A neural network based hybrid system for detection,characterization, and classification of short-duration oceanic signals

A comprehensive classifier system is presented for short-duration oceanic signals obtained from passive sonar, which exhibit variability in both temporal and spectral characteristics even in signals obtained from the same source. Wavelet-based feature extractors are shown to be superior to the more commonly used autoregressive coefficients and power spectral coefficients for describing these signals. A variety of static neural network classifiers are evaluated and are shown to compare favorably with traditional statistical techniques for signal classification. The focus is on those networks that are able to time-out irrelevant input features and are less susceptible to noisy inputs, and two new neural-network-based classifiers are introduced. Methods for combining the outputs of several classifiers to yield a more accurate labeling are proposed and evaluated. These methods lead to higher classification accuracy and provide a mechanism for recognizing deviant signals and false alarms. Performance results are given for signals in the DARPA standard data set I     

Classification of transient sonar sounds using perceptually motivated features

This paper describes a novel framework for classifying underwater transient signals recorded by passive sonar. The proposed approach involves two key ideas. Firstly, a feature-selection algorithm is used to identify those acoustic features that optimally model each class of transient sound. Secondly, features that are perceptually motivated are proposed, i.e., they encode information that human listeners are likely to use in transient classification tasks. Three perceptual features are proposed, which encode timbre, the physical material of the sound source, and the temporal context (pattern) in which the transient occurred. The authors show how these features, which are computed over different temporal windows, can be combined to make classification decisions. The performance of the proposed classifier is evaluated on a corpus of transient signals extracted from passive sonar recordings. Specifically, the performance of the perceptual features is compared with spectral features and with those that encode statistics of time, frequency, and power. The present results show that the perceptual features provide valuable cues to the class of a transient. However, the best performing classifier was obtained by selecting a subset of perceptual, spectral, and statistical features in a class-dependent manner.     

基于BP网络对模拟声呐信号分类

针对常规的主动声呐调查设备,在简单海洋分层模型的基础上,模拟了多波束类单频信号、侧扫类单频信号、Ch irp调频信号和混合信号4类声呐接收信号,并针对接收信号特征构造了3层BP网络模型,将隐藏层神经元数目设为可调节;利用时间域脉冲宽度和水深与频率域功率谱密度相结合的特征参量,成功地对模拟信号进行了分类。采用改进的BP网络模型,用训练成功的BP网络对102个检测信号进行了分类测试,结果表明,分类成功率较高,可达76%~84.6%,因而利用BP网络可以对不同类别设备的模拟声呐接收信号进行分类。     

A comparison of inter-frame feature measures for robust objectclassification in sector scan sonar image sequences

This paper presents an investigation of the robustness of an inter-frame feature measure classifier for underwater sector scan sonar image sequences. In the initial stages the images are of either divers or remotely operated vehicles (ROV's). The inter-frame feature measures are derived from sequences of sonar scans to characterize the behavior of the objects over time. The classifier has been shown to produce error rates of 0%-2% using real nonnoisy images. The investigation looks at the robustness of the classifier with increased noise conditions and changes in the filtering of the images. It also identifies a set of features that are less susceptible to increased noise conditions and changes in the image filters. These features are the mean variance, and the variance of the rate of change in time of the intra-frame feature measures area, perimeter, compactness, maximum dimension and the first and second invariant moments of the objects. It is shown how the performance of the classifier can be improved. Success rates of up to 100% were obtained for a classifier trained under normal noise conditions, signal-to-noise ratio (SNR) around 9.5 dB, and a noisy test sequence of SNR 7.6 dB     

A neural network approach to classification of sidescan sonarimagery from a midocean ridge area

