基于MODIS谱纹信息融合的海洋溢油检测方法
收稿日期: 2013-08-28
修回日期: 2013-09-22
网络出版日期: 2014-03-10
基金资助
国家科技支撑课题小卫星智能观测荒漠化和海岸带监测应用示范(2011BAH23B04);国家海洋公益性行业科研专项经费资助项目(201005011)。
MODIS Based Spectral and Texture Integration Oil Spill Detection Method
Received date: 2013-08-28
Revised date: 2013-09-22
Online published: 2014-03-10
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。
苏伟光, 苏奋振, 杜云艳 . 基于MODIS谱纹信息融合的海洋溢油检测方法[J]. 地球信息科学学报, 2014 , 16(2) : 299 -306 . DOI: 10.3724/SP.J.1047.2014.00299
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 sensitive 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 China 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 eigenvalues of oil slick and sea by gray level co-occurrence matrix in the MODIS band 2. Then three texture eigenvalues 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 feature of MODIS data can effectively extract the oil slick in the Bohai Sea, and has a strong ability to suppress noise.
[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(4):1916-1924.
[2] David Mera, José M. Cotos, José Varela-Pet, et al. Adaptive thresholding algorithm based on SAR images and wind data to segment oil spills along the northwest coast of the Iberian Peninsula[J]. Marine Pollution Bulletin, 2012,64(10):2090-2096.
[3] 苏伟光.海洋卫星遥感溢油监测技术与应用研究[D].长沙:中南大学,2008.
[4] Liu A K, Wu S Y, Tseng W Y, et al. Wavelet analysis of SAR images for coastal monitoring [J]. Canadian Journal of Remote Sensing, 2000(26):494-500.
[5] Kanaa T F N, Tonye E, Mereier G, et al. Detection of oil Slick Signatures in SAR Images by Fusion of Hysteresis Thresholding Responses[J]. International Geoscience and Remote Sensing Symposium, 2003(4):2750-2752.
[6] Topouzelis K, Karathanassi V and Pavlakis P, et al. Detection and discrimination between oilspills and look-alike phenomena through neural networks[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2007(62):264-270.
[7] Brekke Camilla, Solberg Anne H. S. Oil spill detection by remote sensing[J]. Remote Sensing of Environment, 2005(95):1-13.
[8] CROSS A.M. Monitoring marine oil pollution using AVHRR data: observations off the coast of Kuwait and Saudi Arabia during January 1991[J]. International Journal of Remote Sensing, 1992,13(4):781-788.
[9] Tseng W Y. Oil spill detection from NOAA-AVHRR imagery[J]. International Journal of Remote Sensing, 1995,16(18):3481-3482.
[10] Hu, C., F. E. Müller-Karger, C. Taylor, et al. MODIS detects oil spills in Lake Maracaibo, Venezuela[J]. Eos Trans, 2003,84(33):313-319.
[11] Cococcioni Marco, Corucci Linda, Masini Andrea, et al. SVME: an ensemble of support vector machines for detecting oil spills from full resolution MODIS images[J].Ocean Dynamics, 2012(2):449-467.
[12] SrivastavaH., SinghT.P. Assessment and Development of algorithms to detection of Oil Spills using MODIS Data[J]. J. Indian Soc. Remote Sens.,2010(38):161-167.
[13] Kudryavtsev Vladimir, Myasoedov Alexander, Chapron Bertrand, Johannessend Johnny A and Collard Fabrice . Joint sun-glitter and radar imagery of surface slicks[J]. Remote Sensing of Environment, 2012,120(SI):123-132.
[14] 张永宁,丁倩,高超,等.油膜波谱特性分析与遥感监测溢油[J].海洋环境科学,2000,19(3):5-10.
[15] 赵冬至,从丕福.海面溢油的可见光波段地物光谱特征研究[J].遥感技术与应用,2000,15(3):160-164.
[16] Ma Long, Li Ying, Liu Yu. Oil spill monitoring based on its spectral characteristics[J]. Environmental Forensics, 2009, 10(4):317-323.
[17] 陆应诚,陈君颖,包颖,等.基于HJ-1星CCD 数据的溢油遥感特性分析与信息提取[J].中国科学·信息科学, 2011,41(增刊):193-201.
[18] 苏伟光,苏奋振,周成虎,等.海面溢油光学卫星遥感监测能力分析[J].地球信息科学学报,2012,14(5):523-530.
[19] 邹亚荣,林明森,马腾波,等.基于GLCM 的SAR 溢油纹理特征分析[J].海洋通报,2009,39(6):1269-1274.
[20] Oscar Garcia-Pineda, Beate Zimmer, Matt Howard, et al. Using SAR images to delineate ocean oil slicks with a texture-classifying neural network algorithm (TCNNA)[J]. Can. J. Remote Sensing, 2009,35(5):1-11.
[21] 石立坚,赵朝方,刘朋.基于纹理分析和人工神经网络的SAR图像中海面溢油识别方法[J].中国海洋大学学报,2009,39(6):1269-1274.
[22] Poonsm M Bhogle, Sonalipatil. Oil Spill Detection in SAR Images Using Texture Entropy Algorithm and Mahalanobis Classifier[J]. International Journal of Engineering Science and Technology, 2012,4(12):4823-4826.
[23] Zhang Fengli, Shao Yun, Tian Wei, et al. Oil Spill Identification based on Textural Information of SAR Image[C]. Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International, 2008,1308-1311.
[24] 李颖,兰国新,刘丙新.辅以纹理特征的HJ-CCD 海上溢油信息提取——以PL19-3溢油为例[J].中国环境科学,2012,32(8):1514-1520.
[25] 李金莲,刘晓玫,李恒鹏.SPOT5影像纹理特征提取与土地利用信息识别方法[J].遥感学报, 2006,10(6):926-93.
[26] Cortes C, Vapnik V.. Support-Vector Networks[J]. Machine Learning, 1995,20(3):273-297.
[27] 苏伟光.海洋卫星遥感溢油监测技术与应用研究[D].长沙:中南大学,2008.
/
〈 | 〉 |