shows the false-alarm rates (FARs) obtained using various combinations of fusing sensors and neural classifiers averaged over the 30 images. The results show that using two neural-network classifiers on the input textural and spectral characteristics of selected multispectral bands, we obtained FARs of approximately 3%. Using polarization-resolved images only, we obtained FARs of 1.15%. Fusing the best classifier output with the polarization-resolved images, we obtained FARs as low as 0.023%. This result has shown the large improvement gained in the sensor fusion. Also, an improvement is shown by comparing these results with those reported in an existing commercial system     

Multisensor fusion for atrial and ventricular activity detection incoronary care monitoring

Information management for critical care monitoring is still a very difficult task. Medical staff is often overwhelmed by the amount of data provided by the increased number of specific monitoring devices and instrumentation, and the lack of an effective automated system. Specifically, a basic task such as arrhythmia detection still produce an important amount of undesirable alarms, due in part to the mechanistic approach of current monitoring systems. In this work, multisensor and multisource data fusion schemes to improve atrial and ventricular activity detection in critical care environments are presented. Applications of these schemes are quantitatively evaluated and compared with current methods, showing the potential advantages of data fusion techniques for event detection in noise corrupted signals.     

采用D-S证据理论的双色红外小目标融合检测

针对远距离低信噪比条件下目标检测难的实际问题,提出采用D-S证据理论的双色红外小目标融合检测方法。该方法首先采用统计检测方法对各传感器图像进行目标检测处理;接着采用“或”逻辑对各传感器的目标检测结果进行融合,以降低目标漏检的可能性;然后在各传感器图像中提取融合检测结果中各候选目标区域的多个图像特征作为进一步消除虚警的证据;最后采用D-S证据理论对各候选目标区进行基于多特征的目标融合识别处理,并将识别结果作为整个系统最终的目标检测输出。实验结果证明了该算法的有效性。     

Multisensor data fusion for physical activity assessment

This paper presents a sensor fusion method for assessing physical activity (PA) of human subjects, based on support vector machines (SVMs). Specifically, acceleration and ventilation measured by a wearable multisensor device on 50 test subjects performing 13 types of activities of varying intensities are analyzed, from which activity type and energy expenditure are derived. The results show that the method correctly recognized the 13 activity types 88.1% of the time, which is 12.3% higher than using a hip accelerometer alone. Also, the method predicted energy expenditure with a root mean square error of 0.42 METs, 22.2% lower than using a hip accelerometer alone. Furthermore, the fusion method was effective in reducing the subject-to-subject variability (standard deviation of recognition accuracies across subjects) in activity recognition, especially when data from the ventilation sensor were added to the fusion model. These results demonstrate that the multisensor fusion technique presented is more effective in identifying activity type and energy expenditure than the traditional accelerometer-alone-based methods.     

Multisensor towed array detection system for UXO detection

The multisensor towed array detection system (MTADS) was designed to be an efficient, sensitive tool for the detection and characterization of buried unexploded ordnance. It comprises arrays of total-field magnetometers and time-domain electromagnetic induction (EMI) sensors, associated navigation and data acquisition hardware, and a custom data analysis system. The MTADS has conducted eleven demonstrations and surveys. The system has shown the ability to detect ordnance at its likely self-penetration depths with a probability of detection of 0.95 or better The model-derived positions and depths of the detected ordnance items are generally well within the physical size of the targets, making remediation much quicker and less costly than with standard techniques. Data sets corresponding to many of the MTADS surveys are available to others in the field     

An abrupt change detection algorithm for buried landmines localization

Ground-penetrating radars (GPRs) are very promising sensors for landmine detection as they are capable of detecting landmines with low metal contents. GPRs deliver so-called Bscan data which are, roughly, vertical slice images of the ground. However, due to the high dielectric permittivity contrast at the air-ground interface, a strong response is recorded at early time by GPRs. This response is the main component of the so-called clutter noise and it blurs the responses of landmines buried at shallow depths. The landmine detection task is therefore quite difficult. This paper proposes a new method for automated detection and localization of buried objects from Bscan records. A support vector machine algorithm for online abrupt change detection is implemented and proves to be efficient in detecting buried landmines from Bscan data. The proposed procedure performance is evaluated using simulated and real data.     