A neural-network approach to classification of sidescan-sonar imagery is tested on data from three distinct geoacoustic provinces of a midocean-ridge spreading center: axial valley, ridge flank, and sediment pond. The extraction of representative features from the sidescan imagery is analyzed, and the performance of several commonly used texture measures are compared in terms of classification accuracy using a backpropagation neural network. A suite of experiments compares the effectiveness of different feature vectors, the selection of training patterns, the configuration of the neural network, and two widely used statistical methods: Fisher-pairwise classifier and nearest-mean algorithm with Mahalanobis distance measure. The feature vectors compared here comprise spectral estimates, gray-level run length, spatial gray-level dependence matrix, and gray-level differences. The overall accurate classification rates using the best feature set for the three seafloor types are: sediment ponds, 85.9%; ridge flanks, 91.2%; and valleys, 80.1%. While most current approaches are statistical, the significant finding in this study is that high performance for seafloor classification in terms of accuracy and computation can be achieved using a neural network with the proper combination of texture features. These are preliminary results of our program toward the automated segmentation and classification of undersea terrain     

Single-ping target speed and course estimation using a bistatic sonar

This paper focuses on estimating the two-dimensional (2-D) target-speed vector (course and speed) using a multistatic sonar that consists of one monostatic sonar and one bistatic receiver. The speed and course estimates are obtained after a single transmission. The theory on bistatic Doppler and 2-D target-speed vector estimation is first considered and then applied to simulated and real data. The results can be used to improve classification algorithms or to feed speed information to tracking algorithms, for example.     

Active impulsive echo discrimination in shallow water by mappingtarget physics-derived features to classifiers

One of the most difficult challenges in shallow-water active sonar processing is false-alarm rate reduction via active classification. In impulsive-echo-range processing, an additional challenge is dealing with stochastic impulsive source variability. The goal of active classification is to remove as much clutter as possible while maintaining an acceptable detection performance. Clutter in this context refers to any non-target, threshold-crossing cluster event. In this paper, we present a clutter-reduction algorithm using an integrated pattern-recognition paradigm that spans a wide spectrum of signal and image processing-target physics, exploration of projection spaces, feature optimization, and mapping the decision architecture to the underlying good-feature distribution. This approach is analogous to a classify-before-detect strategy that utilizes multiple informations to arrive at the detection decision. After a thorough algorithm evaluation with real active sonar data, we achieved over an order of magnitude performance improvement in clutter reduction with our methodology over that of the baseline processing     

基于粒子群优化算法的PSO-BP海底声学底质分类方法

利用粒子群优化算法（PSO）较强的鲁棒性和全局搜索能力等优点,将PSO算法与BP神经网络相结合,优化了BP神经网络分类时的初始权值和阈值。基于珠江河口三角洲的侧扫声呐图像数据,提取了海底声呐图像中砂、礁石、泥3类典型底质的6种主要特征向量,利用PSO-BP方法对海底底质进行分类识别。实验表明,3类底质分类精度均大于90%,高于BP神经网络70%左右的分类精度,表明PSO-BP方法可有效应用于海底底质的分类识别。     

Active learning for detection of mine-like objects in side-scan sonar imagery

A data-adaptive algorithm is presented for the selection of the basis functions and training data used in classifier design with application to sensing mine-like targets with a side-scan sonar. Automatic detection of mine-like targets using side-scan sonar imagery is complicated by the variability of the target, clutter, and background signatures. Specifically, the strong dependence of the data on environmental conditions vitiates the assumption that one may perform a priori algorithm training using separate side-scan sonar data collected previously. In this paper, a novel active-learning algorithm is developed based on kernel classifiers with the goal of enhancing detection/classification of mines without requiring an a priori training set. It is assumed that divers and/or unmanned underwater vehicles (UUVs) may be used to determine the binary labels (target/clutter) of a small number of signatures from a given side-scan collection. These sets of signatures and associated labels are then used to train a kernel-based algorithm with which the remaining side-scan signatures are classified. Information-theoretic concepts are used to adaptively construct the form of the kernel classifier and to determine which signatures and associated labels would be most informative in the context of algorithm training. Using measured side-looking sonar data, the authors demonstrate that the number of signatures for which labels are required (via diver/UUV) is often small relative to the total number of potential targets in a given image. This procedure designs the detection/classification algorithm on the observed data itself without requiring a priori training data and also allows adaptation as environmental conditions change.     

