| 274 | 10 | 183 |
| 下载次数 | 被引频次 | 阅读次数 |
在合成孔径雷达(SAR)图像中区分溢油和类油现象是溢油SAR探测的关键任务。实现该任务一般可分为3步:首先是提取油膜和类油膜的特征;然后筛选出有助于油膜和类油膜分类的关键特征;最后构造有效的分类器进行模式识别以便做出准确的判别。本文基于2011年蓬莱19-3油田溢油事故期间的15景SAR图像提取了138个油膜和类油膜样本的几何特征、背景特征、散射特征和纹理特征,将Fisher判别率和序列前向选择方法相结合,筛选出背景后向散射系数标准差、逆差距、能量和后向散射系数的均值四个关键特征组成的特征子集。在此基础上,为提高分类器的精度,将决策树模型CART算法与Bagging技术相结合,通过随机抽样给出多个维数相同大小的训练数据集从而建立多个决策树模型,以投票的方式对油膜和类油膜样本进行分类;最后,文中采用了五折和十折交叉验证方法对油膜和类油膜的分类结果进行评估,研究显示基于Bagging的决策树方法的油膜和类油膜分类的平均精度在85%以上,且将文中所用基于Bagging的CART决策树分类算法与经典CART决策树分类算法及神经网络分类算法相比较,发现本文所用方法的分类精度较高,从而表明了该方法在溢油SAR探测方面的可行性。
Abstract：Discriminating oil spills from lookalike phenomena is a crucial procedure in oil spill detection.To achieve this purpose,three-step approach is taken in general:firstly,features of oil spills and lookalikes are extracted;then,key features which are beneficial to the oil spill classification are screened out;finally,effective classifier is built and pattern recognition method is used to conduct classification.In this paper,16 kinds of features which include geometric features,surrounding features,backscattering features and textural features of 138 oil spills and lookalikes are extracted from 15 SAR images.The images were acquired during Penglai 19-3Platform oil spill accident in 2011.The 16 features are sorted from big to small based on the FDR value of the single feature.We find that the standard deviation of backscattering coefficient of the backgrounds has larger FDR value.Therefore,it can be selected as the first feature.Then,the forward selection method of sequential search method are used to determinate the optimal feature subset for oil spill detection.We find that the standard deviation of backscattering coefficient of the backgrounds,inverse difference moment,energy and the mean value of backscattering coefficient can be selected as the optimal feature subset in this work.CART(Classification And Regression Tree)is a kind of binary decision tree which is helpful to improve efficiency of generating tree.However,the disadvantage of the decision tree classifier is that the variance of classification results is quite high.So the decision tree classifier is an unstable classifier.While for bagging algorithm,the only real training set in practice are divided into different training sets through resampling methods.And that is benefit for improving the unstable classifier performance.The bagging method based on decision-making tree combines massive calculation of single classifiers which is helpful to improve the accuracy of oil spill detection.In this paper,we combine CART with bagging algorithm to classify the oil spills from look-alike.Multiple training data sets with the same size are generated by random selection,and then several decision tree models can be established.So the oil spills and lookalikes can be classified by voting.The experiment results show that,the classification accuracy tends to be stable through 100 iterations.In order to get effective classification results,five-fold and ten-fold cross validation are employed to evaluate the classification results,and the results show that the average classification accuracy of oil spills and lookalikes is above 85%.At last,we compared the CART that based on bagging algorithm with conventional CART and BP Neural network classification algorithm for oil spill discrimination.We find that the classification accuracy of our method is higher than the other two methods,which indicates that the effectiveness of our method in oil spill detection on SAR image.
[1]Solberg A H S,Storvik G,Solberg R,et al.Automatic detection of oil spills in ERS SAR images[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(4):1916-1924.
[2]Solberg A H S,Brekke C,Husy P.Oil spill detection in Radarsat and Envisat SAR images[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(3):746-755.
[3]Fiscella B,Giancaspro A,Nirchio F,et al.Oil spill detection using marine SAR images[J].International Journal of Remote Sensing,2000,21(18):3561-3566.
[4]Li F,Shen C M.A two-stage method for oil slick segmentation[J].International Journal of Remote Sensing,2010,31(15):4217-4226.
[5]Akar S,Süzen M L,Kaymakci N.Detection and object-based classification of offshore oil slicks using ENVISAT-ASAR images[J].Environ Monit Assess,2011,183:409-423.
[6]周慧,陈澎.利用Mahalanobis距离的SAR图像溢油识别[J].计算机工程与应用,2011,47(18):195-203.Zhou H,Chen P.Oil spills identification in SAR image using Mahalanobis distance[J].Computer Engineering and Applications,2011,47(18):195-203.