Multisensor detection of ionospheric phenomena

For the past several years, observations using a large number of geophysical sensors have been conducted at a site near Boulder, Colo. Data are continuously recorded on magnetic tape and have the advantages of a common time base and the availability of an on-line computer which performs data processing and controls the operation of the station. The original purpose of the installation was to study ground-based techniques for detection of high-altitude nuclear explosions. Scientific studies to which the data have been applied include the changes in the ionosphere during sudden ionospheric disturbances, ionospheric effects which appear to be related to severe thunderstorms, and the characteristics of traveling ionospheric disturbances which are believed to be related to magnetic activity. The system has the capability of automatically detecting sudden ionospheric disturbances and of providing real-time indices of ionospheric and magnetic activity.     

基于Rail-GPSAR实测数据的地雷检测新方法

本文借鉴恒虚警率(CFAR)思想估计图像数据中杂波的统计量,实现图像的预白化处理。在训练图像中选取地雷图像切片的距离向中心切线作为本征向量构造训练数据阵,获取检测器的参数估计,结合主分量分析设计高效的偏差最优线性二次(DOLQ)检测器。验证了DOLQ检测器输出的灰度图像服从Gamma分布,利用其分布参数和实测数据特点确定整体阈值。对得到的二元图像利用形态学操作获取可疑目标块,然后通过整体阈值和局部门限确定的自适应阈值对其进行二次检测,以确保无漏检的情况下尽可能降低虚警。基于图像中目标能量的空间范围,提出了利用能量环对预白化处理后的图像进行目标检测。最后,提出了一种将能量环与DOLQ检测器的检测结果进行决策级融合的新方法,完成对不同土壤环境、埋设深度地雷的检测。对实际图像的检测结果表明,新方法能够显著降低虚警,且具有较好的稳健性。     

基于最大隶属度与证据理论的目标识别融合

为解决各传感器的类型、精度,外界干扰以及不同传感器对不同目标敏感程度的不同对目标识别的决策结果的影响,通过运用智能信息处理和多源信息融合的相关知识建立了基于最大隶属度与证据理论的目标识别融合模型.该模型首先分析了影响目标识别的因素;然后各雷达站依据最大隶属度选取了不同的权重,从而求出了所测目标相对于目标库中参考目标的隶属度,并将得到的本站对目标的决策结果进行归一化处理后送往了融合中心.研究了比较常用的对不确定信息进行处理的D-S证据理论法,并深入分析了其证据合并规则与决策规则.在融合中心运用了D-S证据理论的有关知识进行融合,最终输出了融合后的目标识别的决策结果.实例证明了该目标识别融合模型的可行性.     

D-S证据理论数据融合算法在某系统故障诊断中的应用

介绍了Dempster-Shafer(D-S)证据理论数据融合算法的基本原理,在此基础上以电压-码转换电路板为被诊断对象,探索了基于D-S证据理论多传感器数据融合算法的某系统电路故障元器件诊断方法.诊断结果表明D-S证据理论多传感器信息融合算法可有效地提高故障模式的识别能力,使故障元器件得以有效定位.     

基于证据理论和神经网络的烟雾图像检测

烟雾图像检测对于预防火灾具有重要的研究意义,烟雾受到空气和自身扩散的作用,变化过程十分复杂,导致传统方法的检测效果差,为了解决该难题,提出证据理论和神经网络的烟雾图像检测方法。研究了当前烟雾图像检测状态,找到引起当前方法检测效果差的原因,提取烟雾图像特征,并采用神经网络得到烟雾图像检测结果,最后根据证据理论对神经网络的烟雾图像检测结果进行融合,并通过烟雾图像检测实验进行可行性验证,该方法烟雾图像检测正确率超过95%,获得了令人满意的烟雾图像检测结果。     

基于帧差检测技术与区域特征的红外与可见光图像融合算法

为了提高红外图像的融合质量并降低复杂度,提出一种基于帧差检测技术与区域特征的红外与可见光图像融合算法。首先,设计帧差法对红外图像中的目标完成检测,从而进行目标分簇与图像分割;并借助帧之间的信息完成目标的准确定位;再根据目标区域的特征设计不同的融合规则,充分利用可见光和红外图像的有效信息进行互补,完成图像融合,并对融合算法的复杂度进行理论分析。同时,在可见光和红外图像中目标不可动可观察及目标可运动可观察两种条件下进行融合实验,实验结果表明,与当前图像融合技术相比,所提技术具有更高的融合质量,其融合图像能够准确反映目标和背景。     