基于虚警函数的侧扫声纳水下目标实时检测方法

研究了侧扫声纳系统进行水下目标探测过程中目标信号的检测问题。通过分析海底回波信号的统计模型及其参数的估计,讨论了目标信号对统计模型拟合的影响规律,提出了侧扫声纳回波信号虚警函数和虚警率的概念,及其对Ping信号中目标信号的检测方法。算例结果表明,回波信号的三种分布模型中K分布拟合程度最优,在相同虚警率的条件下,基于K分布的虚警函数目标检测率最高。该法可为侧扫声纳回波信号中目标的实时报警提供技术支撑。     

Segmentation and classification of shallow subbottom acoustic data,using image processing and neural networks

Subbottom acoustic profiler provides acoustic imaging of the subbottom structure constituting the upper sediment layers of the seabed, which is essential for geological and offshore geo-engineering studies. Delineation of the subbottom structure from a noisy acoustic data and classification of the sediment strata is a challenging task with the conventional signal processing techniques. Image processing techniques utilise the spatial variability of the image characteristics, known for their potential in medical imaging and pattern recognition applications. In the present study, they are found to be good in demarcating the boundaries of the sediment layers associated with weak acoustic reflectivity, masked by noisy background. The study deals with application of image processing techniques, like segmentation in identification of subbottom features and extraction of textural feature vectors using grey level co-occurrence matrix statistics. And also attempted classification using Self Organised Map, an unsupervised neural network model utilising these feature vectors. The methodology was successfully demonstrated in demarcating the different sediment layers from the subbottom images and established the sediments constituting the inferred four subsurface sediment layers differ from each other. The network model was also tested for its consistency, with repeated runs of different configuration of the network. Also the ability of simulated network was tested using a few untrained test images representing the similar environment and the classification results show a good agreement with the anticipated.     

二维小波变换在侧扫声图目标检测中的应用

针对侧扫声纳图像目标边缘检测困难的问题,利用二维离散小波变换对侧扫声纳(SSS)声图进行多分辨率分析,对大尺度分解的小波系数进行非极大值抑制,并重构小尺度上的低频分量。联合各尺度上的低频分量,构建SSS声图像素点处特征向量,构成其特征空间,对特征空间进行主成分分析,压缩其维数,并对压缩后的特征向量进行K-均值聚类分析,提取类间边缘线。利用含有沉船的SSS声图,并在其均质区域内加入目标与声影进行验证实验。该方法在实验中边缘检测准确率为0.90,表明该方法的有效性。     

基于频域典型相关分析的水下目标回波识别

水下目标回波的特征提取与分类识别是当前主动声纳关键技术之一。采用基于回波频域特性的典型相关分析算法(CCA:Canonical Correlation Analysis)提取回波的特征,这些特征集中体现了不同目标回波的综合相关特性。设计合适的支持向量机分类器,并获得识别结果。利用这一方法对湖试中的不同目标回波进行分类识别,分析了不同接收信噪比条件下的性能,获得了理想的结果。     

济州岛南部海域海底声呐图像分析与声学底质分类

东海北部外陆架靠近济州岛南部海域,是黄海槽向冲绳海槽延伸的部分,属于黑潮分支黄海暖流的通道入口,分布着脊槽相间的海底底形,对其海底声呐图像的处理分析及声学底质分类的分析研究,有助于了解该通道海底底形表层纹理特征及沉积物分布规律。基于在济州岛南部海域获取的多波束声呐数据,应用图像处理技术和方法,对数据进行了处理,获得了海底声呐影像图,并对其表层纹理特征进行了描述和分析;同时,基于多波束反向散射强度数据,结合19组海底地质取样数据,建立研究区海底反向散射强度与沉积物粒度特征之间的统计关系模型,并以改进的学习向量量化神经网络方法,实现对海底粉砂质砂、黏土质砂以及砂-粉砂-黏土3种底质类型的快速自动分类识别。     

Undersea Target Classification Using Canonical Correlation Analysis

Canonical correlation analysis is employed as a multiaspect feature extraction method for underwater target classification. The method exploits linear dependence or coherence between two consecutive sonar returns, at different aspect angles. This is accomplished by extracting the dominant canonical correlations between the two sonar returns and using them as features for classifying mine-like objects from nonmine-like objects. The experimental results on a wideband acoustic backscattered data set, which contains sonar returns from several mine-like and nonmine-like objects in two different environmental conditions, show the promise of canonical correlation features for mine-like versus nonmine-like discrimination. The results also reveal that in a fixed bottom condition, canonical correlation features are relatively invariant to changes in aspect angle.     

