共查询到20条相似文献，搜索用时 453 毫秒
1.
A linear FM sonar system was developed to support the objective of remote acoustic classification of seafloor sediments. It is a calibrated, wideband, digital, frequency modulated sonar that provides quantitative, high-resolution, low-noise sub-bottom data. Since the linear sonar system can precisely transmit a specified waveform, the calibrated digitally recorded reflection data can be processed to estimate the acoustic impulse response of the seabed and sediment attenuation. An acoustic pulse with special frequency domain weighting characteristics is designed to provide low temporal sidelobe levels and a nearly constant resolution with depth even after passing through a sediment with high losses such as sand. After correlation processing, the wideband acoustic pulse yields an effective beam pattern with high spatial resolution and insignificant sidelobe levels. Data sets generated with the FM profiler indicate that the required temporal and spatial characteristics of the sonar are realized in practice 相似文献
2.
Parametric transduction offers valuable advantages for underwater acoustic communications. Perhaps the most significant benefit is the fact that high directivity is achieved by means of a physically small transmit transducer. This feature may, ultimately, be employed to permit long-range, low-frequency communication using a compact source. The high directivity is desirable to combat multipath propagation and to achieve data communications in water which is shallow by comparison with range. A real-time, high data-rate “model” differential phase shift keying (DPSK) communication system has been constructed and demonstrated. This system uses parametric transduction, with a 300-kHz primary frequency and a 50-kHz secondary frequency. Experimental results show that the system can be employed to combat multipath propagation in shallow water and can achieve high data-rate text and color image transmission at 10 and 20 kb s-1 for 2-DPSK and 4-DPSK, respectively, through a transmission bandwidth of 10 kHz. The “model” system was developed to confirm performance predictions for a future, operational long-range link employing a 50-kHz primary frequency and a 5-kHz secondary frequency 相似文献
3.
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. 相似文献
4.
5.
6.
7.
8.
9.
黄河三角洲湿地地物精确分类对湿地资源的保护、开发和利用具有重要意义。目前的湿地分类算法大多存在着全局信息利用不足,地物类型边界不易区分等问题,导致分类精度不高。针对此问题,本文提出了基于双路图卷积的黄河三角洲湿地地物分类算法,包括图结构数据构建模块、特征提取与融合模块两部分。图结构数据构建模块,设计欧式图表示光谱值之间的绝对差异,衡量不同地物类型,设计余弦图表达不同像素光谱波形之间的差异,用以区分不同的地物边界;特征提取与融合模块,利用图卷积聚合全局信息,对欧式图利用双层图卷积进行特征提取,对余弦图使用图U-Net网络进行特征提取,之后将两个特征融合,得到同时具有光谱值绝对差异和光谱波形差异的融合特征,最后进行分类。在CHRIS和GF5两个数据集的实验结果表明,本文所提算法在黄河三角洲湿地地物分类中取得了具有竞争力的分类结果。 相似文献
10.
Acoustic echoes obtained during high-resolution shallow marine seismic surveys contain information about the statistical nature of the sedimentary bottom and its spatial variability. Use of a broad-band seismic source and an appropriately chosen data acquisition window makes the acoustic responses particularly amenable to quantitive analysis. The work reported utilizes experimental frequency-domain spatial coherence functions of along-track acoustic echoes as empirical metrics of bottom character, and by virtue of their correlation with known sediment types, as objective bases for remote sediment classification. Theoretical relationships between parameters describing sediment surface topographies and echo coherence are derived for the case of dominant water-sediment interface acoustic scattering. The diverse experimental data base was acquired from the Grand Banks of Newfoundland using a 1- to 10-kHz Huntec DTS system. Bottom photographs, cores, and grab samples combined with expert geological synthesis provide qualitative and quantitative control. 相似文献
11.
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 相似文献
12.
