地球信息科学学报
地毬信息科學學報
지구신식과학학보
GEO-INFORMATION SCIENCE
2014年
2期
299-306
,共8页
溢油%MODIS%光谱%纹理%SVM
溢油%MODIS%光譜%紋理%SVM
일유%MODIS%광보%문리%SVM
oil spill%MODIS%spectral%texture%SVM
鉴于仅依赖光谱特征或纹理特征的传统溢油检测算法的信息检测精度较低的问题，本文提出了一种新的光学遥感数据的谱纹海面溢油检测方法。谱是光学遥感数据的油膜敏感波段图像，纹是利用灰度共生矩阵计算获得的图像纹理特征，将这些特征相结合，引入支持向量机方法（Support Vector Machine, SVM），建立谱纹海面溢油检测模型。本文以2006年渤海溢油事故为例，利用中等分辨率成像光谱仪MODIS的光学遥感数据对溢油进行检测，MODIS的第2波段为油膜敏感波段，所以，第2波段图像即为选取的谱特征，经过对各个纹理特征的分析得到，均值、对比和相关3个特征量可作为溢油提取的纹理特征。检测结果的总体精度达91.23%。试验结果表明，将MODIS图像的光谱特征和纹理特征相结合，可有效地对渤海海洋油膜信息进行检测，并具有很强的抑制噪声能力。
鑒于僅依賴光譜特徵或紋理特徵的傳統溢油檢測算法的信息檢測精度較低的問題，本文提齣瞭一種新的光學遙感數據的譜紋海麵溢油檢測方法。譜是光學遙感數據的油膜敏感波段圖像，紋是利用灰度共生矩陣計算穫得的圖像紋理特徵，將這些特徵相結閤，引入支持嚮量機方法（Support Vector Machine, SVM），建立譜紋海麵溢油檢測模型。本文以2006年渤海溢油事故為例，利用中等分辨率成像光譜儀MODIS的光學遙感數據對溢油進行檢測，MODIS的第2波段為油膜敏感波段，所以，第2波段圖像即為選取的譜特徵，經過對各箇紋理特徵的分析得到，均值、對比和相關3箇特徵量可作為溢油提取的紋理特徵。檢測結果的總體精度達91.23%。試驗結果錶明，將MODIS圖像的光譜特徵和紋理特徵相結閤，可有效地對渤海海洋油膜信息進行檢測，併具有很彊的抑製譟聲能力。
감우부의뢰광보특정혹문리특정적전통일유검측산법적신식검측정도교저적문제，본문제출료일충신적광학요감수거적보문해면일유검측방법。보시광학요감수거적유막민감파단도상，문시이용회도공생구진계산획득적도상문리특정，장저사특정상결합，인입지지향량궤방법（Support Vector Machine, SVM），건립보문해면일유검측모형。본문이2006년발해일유사고위례，이용중등분변솔성상광보의MODIS적광학요감수거대일유진행검측，MODIS적제2파단위유막민감파단，소이，제2파단도상즉위선취적보특정，경과대각개문리특정적분석득도，균치、대비화상관3개특정량가작위일유제취적문리특정。검측결과적총체정도체91.23%。시험결과표명，장MODIS도상적광보특정화문리특정상결합，가유효지대발해해양유막신식진행검측，병구유흔강적억제조성능력。
Marine oil spill detection has become a worldwide issue. Traditional oil spill detection algorithm only depended on the spectral or texture has low detection accuracy. This paper presents a new method of the oil spill detection based on spectral and texture from optical remote sensing data. The spectral feature is oil slick sensi-tive band of the optical remote sensing data and the texture feature is got by gray level co-occurrence matrix. The model used support vector machine method to establish the spectrum and texture oriented oil spill detection method with these features. This paper used the MODIS optical remote sensing data to detect the oil spill in Chi-na Bohai Sea in 2006. The oil spill information can be shown on this band clearly because the variance of the sea water spectrum is less than the contrast of oil-water spectrum in the MODIS band 2, so we called the MODIS band 2 is the oil slick sensitive band, which we selected as the spectral feature. We obtained eight texture eigen-values of oil slick and sea by gray level co-occurrence matrix in the MODIS band 2. Then three texture eigenval-ues include mean, contrast and correlation were selected by analysis. Based on the selected sample, the detection accuracy was up to 91.32%and the Kappa coefficient is 0.7125. In contrast with spectral and texture integration Maximum Likelihood method and SVM method only use the spectral feature, the detection method we proposed is superior to these methods. The results showed that the method to combine the spectral feature and textural fea-ture of MODIS data can effectively extract the oil slick in the Bohai Sea, and has a strong ability to suppress noise.