面向引线框架缺陷的图像配准算法

为了降低引线框架缺陷识别的误检率,比较了基于灰度的模板匹配和基于特征的匹配算法之间的优缺点,并针对引线框架缺陷检测中参考图和检测图存在差异的特点,提出基于区域定位和不变矩的特征匹配算法。该算法通过边缘检测定位出特征区域,并用不变矩进行区域特征描述。在缺陷识别试验中,相比于模板匹配算法,该算法表现出更快的结算速度,更高的配准精度,更低的配准失败概率。结果表明,该配准算法适用于引线框架缺陷识别,降低误检率。     

Single-particle theory of the free-electron laser in a moving frame

We give a summary of the theory of a single electron involved in free-electron laser (FEL) operation. We use the method of transformation to a predetermined moving frame where the wiggler-laser scattering process is elastic. In this paper, we discuss the classical and quantum dynamics of such an electron and evaluate perturbatively the lowest order FEL behavior from the classical pendulum equation. The presentation is tutorial throughout and stresses analytic results and physically significant dimensionless parameters. No results are included for the dynamic evolution of the light during the laser action.     

基才模糊C均值聚类和D-S证据理论的多传感器信息融合技术研究

D-S证据理论能很好地表达"不确定"和"未知"等信息融合中的重要概念,在多传感器信息融合领域得到了广泛的应用.针对传感器数量较多时,D-S方法计算量很大的问题,提出了利用模糊C均值聚类来减少证据体数目.再结合D-S证据理论进行信息融合的办法.实验数据表明,该方法大大减少了计算量,保证了目标识别的准确度.     

Robust data fusion for multisensor detection systems

Minimax robust data fusion schemes for multisensor detection systems with discrete-time observations characterized by statistical uncertainty are developed and analyzed. Block, sequential, and serial fusion rules are considered. The performance measures used, and made robust with respect to the uncertainties, include the error probabilities of the hypothesis testing problem in the block fusion case and the error probabilities and expected numbers of samples or sensors in the sequential and serial fusion cases. For different sensor observation statistics, the minimax robust fusion rules are derived for two asymptotic cases of interest: when the number of sensors is large and when the number of times the fusion center collects the local (sensor) decisions is large. Moreover, for the case of identical sensor observation statistics and a large number of sensors, it is shown that there is no loss in optimality, if local tests using likelihood ratios and equal thresholds are used in the sequential fusion rule. In all situations, the robust decision rules at the sensors and the fusion center are shown to make use of likelihood ratios and thresholds that depend on the least-favorable probability distributions of the uncertainty class describing the statistics of sensor observations     

Inexpensive fusion methods for enhancing feature detection

Recent successful approaches to high-level feature detection in image and video data have treated the problem as a pattern classification task. These typically leverage the techniques learned from statistical machine learning, coupled with ensemble architectures that create multiple feature detection models. Once created, co-occurrence between learned features can be captured to further boost performance. At multiple stages throughout these frameworks, various pieces of evidence can be fused together in order to boost performance. These approaches whilst very successful are computationally expensive, and depending on the task, require the use of significant computational resources. In this paper we propose two fusion methods that aim to combine the output of an initial basic statistical machine learning approach with a lower-quality information source, in order to gain diversity in the classified results whilst requiring only modest computing resources. Our approaches, validated experimentally on TRECVid data, are designed to be complementary to existing frameworks and can be regarded as possible replacements for the more computationally expensive combination strategies used elsewhere.     

Design of optimum sync and detection patterns for frame synchronisation

Frame synchronisation for a packet transmission system, in which the sync pattern is preceded by a known preamble, is considered. The correlation receiver uses an extended (or shortened) version of the sync pattern, which is called the detection pattern. This leads to a new criterion for designing optimum pairs of sync and detection patterns. The obtained patterns result in a normalised improvement of up to 3.91 dB over the known optimum patterns.     

Linear dispersion codes for MIMO systems based on frame theory

Multiple-input multiple-output (MIMO) wireless communication systems provide high capacity due to the plurality of modes available in the channel. Existing signaling techniques for MIMO systems have focused primarily on multiplexing for high data rate or diversity for high link reliability. In this paper, we present a new linear dispersion code design for MIMO Rayleigh fading channels. The proposed design bridges the gap between multiplexing and diversity and yields codes that typically perform well both in terms of ergodic capacity as well as error probability. This is important because, as we show, designs performing well from an ergodic capacity point of view do not necessarily perform well from an error probability point of view. Various techniques are presented for finding codes with good error probability performance. Monte Carlo simulations illustrate performance of some example code designs in terms of ergodic capacity, codeword error probability, and bit error probability.