Seafloor sediment classification based on echo characteristics obtained from single-beam echosounder is very useful in remote
and instant sediment classification. Results of different classification techniques using such data provide robust results
when the acoustic beam has a normal incidence with the seabottom. This may not always be true and show poor classification,
with the data acquired during rough sea periods corresponding to both oblique and normal incidence of the acoustic pulse,
due to roll and pitch motion of the ship. In the present study, an attempt is made to exploit the artificial neural network
(ANN) techniques for better classification with such data. Learning Vector Quantisation (LVQ) is a supervised learning algorithm
of ANN that is found to be an effective tool and show good performance. The input data to the network include the roughness
index (E1) and hardness index (E2) derived from echo characteristics. The network utilizes the competitive learning, a distance
function in the first layer and a linear function in the second layer. The network was tried with a different size of hidden
neurons and training data size to see the influence on classification. It is found that with ten neurons in the first layer
and four neurons in the second layer good performance in classification for the data was achieved. 相似文献
13.
Tarek Elsayed 《Applied Ocean Research》2009,31(3):179-185
A multiple attribute risk assessment approach using a fuzzy inference system is developed in this work. The approach is based on the use of fuzzy sets, a rule base and a fuzzy inference engine. Traditional input probabilities and consequences used in risk assessment are represented by fuzzy sets to take into account uncertainties associated with the assignment of their values. The output risk values can be presented as crisp values or fuzzy sets with associated degree of membership. The fuzzy inference system FIS is used as an alternative approach to qualitative risk matrix techniques currently used in many industries and by ship classification societies. Two approaches for fuzzy inference are adopted. These include the Mamdani approach in which output risk values are fuzzy sets and the Sugeno method of fuzzy inference, in which output risk values are constant or linear.The use of a fuzzy set approach is particularly suited for handling multiple attribute risk problems with imprecise data. It improves upon existing qualitative methods and allows the ranking of risk alternatives based on a unified fuzzy risk index measure. Results show that while the Mamdani method is intuitive and well suited to human input, the Sugeno method is computationally more efficient and guarantees continuity of the final risk output surface. Results also show that computed risk values using a fuzzy risk index measure are consistent with those obtained using a qualitative risk matrix approach. The proposed methodology is also applicable to other ship operating modes such as transit in open sea and/or entering/leaving port. A case study for a liquefied natural gas LNG ship loading/offloading at the terminal is presented to demonstrate the developed approach capability. 相似文献
14.
An automatic approach to the detection and extraction of mine features in sidescan sonar 总被引：6，自引：0，他引：6
Mine detection and classification using high-resolution sidescan sonar is a critical technology for mine counter measures (MCM). As opposed to the majority of techniques which require large training data sets, this paper presents unsupervised models for both the detection and the shadow extraction phases of an automated classification system. The detection phase is carried out using an unsupervised Markov random field (MRF) model where the required model parameters are estimated from the original image. Using a priori spatial information on the physical size and geometric signature of mines in sidescan sonar, a detection-orientated MRF model is developed which directly segments the image into regions of shadow, seabottom-reverberation, and object-highlight. After detection, features are extracted so that the object can be classified. A novel co-operating statistical snake (CSS) model is presented which extracts the highlight and shadow of the object. The CSS model again utilizes available a priori information on the spatial relationship between the highlight and shadow, allowing accurate segmentation of the object's shadow to be achieved. 相似文献
15.
全极化合成孔径雷达(Synthetic Aperture Radar,SAR)数据具有丰富的极化信息,能够提取出大量异构性特征。核学习方法在解决小样本、高维特征分类问题上具有优势,但异构特征对不同核函数具有响应差异。本文利用一种引入先验标签的多核学习方法进行全极化SAR的溢油信息提取,即基于分析结果对特征集进行遴选与组合,分别在每个特征组合中训练得到一个预备层核函数,以新获取的预备层核函数作为新的底层核函数,对全部特征进行学习分类。通过提取与分析溢油和海水的统计特征、物理散射特征和纹理特征,建立溢油全极化SAR特征谱,并利用引入先验标签的多核学习分类器进行溢油提取实验。结果表明,该方法能够利用全极化SAR多维异构特征的互补特性有效提高溢油分类提取精度。 相似文献
16.
