基于RBF网络模型的SAR溢油图像识别方法

周慧; 陈澎

doi:10.16411/j.cnki.issn1006-7736.2018.02.017

大连海事大学学报 >

2018 , Vol. 44 >Issue 2: 113 - 117

DOI: https://doi.org/10.16411/j.cnki.issn1006-7736.2018.02.017

船舶与海洋工程

基于RBF网络模型的SAR溢油图像识别方法

周慧 ,
陈澎

展开

(1.大连东软信息学院软件工程系，辽宁大连 116023;2.大连海事大学航海学院，辽宁大连 116026)

周慧(1983-)，女，硕士，副教授，研究方向：遥感与地理信息科学.

收稿日期: 2017-07-20

修回日期: 2017-11-13

网络出版日期: 2017-11-14

基金资助

国家自然科学基金资助项目(51609032);辽宁省教育厅科技项目（L2015057）.

收起

SAR oil spills image recognition based on RBF network model

ZHOU Hui ,
CHEN Peng

Expand

(1.Department of Software Engineering,Dalian Neusoft Information University, Dalian 116023, China;2.Navigation College,Dalian Maritime University, Dalian 116026,China)

Received date: 2017-07-20

Revised date: 2017-11-13

Online published: 2017-11-14

Fold

摘要

利用径向基函数（radial basis function, RBF）神经网络模型区分油膜和类油膜，旨在为溢油事故决策支持提供重要前提.首先，对合成孔径雷达（SAR）图像进行特征提取，获得有效的特征向量，并将特征向量作为输入层参数，建立激励函数；其次，利用SAR图像样本训练RBF神经网络模型，将输出值与实际值之间的误差作为约束条件调整权重因子、径向基中心和宽度，根据输出层的线性激活函数值判断溢油情况.实验结果表明，RBF模型在识别油膜与类油膜图像方面准确率超过90%. 通过比较RBF和BP神经网络在SAR溢油图像分类上的准确率，也证明了RBF的有效性.

关键词： 溢油; 油膜/类油膜; 合成孔径雷达(SAR); 图像识别; 特征向量; 径向基函数网络

本文引用格式

周慧 , 陈澎 . 基于RBF网络模型的SAR溢油图像识别方法[J]. 大连海事大学学报, 2018 , 44(2) : 113 -117 . DOI: 10.16411/j.cnki.issn1006-7736.2018.02.017

Abstract

Radial basis function (RBF) neural network model was used to distinguish oil slicks or look-alikes oil slicks to provide an important prerequisite for oil spill decision. Firstly, the efficient eigenvectors was extracted from synthetic aperture radar (SAR) images to acquire eigenvectors, and eigenvectors were used as input layer parameters to establish excitation function. Secondly，the RBF neural network model was trained by SAR image samples, and the error between output value and actual value was used as a constraint condition to adjust the weight factor, radial basis center and width, and estimate the oil spill situation according to the linear activation function value of output layer. Experimental results show that the accuracy rate of RBF model is more than 90% in recognition of “oil slicks” and “look-alikes oil slicks” image. The results also reveal that the outputs from the RBF neural network are more accurate compared to those from the BP neural network.

Key words： oil spill; oil slicks/look-alikes oil slicks; synthetic aperture radar(SAR); image recognition; eigenvector; radial basis function network

参考文献

[1]MU Lin, ZOU He-ping, WU Shuang-quan, SONG Jun, LI Huan, XU Ling-ling, ZHAO Ru-xiang.Numerical model research on the ocean oil spill[J].Marine Science Bulletin, 2011, 30(4):473-480
[2]Cheng Y, Li X, Xu Q, et al.SAR observation and model tracking of an oil spill event in coastal waters[J].Marine pollution bulletin, 2011, 62(2):350-363
[3] 陈澎.机载激光荧光海上溢油信息提取与反演研究[D]. 大连海事大学, 2012.
[4]Ramakrishnan R, Majumdar T J.Classification of oil spill in the Krishna-Godavari offshore using ERS-1 SAR images with a fuzzy logic approach[J].Indian Journal of Geo-Marine Sciences, 2013, 42(4):431-436
[5] 谢明红.基于径向基函数网络的图像三维恢复技术在雕刻加工中的应用[J]. 光学精密工程, 2007, 15(1).[J].光学精密工程, 2007, 15(1):-
[6] SU T, MENG J, ZHANG X.Segmentation Algorithm for Oil Spill SAR Images Based on Hierarchical Agglomerative Clustering[J]. Advances in Marine Science, 2013, 2: 013.[J].Advances in Marine Science, 2013, 2:13-
[7]Ma L, Chen G.Method for Oil Spill Monitoring By Polarimetric SAR[J].Environmental Forensics, 2013, 14(4):294-300
[8] Choi Y, Takahashi K, Abe A, et al.Simulation of Deepwater Horizon Oil Spill using Atmosphere-Ocean General Circulation Model[J]. Reports of Research Institute for Applied Mechanics, Kyushu University. 2012, 143( 23- 27).
[9]Safdari-Vaighani A, Heryudono A, Larsson E.A radial basis function partition of unity collocation method for convection–diffusion equations arising in financial applications[J].Journal of Scientific Computing, 2015, 64(2):341-367
[10] Bagheri M, Mirbagheri S A, Ehteshami M, et al.Modeling of a sequencing batch reactor treating municipal wastewater using multi-layer perceptron and radial basis function artificial neural networks[J]. Process Safety and Environmental Protection, 2015, 93: 111-123.
[11] Tapia D I, Fraile J A, Rodríguez S, et al.Integrating hardware agents into an enhanced multi-agent architecture for Ambient Intelligence systems l[J]. Information Sciences, 2013, 222: 47-65.
[12]Andrade F, Lyra A, Pellegrini J, et al.Introducing Resources in Oil Spill Trajectory Modeling-Contingency Analysis[C]//2013 SPE Latin-America Conference in Health, Safety, Environment & Social Responsibility Conference in the Oil and Gas Industry. 2013.
[13]Krohling R A, Campanharo V C.Fuzzy TOPSIS for group decision making: A case study for accidents with oil spill in the sea[J].Expert Systems with Applications, 2011, 38(4):4190-4197
[14]Le He?naff M, Kourafalou V H, Paris C B, et al.Surface evolution of the deepwater horizon oil spill patch: combined effects of circulation and wind-induced drift[J].Environmental science & technology, 2012, 46(13):7267-7273
[15]Mezi? I, Loire S, Fonoberov V A, et al.A new mixing diagnostic and Gulf oil spill movement[J].Science, 2010, 330(6003):486-489
[16]Bi H, Si H.Dynamic risk assessment of oil spill scenario for Three Gorges Reservoir in China based on numerical simulation[J].Safety Science, 2012, 50(4):1112-1118
[17]Niu X, Ban Y.Multi-temporal RADARSAT-2 polarimetric SAR data for urban land-cover classification using an object-based support vector machine and a rule-based approach[J].International Journal of Remote Sensing, 2013, 34(1):1-26

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献