共查询到20条相似文献，搜索用时 343 毫秒
1.
2.
3.
基于粒子群优化算法的PSO-BP海底声学底质分类方法 总被引：2，自引：2，他引：0
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。 相似文献
4.
Selection of a set of dominant echo features to classify seafloor sediments using a multilayer perceptron neural network is
investigated at two acoustic frequencies (33 and 210 kHz). Several sets of inputs with different combinations of two, three,
four, five, and six echo features are exploited with three-layer neural networks. The performances of the networks are analyzed
to assess the most discriminating set of echo features for classification of seafloor sediments. The results of the overall
average performances reveal that backscatter strength and time spread are the two most important echo features at 33 kHz,
whereas backscatter strength has higher discriminating characteristics at 210 kHz for seafloor sediment classification. In
addition, a set of four echo features consisting of backscatter strength, time-spread, statistical skewness, and Hausdroff
dimension gives the highest success at both the acoustic frequencies. 相似文献
5.
6.
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. 相似文献
7.
Michalopoulou Z.-H. Alexandrou D. de Moustier C. 《Oceanic Engineering, IEEE Journal of》1995,20(3):190-197
In this paper neural and statistical classifiers are applied to the problem of seafloor classification. The feature vectors used consist of acoustic backscatter as a function of angle of incidence. Simulated seafloor backscatter is obtained by employing the Helmholtz-Kirchhoff approximation and the statistical properties of bottom reverberation. These synthetic data are used initially to train multilayer perceptrons and then to test them for their ability to discriminate among signal returns produced by seafloors with different roughness parameters. The same data are also processed with optimum Bayesian classifiers. A comparison of the results indicates a suboptimum performance for the perceptrons. The same procedures are applied to real data collected by the Sea Beam bathymetric system over two Central North Pacific seamounts. In this case, the perceptron performance is similar to that of the statistical classifier, which is no longer optimum, since no prior knowledge of the probability distribution parameters is available. In addition, Self Organizing Maps are applied to both synthetic and real data and are shown to result in a successful separation of the output space into distinct regions corresponding to different seafloor classes 相似文献
8.
海底表层底质分布信息的准确获取在构建海洋基础地理数据库中发挥着重要作用。目前,多波束是实现大范围海底底质分类的有效手段之一,基于多波束测深和反向散射强度数据所派生的声学特征被广泛应用于底质分类建模。然而,随着特征维度的增加,特征空间中存在的无关和冗余特征严重影响底质分类精度。为了定量评估声学特征对底质类别的表征能力,并消除无效特征对分类结果的干扰,本文提出了基于多维度声学特征优选的海底底质分类方法。首先,结合实际底质样本的物理属性对多维特征进行排序和优选,排除冗余和无关特征。其次,分别应用支持向量机、随机森林和深度信念网络构建海底底质监督分类模型。通过利用爱尔兰海南部多波束调查数据和实地取样信息进行试验,结果表明提出方法对海底底质的总体分类精度和Kappa系数分别最高达到了86.20%和0.834,相较于主成分分析和熵指标特征选择方法有明显提高,突出了该方法在海底底质探测及制图的应用潜力。 相似文献
9.
联合光谱和纹理特征的滨海湿地高光谱深度学习分类—以黄河三角洲湿地为例 总被引：2，自引：0，他引：2
本文基于CHRIS高光谱遥感影像，发展了一种结合地物光谱特征和多纹理空间特征信息，采用双全链接的8层深度卷积神经网络分类算法对滨海湿地高光谱影像进行遥感地物分类，并在黄河口滨海湿地进行了应用。结果表明：1）基于测试样本数据，联合光谱特征和K-L变换的纹理特征信息，采用DCNN模型方法展现了高的分类精度，精度高达99%；2）利用光谱特征和全纹理特征的精度比仅使用光谱特征和光谱特征联合K-L变换后纹理特征的分类精度低。利用K-L变换后的光谱特征和纹理特征的DCNN分类精度达到99.38%，相比于使用全纹理特征信息的精度提高了4.15%；3）基于验证图像，发展的DCNN分类方法精度优于其他算法，DCNN方法总体分类精度为84.64%，Kappa系数为0.80；4）相比于浅层分类方法，本文发展的DCNN模型分类算法保证了所有地物类型的分类精度更加均衡，保持了主要地物类型的分类精度几乎不变，同时提高了滩涂和农田的精度。基于DCNN模型，潮滩和农田的分类精度分别达到79.26%和56.72%。比其它浅层分类方法提高了2.51%和10.6%。 相似文献
10.