Real time time-frequency active sonar processing: a SIMD approach

A paradigm for massively parallel processing of matched filters, replica correlators, ambiguity functions, and time-frequency distributions is presented, using a SIMD (single instruction stream, multiple data stream) programming methodology. It is shown that active sonar detection algorithms, as implemented by frequency domain processing, can be a natural match to a SIMD methodology, meeting the extensive computational needs of enhanced active sonar systems. The decomposition process is presented, and examples are given of the output of the computer program CMASP (Connection Machine Ambiguity Surface Processor). CMASP can provide real-time simultaneous multiple-beam, Doppler, and waveform replica correlations. Synthetic data are processed, and the corresponding CMASP outputs are displayed as three-dimensional ambiguity surfaces on networked graphic workstations. Because of efficient problem decomposition, other time-frequency processing can be exploited. Specifically, real-time instantaneous-like time-frequency distributions have been realized in which the data set is presented and processed as time-varying spectral representations     

Seabed Classification Using BP Neural Network Based on GA

INTRODUCTIONUnderwaterremotesensingtools,suchasmulti beam ,sidescansonar,sub bottom pro file ,video ,etc .,arenormalmeanstoexploreseabed .Foreaseofnotation ,sidescansonarim ageisusedtodemonstrateseabedimage .Sidescansonarisakindofhigh resolutionimagingandcancontinuouslymonitorthechangesofseafloor.Inordertorelievetechniciansfromhardhandwork ,theautomaticclassificationbycomputerisneeded .Differentfromthespatialremotesensingimage ,underwatersonarimageistheformernon multi spectralimage .Theo…     

Searching for seafloor massive sulfides: a quantitative review of high-resolution methods in deep sea sonar bathymetry for mining applications

Seafloor massive sulphides are deep sea mineral deposits currently being examined as a potential mining resource. Conventional sonar bathymetry products gathered by sea surface platforms do not achieve adequate spatial resolution to detect these resources. High-resolution beamforming methods (such as multiple signal classification and estimation of signal parameters via rotational invariance techniques) improve the resolution of sonar bathymetry. We perform a quantitative review of these high-resolution methods using a novel simulator, showing results in the absence of platform motion for a single ping cycle. It was found that high-resolution methods achieved greater bathymetric accuracy and higher resolution than conventional beamforming and that these methods may be adequate for this style of marine exploration. These methods were also robust in the presence of unwanted persistent signals and low signal to noise ratios.     

High-resolution beamforming by the Wigner-Ville distribution method

The Wigner-Ville distribution (WVD) function was originally proposed by Wigner in quantum mechanics and Ville applied it for signal analysis. This method has made it possible to represent a signal's power density spectrum in the time-frequency domain as a natural extension of the Fourier transform method (FTM). Recently, it has attracted great interest for its validity to analyze time-varying signals accomplished by the development of high-speed digital signal processing, and it is used for analyzing nonstationary signals. Conventionally, a sonar beamformer is constructed using delay lines, but the development of the high-speed processor has made it possible to apply the FTM for sonar beamforming. However, the bearing resolution of the beamformer is not enough for discriminating small underwater objects on the sea bottom by this method. To solve this problem, we aim to apply the WVD method, which can represent finer structure of signals as a natural extension of the FTM, for sonar beamforming to obtain sharper beam patterns than those of the beamforming method by FTM. Simulation results by computational calculations to clarify the resolution by the WVD method, which is presented in this paper, becomes approximately twice as high as by conventional FTM. The results of an experiment at sea also show the performance of this method