目标地震动信号的特征提取及识别研究

地面目标的地震动信号是目标识别的关键,本文研究了机动目标地震动特性,总结出目标的地震动信号的特征提取规律,并将神经网络方法用于目标的地震动信号的分类识别中。给出了识别结构及改进的BP算法,并将改进的BP算法用于实际目标的地震动信号的分类识别,得到令人满意的结果。     

用1(1/2)维谱结合小波包能量提取地震动信号特征

针对车辆（轮式车、履带式车）引起的地震动信号中,具有非平稳、非高斯性特征相互重叠的实际情况,研究了地面活动目标产生的地震动信号特性;从理论上说明了1(1/2)维谱可消除车辆引起的地震动信号中的高斯白噪声或有色噪声,在将[112]维谱分析和小波包能量谱相结合的基础上,提出一种特征提取方法,以便区分不同的车辆目标。在时频域构建以[112]维谱和小波包能量谱作为地震动信号的联合特征向量,建立以训练误差为目标的BP神经网络模式分类器;然后对两类车辆信号进行识别。地震动信号的车辆实测数据表明,该方法能够准确和有效地识别车辆引起的地震动信号。     

基于BPSO-KNN算法的被动声呐目标分类识别技术研究

以提取得到的被动声呐目标功率谱特征为基础,采用二进制粒子群(Binary Particle Swarm Optimization, BPSO)优化算法和k最近邻(k-Nearest Neighbor, KNN)分类算法相结合的BPSO-KNN算法进行特征选择和参数优化,分别用KNN分类算法和BPSO-KNN分类算法对实际得到的四类海上被动声呐目标进行分类识别。结果表明,BPSO-KNN算法可对提取的功率谱特征进行特征优化选择,并对KNN分类器进行参数优化,提高了对四类目标的分类精度。该算法在被动声呐目标分类识别方面有参考价值。     

复合基神经网络在水声目标分类识别中的应用

本文根据不同神经网络的分类特点，提出将径向基函数网络和多层感知器网络复合构成复合基网络，用于水声信号的分类识别，试验表明，该网络的分类能力及对未来训练目标的适应性优于ＢＰ网和ＲＢＦ网。     

光电图像序列运动弱目标实时检测算法

针对光电探测图像序列中的运动弱小目标实时检测问题,提出了一种基于时空域融合滤波的弱目标检测算法。算法在空域上利用形态学Tophat滤波抑制背景增强目标,在时域上通过改进的帧间差分方法增强运动目标,两者融合后经自适应门限分割与航迹关联确认目标。实际录取数据分析结果表明,算法全面考虑运动弱小目标在时域与空域方面的特性,能更有效地从复杂背景中检测低信噪比运动弱小目标,减小了虚警率,抗噪声干扰能力强。     

复音音调提取及其在目标识别中的应用

提出了基于自相关原理提取音调的具体方法和步骤,以乐音和舰船辐射噪声为例,采用3层BP神经网络目标分类器进行仿真实验。仿真结果证明音调是有效的识别特征,且音调的识别率与目标辐射声信号的频率特性的可分性有关。频率特性的可分性越高,则目标识别率越高;当可分性不高时,可以将音调和其他主观量结合共同作为识别特征。实验表明,将特性响度作为目标特征,与音调特征结合起来,目标识别率得到进一步提高。     

基于图像序列的运动目标检测识别的关键技术研究

为提高运动目标检测的识别效果,通过分析、综合比较各种运动目标检测算法的优劣性,提出了基于全局自适应帧差法和基于码本模型的背景减除法对同一运动目标进行检测。通过对运动目标检测提取运动目标的掩膜,对掩膜进行外接矩形分析,从而得到包围运动目标的矩形框;将矩形框内的图片截取出来,调整该矩形并提取图片的HOG特征,最后通过训练好的SVM进行分类。在训练过程中,针对难易情况应用自举法对训练器进行优化。实验表明,与传统HOG+SVM多尺度检测算法相比,该方法在速度和准确性上可提升20%左右,可作为运动目标检测与识别的参考方法。     

基于主分量分析的声信号特征提取及识别研究

主分量分析(PCA)是统计学中分析数据的一种有效方法。研究了基于这种算法对四种战场目标的声信号进行特征提取,获得了低维的特征类器对声目标进行分类,分类结果准确率较高,均获得满意的实验效果     

基于VMD与共振稀疏分解的舰船辐射噪声窄带特征提取

为了获取实测舰船辐射噪声信号中有效的目标信息、提高低信噪比条件下目标信号的可分性,文章提出了结合变分模态分解(Variational Mode Decomposition,VMD)和共振稀疏分解(Resonance-based Sparsity Signal Decomposition,RSSD)的舰船辐射噪声信号特征提取方法。基于舰船辐射噪声信号具有一定的周期性而外界干扰具有随机性的特点,首先利用VMD自相关分析的方法重构信号,主要剔除带外噪声分量;然后采用RSSD算法基于信号共振属性的不同,进一步滤除带内噪声和瞬态干扰,实现对信号中周期性振荡成分的提取;最后提取信号的波形结构特征用于目标的分类识别。仿真信号与实测信号分析表明,该方法可以较好地滤除带内外噪声,增强舰船辐射噪声信号固有的窄带特征。多类舰船目标的分类实验结果表明,该方法可以有效提高低信噪比信号的可分性,有利于提高目标识别的性能。     