为了评价主成分分析方法和决策级数据融合方法对高光谱图像地物分类结果的影响,作者利用各分类器和主成分分量的优势,提出了两组地物分类结果的决策级融合策略,利用8种常用监督分类方法对高光谱原始图像和PCA变换后不同分量组合图分类得到的结果进行决策级融合,并应用覆盖黄河入海口新老河道交界处的CHRIS/PROBA高光谱图像开展实验研究。结果表明:直接采用每类地物分类精度最高的、空穴和缝隙采用总体分类精度最高的融合策略,在综合考虑生产者精度和用户精度的情形下,仅使用最大似然法、支持向量机和人工神经网络3种分类方法,按照分类精度从高到低的顺序进行的融合分类效果最好,总体分类精度为87.82%。与8种监督分类方法中效果最好的最大似然法相比,精度提高了2.7个百分点,同时明显减少了错分现象,尤其是对于分布面积较小的翅碱蓬和柽柳,滩涂被误分为翅碱蓬、芦苇被误分为柽柳的现象大大降低。 相似文献
17.
基于国家海洋信息中心质量控制后的西太平洋 10 度方区约 100 万站次温盐实测历史调查资料,对经过 26 种严格质量控制方法的综合海温质量符进行分类分析,首次将深度学习技术应用于海洋数据质量控制多分类 （multiclass classification）算法与应用研究。通过人工合成少数类样本和加权损失函数方法减少多数类的频率来降低数据的不平衡,并构建了多层感知器 （Multi-Layer Perceptron, MLP） 和深度神经网络 （Deep Neural Network, DNN） 两个海温资料质量符分类深度学习模型。分类结果表明本文构建的两个深度分类模型能够较准确快速地识别该海域海温数据质量,在 20 975 条温盐剖面资料测试集中分类准确率分别达到 99.63%和 99.69%。海温资料的分类精度评分有着较好的表现,其中正确数据 （QC1） 和数据缺失（QC9） 的正确识别率均达 100%。MLP 和 DNN 多分类质量控制模型可大幅降低传统质量控制方法的工作量,提升海量数据处理速度和分析能力,为海温观测资料在海洋研究与工程中应用提供参考。 相似文献
18.
The upper Indus Fan is characterized by an average 1∶500 gradient, chanels with 100 m high levees, several continuous subbottom reflectors on 3.5-kHz records, and generally fine-grained sediments. Multichannel seismics show the levee complexes typified by overlapping wedge-shaped reflection sets and channel axis by high-amplitude discontinuous reflections. The middle fan has 1∶500–1∶1000 gradients and channels with ≈20 m high levees. The lower fan has gradients less than 1∶1000, channels with 8–20 m high levees, few or no subbottom reflectors on 3.5-kHz records, and high sand content. Besides the dominant unchannelized turbidity currents, channelized and overbank flows also played a significant role in the sedimentation of the lower fan. 相似文献
19.
A nondestructive method of measuring in situ the oil-water interface in a sunken oil barge is described. The method makes use of the different acoustic absorption properties of water and BunkerC oil to detect the oil-water interface and can be implemented using a standard 200-kHz echo sounder. An electrically driven bottom-crawling remotely controlled vehicle used to carry out field tests on a sunken oil barge is described, and samples of the sounder records obtained are presented. Results indicate the method is feasible for tanks of simple geometry that have distinct layers of liquids with sufficiently different acoustic absorption properties. 相似文献
20.
基于多源水深数据融合的海底高精度地形重建 总被引：2，自引：0，他引：2
本文在研究多源水深数据构建技术的基础上,分析了张力样条插值算法和“移去-恢复”法的多源水深数据融合处理技术,基于该方法选取实验区,利用多波束、单波束、历史海图等多源水深数据进行高精度海底地形融合试验,并针对多源水深融合技术缺少误差评估的现状,利用split-sample方法对融合结果进行水深不确定性评估,形成融合结果的可靠性空间分布。结果表明该方法无论是在数据稀疏区还是高密度区都达到了较好的融合效果,既保留了高分辨率水深数据的细节信息,又较真实的反映了研究区海底地形特征,且构建的海底地形精度可靠,误差百分比集中在0.5%。本文整套数据融合和结果评估方法可为多源水深数据融合的海底高精度地形构建提供借鉴和参考。 相似文献