Seabed Classification Using BP Neural Network Based on GA 总被引：4，自引：0，他引：4
INTRODUCTIONUnderwaterremotesensingtools,suchasmulti beam ,sidescansonar,sub bottom pro file ,video ,etc .,arenormalmeanstoexploreseabed .Foreaseofnotation ,sidescansonarim ageisusedtodemonstrateseabedimage .Sidescansonarisakindofhigh resolutionimagingandcancontinuouslymonitorthechangesofseafloor.Inordertorelievetechniciansfromhardhandwork ,theautomaticclassificationbycomputerisneeded .Differentfromthespatialremotesensingimage ,underwatersonarimageistheformernon multi spectralimage .Theo… 相似文献
11.
针对海底地形复杂程度分类问题,在考虑传统水深均值的基础上引入坡度和起伏度两个地形因子作为表征海底地形复杂程度的分类指标并进行量化,对水深数据空间分辨率进行统一,建立包含18种典型海底特征的海底地形复杂度分类库,利用BP神经网络对建立的分类库进行训练学习。为验证该方法的有效性和适用性,选取地形复杂度不同的4块实验区分别采用统计学方法和BP神经网络算法进行海底地形复杂度进行分类,对比发现该方法可以实现海区海底平坦、一般、复杂三种地形的自动识别与分类,并保留实验区海底地形复杂度细节信息。 相似文献
12.
A methodology for acoustic seafloor classification 总被引：3，自引：0，他引：3
A seafloor classification methodology, based on a parameterization of the reverberation probability density function in conjunction with neural network classifiers, is evaluated through computer simulations. Different seafloor provides are represented by a number of scatterer distributions exhibiting various degrees of departure from the nominal Poisson distribution. Using a computer simulation program, these distributions were insonified at different spatial scales by varying the transmitted pulse length. The statistical signature obtained consists of reverberation kurtosis estimates as a function of pulse length. Two neural network classifiers are presented with the task of discriminating among the various scatterer distributions based on obtained acoustic signatures. The results indicate that this approach offers considerable promise for practical, realizable solutions to the problem of remote seafloor classification 相似文献
13.
基于海洋一号C（HY-1C）卫星海岸带成像仪（CZI）遥感影像,提出了一种基于最优特征集的支持向量机海冰分类方法。分别提取CZI影像的光谱特征和纹理特征,采用基于距离可分性的判据进行特征选择,得到最优特征集,以最优特征集作为支持向量机分类器输入,分别对3期辽东湾海域CZI影像开展海冰分类实验和结果分析。结果表明:本文方法得到的海冰分类结果精度优于仅利用光谱特征或纹理特征的海冰分类精度;基于本文方法的3期影像的海冰分类精度均较高,2020年12月19日、2021年1月10日与2021年1月16日的海冰分类总体精度分别为93.67%、91.75%、84.89%,均在80%以上;利用海冰分类结果图估算海冰面积,发现3期辽东湾海冰面积依次增大,最大约为11 998.98 km2。 相似文献
14.
针对水产养殖中的精准投喂问题,以大西洋鲑(Salmo salar)为研究对象,提出一种基于鱼体运动特征和图像纹理特征的鱼群摄食活动强度量化方法,进行鱼类摄食行为识别研究。利用自适应背景差分及光流法得到运动鱼体的速度、转角,并通过信息熵统计速度和转角的分布,之后通过灰度共生矩阵提取能量、熵、对比度、相关性和逆差距5个图像纹理特征值。最后,结合鱼体运动特征及图像纹理特征,对鱼类摄食行为进行识别和检测。实验结果表明,该方法的识别准确率达到了94.17%,相较于单一特征检测本研究的检测精度更高。 相似文献
15.