[7]施永春.基于Adaboost的SAR图像溢油检测[J].电脑知识与技术,2011,7(29):7252-7254.Shi Y C.Using Adaboost to detect oil spill in SAR images[J].Computer Knowledge and Technology,2011,7(29):7252-7254.
[8]Topouzelis K,Psyllos A.Oil spill feature selection and classification using decision tree forest on SAR image data[J].ISPRS Journal of Photogrammetry and Remote Sensing,2012,68:135-143.
[9]Zhang Y Z,Lin H,Liu Q,et al.Oil-spill monitoring in the coastal waters of Hong Kong and Vicinity[J].Marine Geodesy,2012,35:93-106.
[10]邹亚荣,邹斌,梁超,等.多元指标的海上溢油信息提取[J].地球信息科学学报,2012,14(2):265-269.Zhou Y R,Zou B,Liang C,et al.Multiple index information extraction of marine oil spills[J].Journal of Geo-Information Science,2012,14(2):265-269.
[11]Xu L L,Li J,Brenning A.A comparative study of different classification techniques for marine oil spill identification using RADARSAT-1imagery[J].Remote Sensing of Environment,2014,141:14-23.
[12]Evtushenko N V,Ivanov A Y.Oil seeps in the southeastern Black Sea studied using satellite synthetic aperture radar images[J].Atmospheric and Oceanic Physics,2013,49(9):913-918.
[13]Garcia-Pineda O,MacDonald I R,Li X F,et al.Oil spill mapping and measurement in the Gulf of Mexico with textural classifier neural network algorithm(TCNNA)[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2013,6(6):2517-2525.
[14]Singha S,Bellerby T J,Trieschmann O.Satellite oil spill detection using artificial neural networks[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2013,6(6):2355-2363.
[15]Bandiera F,Masciullo A,Ricci G.A bayesian approach to oil slicks edge detection based on SAR data[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(5):2901-2909.
[16]Ivanov A Y,Kucheiko A A.Large discharges from ships in the Black Sea studied by synthetic aperture radar with the support of automated identification systems[J].International Journal of Remote Sensing,2014,35(14):5513-5526.
[17]Singha S,Vespe M,Trieschmann O.Automatic synthetic aperture radar based oil spill detection and performance estimation via a semi-automatic operational service benchmark[J].Marine Pollution Bulletin,2013,73(1):199-209.
[18]Marghany M.Automatic detection of oil spills in the Gulf of Mexico from RADARSAT-2 SAR satellite data[J].Environ Earth Sci,2015,74:5935-5947.
[19]Fisher R A.The use of multiple measurements in taxonomic problems[J].Annals of Eugenics,1936,7(2):179-188.
[20]Sergios Theodoridis,Konstantions Koutroumbas.Pattern Recognition,Fourth Edition[M].李晶皎,王爱侠,王骄,等译.模式识别:第四版.北京:电子工业出版社,2010.
[21]Breiman L,Friedman J,Olshen R,et al.Classification and Regression Trees[M].Pacific Grove:wikipedia,1984.
[22]Srinivas M,Patnaik L M,Adaptive probabilities of crossover and mutation in genetic algorithms[J].IEEE Transactions on Systems Man and Cybernetics,1994,24(4):656-667
[23]Iyer S K,Saxenab B,Improved genetic algorithm for the permutation flow shop scheduling problem[J].Computers and Operations Research,2004,31(4):593-606.
[24]陈云,戴锦芳,李俊杰,基于影像多种特征的CART决策树分类方法及其应用[J].地理与地理信息科学,2008,24(2):33-36.Chen Y,Dai J F,Li J J,CART-based decision tree classifier Using multi-feature of image and its application[J].Geography and Geo-Information Science,2008,24(2):33-36.
[25]张娜,张庆河,基于CART决策树方法的MODIS数据海冰反演[J].海洋通报,2016,33(3):321-327.Zhang N,Zhang Q H.Retrievalof the sea ice area from MODIS data by CART decision tree method[J].Marine Science Bulletin,2016,33(3):321-327.
[26]Breiman L.Bagging predictors[J].Machine Learning,1996,24:123-140.
[27]秦姣龙,王蔚.Bagging组合的不平衡数据分类方法[J].Computer Engineering,2011,37(14):178-182.Qin J L,Wang W.Imbalanced data classification method for bagging combination[J].Computer Engineering,2011,37(14):178-182.
基本信息:
DOI：10.16441/j.cnki.hdxb.20160196
中图分类号:TN957.52
引用信息:
[1]张彦敏,徐卓,旭锋.海上溢油合成孔径雷达探测研究[J],2017,47(02):106-115.DOI:10.16441/j.cnki.hdxb.20160196.
基金信息:
海洋公益性科研专项(201505002);; 国家自然科学基金项目(61501520)资助~~