Intelligent Seismic Acceleration Signal Processing for Damage Classification in Buildings

Three new pattern recognition methods, based on fuzzy logic techniques that are suitable for seismic acceleration signal classification, are proposed in this paper. The classification of unknown signals is carried out according to the structural or architectural damage that is produced by the seismic signals. A set of 400 natural accelerograms, which have been recorded in various regions with well-known strong seismic activity, has been used for evaluation of the proposed methods. The seismic accelerograms are first treated as graphs; the similarity between them is exploited in order to perform the classification. In the second approach, a set of parameters are derived from each signal through computer analysis. These describe effectively the intensity measure of the seismic excitation, and they are used instead of the accelerograms. Similarity between them is appropriately utilized. Finally, a method that depends purely on fuzzification of the accelerograms parameters is also described. Classification results are presented for each method, and correct classification rates up to approximately 85% are recorded. The contribution of this paper to seismic signal classification lies in the methodology that allows for classification of seismic signals according to the damage in buildings. This process depends strongly on the structural parameters of the specific building, and therefore, given a building and a seismic signal, each signal can be classified into one of the four well-defined and scientifically approved damage classes. Consequently, the proposed paper contributes an effective method for engineers to test the response of a building to seismic signals, produced by earthquakes.     

基于深度置信网络与信息融合的齿轮故障诊断方法

针对齿轮在复杂运行工况下故障特征提取困难,传统故障诊断方法的识别精度易受人工提取特征的影响,以及单传感器获取信息不全面等问题,提出基于深度置信网络(DBN)与信息融合的齿轮故障诊断方法。通过多传感器信息融合技术对每个传感器采集的振动信号进行数据层融合;利用DBN进行自适应特征提取从而实现故障分类。为了避免因人为选择DBN结构参数,导致模型识别精度下降的问题,利用改进的混合蛙跳算法(ISFLA)对DBN结构参数进行优化。试验表明,与BP神经网络、未经优化的DBN以及单传感器故障诊断相比,该研究提出的信息融合及优化方法具有更高的故障识别精度。     

Analysis and classification of malignancy in pancreatic magnetic resonance images using neural network techniques

Computer-aided diagnosis (CAD) is a computerized way of detecting tumors in MR images. Magnetic resonance imaging (MRI) has been generally used in the diagnosis and detection of pancreatic tumors. In a medical imaging system, soft tissue contrast and noninvasiveness are clear preferences of MRI. Inaccurate detection of tumor and long time consumption are the disadvantages of MRI. Computerized classifiers can greatly renew the diagnosis activity, in terms of both accuracy and time necessity by normal and abnormal images, automatically. This article presents an intelligent, automatic, accurate, and robust method to classify human pancreas MRI images as normal or abnormal in terms of pancreatic tumor. It represents the response of artificial neural network (ANN) and support vector machine (SVM) techniques for pancreatic tumor classification. For this, we extract features from MR images of pancreas using the GLCM method and select the best features using JAFER algorithm. These features are analyzed by five classification techniques: ANN BP, ANN RBF, SVM Linear, SVM Poly, and SVM RBF. We compare the results with benchmark data set of MR brain images. The analytical outcome presents that the two best features used to classify the MR images using ANN BP technique have 98% classification accuracy.     

频谱相似性目标识别算法

地面运动目标识别的难点是对不同类型车辆目标的识别。介绍了一种地面运动目标的信号识别方法——频谱相似性,详细地叙述了频谱相似性算法的原理,从理论上证明了算法的正确性。通过对实际采集轮式和履带车辆行驶时所发出的声信号作为样本进行训练,再对测试声信号采用频谱相似性算法进行识别,实验结果证明了该算法的可行性。与复杂声信号识别算法相比,该算法具有计算量小、易于移植到DSP等小型信号处理器件上的优点。     

双微阵列语音增强算法在说话人识别中的应用

针对复杂噪声环境下识别性能显著降低的问题,提出一种用于说话人识别系统前端的双微阵列语音增强算法。该算法采用的是相干滤波和频域宽带最小方差无畸变响应波束形成器后置结合改进的维纳滤波器。其基本原理是首先求出双微麦克风阵列信号中两个相邻通道间的相干函数,再利用通道间信号的相干性来进行初始噪声抑制。其次,通过一个频域宽带最小方差无畸变响应(Minimum Variance Distortionless Response,MVDR)波束形成器保留目标声源方向的信号并抑制其他方向的信号干扰,再通过改进的维纳滤波器去除噪声残留提升语音质量。最后,使用梅尔频率倒谱系数(Mel Frequency Cepstral Coefficients,MFCC)和伽马通滤波器组频率倒谱系数(Gammatone Filter-bank Frequency Cepstral Coefficients,GFCC)对增强后的语音信号做特征参数提取并进行说话人识别。仿真过程采用声学人工头模拟双耳采集数据,实验结果表明,该语音增强算法在复杂噪声环境下能够获得较好的增强效果,能有效提升说话人识别系统的识别率。     