纹理特征提取及辅助遥感影像分类技术研究 总被引：6，自引：0，他引：6
研究了利用灰度共生矩阵提取纹理特征的方法，并对利用纹理特征影像辅助光谱特征分类的方法进行了研究。实验结果表明，纹理特征辅助光谱特征分类能够提高遥感影像分类的准确性和精度。 相似文献
16.
De Yao Azimi-Sadjadi M.R. Jamshidi A.A. Dobeck G.J. 《Oceanic Engineering, IEEE Journal of》2002,27(3):619-627
The problem of classifying underwater targets is addressed in this paper. The proposed classification system consists of several subsystems including preprocessing, subband decomposition using wavelet packets, linear predictive coding, feature selection and neural network classifier. A multi-aspect fusion system is introduced to further improve the classification accuracy. The classification performance of the overall system is demonstrated and benchmarked on two different acoustic backscattered data sets with 40- and 80-kHz bandwidth. A comprehensive study is then carried out to compare the classification performance using these data sets in terms of the receiver operating curves, error locations, and generalization and robustness on a large set of noisy data. Additionally, the importance of different frequency bands for the wideband 80-kHz data is also investigated. For the wideband data, a subband fusion mechanism is introduced which offers very promising results. 相似文献
17.
溢油已是当前海洋生态环境破坏的主要因素之一,因此对海洋溢油的检测分析是当前海洋环境保护的一个重要课题。传统的溢油提取仅仅是单独依靠光学影像的光谱信息或者合成孔径雷达(SAR)影像的后向散射系数信息进行提取,这会造成很多同谱异物或者粗糙度相近似的地物错分,因此除了利用传统的影像信息以外,还需结合影像的纹理信息,从而提高溢油提取的精度,减少错分地物的数量。选用2006年渤海地区的三景同轨SAR影像作为数据基础,应用基于灰度共生矩阵的方法对其进行纹理分析。该方法可以很好地对图像区域和表面进行感知并能够从像元的灰度相关性上对纹理特征进行详细描述,因此适合于SAR影像的海洋溢油检测。在纹理分析的过程中有很多的参数需要选择,参数选择的好坏将直接影响最终提取结果的精度。通过对纹理分析过程中的参数进行讨论、实验、选择与验证,最终确定了基于灰度共生矩阵纹理分析中各参数的值,并选择了局部平稳、非相似性、对比度、变化量4个特征量作为溢油提取的纹理特征统计量。将纹理特征与SAR自身的后向散射系数相结合,通过神经网络分类法对其进行分类,并计算出分类精度为80.65%,分类效果良好。由此说明了将影像的传统信息与纹理信息相结合进行溢油提取是一种可行而有效的方法,同时也为后续的海洋溢油检测工作奠定了一定的基础。 相似文献
18.
19.
针对目前海底底质分类要素单一造成的底质分类类别不够细致和底质信息获取效率低等问题,提出一种顾及声图纹理特征的海底底质分类方法,综合利用海底底质来源、地理等属性以及声图纹理特征等分类要素,进一步细化海底底质类别,解决了海底底质分类信息混淆或表达不充分等问题。实例数据分析表明,该分类方法克服了传统方法单一考虑底质粒度信息的缺点,可以真实反映海底底质的时空变化特性以及一定范围内的表面起伏特征,并且所包含的海底底质分类信息量更全面,从而可以为用户提供直接形象的海底底质信息。 相似文献
20.
考虑海底沉积介质为双相介质,为了更好地模拟实际海底底质的不均匀性,将随机介质理论引入双相介质理论。首先,通过基于随机-双相介质理论的高阶有限差分数值技术模拟计算海底底质分别为泥质砂、泥、泥质砾时的地震反射波信号。然后利用小波变换分别求取不同底质的一次反射波的包络作为其特征向量,最后利用基于粒子群智能算法优化的支持向量机神经网络对这些反射波信号进行分类识别。为了进一步考察所用方法的抗噪能力,对正演得到的海底底质反射波信号分别加入10%、30%、50%的高斯白噪音之后再进行分类,支持向量机仍然取得了较好的分类预测效果。基于上述正演模拟及分类识别方法的论证,提出了一套行之有效的微机软件模拟海底沉积物分类识别的一般化流程,这将有利于开展海底沉积物反射特征的进一步研究。 相似文献