基于字典学习的主动声呐目标分类方法

主动声呐目标分类在军事和民用方面都有重要的应用和价值。文章基于稀疏表示理论,结合K-奇异值分解和正交匹配追踪算法,提出一种基于学习字典的稀疏表示分类方法（Dictionary Learning Sparse Representation Classification,DLSRC）。首先,利用K-奇异值分解算法训练各个类别目标回波信号,得到带有目标特征信息的类别字典,类别字典对信号具有良好表征能力并且带有目标类别信息;然后,利用正交匹配追踪算法和各个类别字典稀疏分解测试信号,得到各个类别字典下的稀疏系数后重构信号;最后,根据各个重构信号与测试信号的匹配度判定类别,得到分类准确率。结果显示,200个测试数据在信噪比分别为-5、-3、6 dB时,DLSRC法的分类准确率分别达到87%、89%、95.5%。不同信噪比下基于学习字典稀疏表示分类方法的准确率均高于已有的支持向量机（Support Vector Machine,SVM）、K-最近邻（K-Nearest Neighbor,KNN）和柔性最大值分类器（SoftMax）等分类方法,具有较好的分类性能。     

模糊融合分类器在水雷识别中的应用

当目标的类别多时会使分类器的精度和稳健性大受影响,用神经网络分类器去完成复杂的目标分类任务是难以保证其可靠性的。引入信息融合条件下一种新型的分类器,即模糊融合分类器,该分类器可以自动“过滤”无效和冗余特征的负面影响,实现有效的特征层融合识别。采用4种特征提取方法,利用三个模糊融合神经网络作为分类器进行特征层的融合,再将分类器的输出作为决策层的融合,提高系统的分类性能。通过处理水雷实体回波数据得出的识别率表明,所选取的特征提取和分类器算法是有效的。     

Supervised target detection and classification by training on augmented reality data

A proof of concept for a model-less target detection and classification system for side-scan imagery is presented. The system is based on a supervised approach that uses augmented reality (AR) images for training computer added detection and classification (CAD/CAC) algorithms, which are then deployed on real data. The algorithms are able to generalise and detect real targets when trained on AR ones, with performances comparable with the state-of-the-art in CAD/CAC. To illustrate the approach, the focus is on one specific algorithm, which uses Bayesian decision and the novel, purpose-designed central filter feature extractors. Depending on how the training database is partitioned, the algorithm can be used either for detection or classification. Performance figures for these two modes of operation are presented, both for synthetic and real targets. Typical results show a detection rate of more that 95% and a false alarm rate of less than 5%. The proposed supervised approach can be directly applied to train and evaluate other learning algorithms and data representations. In fact, a most important aspect is that it enables the use of a wealth of legacy pattern recognition algorithms for the sonar CAD/CAC applications of target detection and target classification     

Ground Nephogram Recognition Algorithm Based on Selective Neural Network Ensemble

In view of the low accuracy of traditional ground nephogram recognition model, the authors put forward a k-means algorithm-acquired neural network ensemble method, which takes BP neural network ensemble model as the basis, uses k-means algorithm to choose the individual neural networks with partial diversities for integration, and builds the cloud form classification model. Through simulation experiments on ground nephogram samples, the results show that the algorithm proposed in the article can effectively improve the Classification accuracy of ground nephogram recognition in comparison with applying single BP neural network and traditional BP AdaBoost ensemble algorithm on classification of ground nephogram.     

基于边界不变特征的扩展目标识别方法

提出一种新的以边界不变矩作为识别特征,运用BP网络识别扩展目标的方法。首次通过详细的理论证明和实验分析,揭示了离散边界不变矩不再具有严格的比例不变性,而位移和旋转不变性保持相对稳定,并对该不变矩作为识别特征的误差进行了深入分析,给出了正确计算边界不变矩的途径。在此基础上,以该边界不变矩作为识别特征,输入BP网络,采用合理的网络结构,实现对发生位移、旋转和尺度变化的扩展目标的识别。边界不变特征的引入,减少了数据运算量,实验结果表明,识别率达到95.9%。     

基于改进YOLOv5的旋转目标检测算法及其应用研究

目的 提高工业分拣上常见的纹理多样、随机堆放盒体的检测与识别能力。方法 提出一种基于YOLOv5的旋转目标检测算法，该算法包括目标分类、位姿角度识别和边界框位置定位3个模块功能。目标分类模块中，通过自建数据集和设计8种目标分类标签以供模型分类学习;位姿角度识别模块对YOLOv5头网络中添加角度预测分支，引入环形平滑标签角度分类方法，实现分拣盒体的旋转角度精准检测;在边界框位置定位模块上，使用LCIoU回归框损失函数来计算旋转框回归损失，得到紧密包裹目标位置的边界框。结果 改进的YOLOv5算法在自建数据集上检测精度达到95.03%，在机器人多物体分拣实验中的准确率可达100%。结论 本文算法在盒体处于散乱堆放、密集堆放、堆叠堆放场景下均具有较高的定位与识别精度。