Sea SAR Images Analysis to Detect Oil Slicks in Algerian Coasts

详细信息    查看全文

• 作者：Bahia Lounis ; Aichouche Belhadj-Aissa
• 关键词：Oil slicks detection ; SAR image analysis ; Histogram partition ; Contextual information ; Thresholding
• 刊名：Journal of Mathematical Modelling and Algorithms in Operations Research
• 出版年：2014
• 出版时间：December 2014
• 年：2014
• 卷：13
• 期：4
• 页码：371-386
• 全文大小：2,616 KB
• 参考文献：European Space Agency (ESA): Oil Pollution Monitoring in ERS and its Applications: Marine, vol. 1, BR-128. ESA Publications Division, The Netherlands (1998)
  Ferraro, G., Bernardini, A., David, M., Meyer-Roux, S., Muellenhoff, O., Perkovic, M., Tarchi, D., Topouzelis, K.: Towards an operational use of space imagery for oil pollution monitoring in the Mediterranean Basin: a demonstration in the Adriatic Sea. Mar. Pollut. Bull. 54, 403-22 (2007)CrossRef
  Ardhuin, F.G., Mercier, G., Collard, F., Garello, R.: Operational oil slick characterization by SAR imagery and synergistic data. IEEE J. Ocean. Eng. 30(3), 487-95 (2005)CrossRef
  Topouzelis, K., Bernardini, A., Ferraro, G., Meyer- Roux, S., Tarchi, D.: Satellite mapping of oil spills in the Mediterranean Sea. Fresen. Environ. Bull. 15, 10091-00914 (2006)
  Solberg, A., Brekke, C., Husoy, P.O.: Oil spill detection in Radarsat and Envisat SAR images. IEEE Trans. Geosci. Remote Sens. 45, 746-55 (2007)CrossRef
  Nirchio, F., Sorgente, M., Giancaspro, A., Biamino, W., Parisato, E., Ravera, R., Trivero, P.: Automatic detection of oil spills from SAR images. Int. J. Remote Sens. 26(6), 1157-174 (2005)CrossRef
  Topouzelis, K., Karathanassi, V., Pavlakis, P., Rokos, D.: Detection and discrimination between oil spills and look-alike phenomena through neural networks. ISPRS J. Photogramm. Remote Sens. 62, 264-70 (2007)CrossRef
  Solberg, A., Brekke, C.: Oil spill detection in Northern European Waters: approaches and algorithms. In: Barale, V., Gade, M. (eds.) Remote Sensing of the European Seas, pp. 359-70. Springer, Dordrecht (2008)
  Brekke, C., Solberg, H.A.: Oil spill detection by satellite remote sensing. Remote Sens. Environ. 95, 1-3 (2005)CrossRef
  Barni, M., Betti, M., Mecoeei, A.: A fuzzy approach to oil spill detection on SAR images. Int. Electron. Electr. Eng. 71(1), 157-59 (1995)
  Gasull, A., Fábregas, X., Jiménez, J., Marqués, F., Moreno, V., Herrero, M.A.: Oil spills detection in Sar images using mathematical morphology. In: Proceedings of the 11th European Signal Processing Conference, EUSIPCO-002, vol. I, pp. 25-8. Toulouse (2002)
  Kanaa, T.F., Tonyé, E., Mercier, G., Onana, V.: Détection des nappes d’hydrocarbures dans les images RSO par morphologie mathématique. Rev. Télédétect. 4(3), 215-29 (2004)
  Marghany, M., Craknell, A., Hashim, M.: Modification of fractal algorithm for oil spill detection from RadarSat-1 SAR data. Int. J. Appl. Earth Obs. Geoinform. 11, 96-02 (2009)CrossRef
  Marghany, M., Craknell, A., Hashim, M.: Comparison between radarsat-1 SAR different data modes for oil spill detection by fractal box counting algorithm. Int. J. Digit. Earth 2(3), 237-56 (2009)CrossRef
  Kanaa, T.F.N., Mercier, G., Tonye, E.: Sea Surface Slicks Characterization in SAR Images, pp. 21-3. Oceans 05 europe (2005)
  Derroche, S., Mercier, G.: Unsupervised multiscale oil slick segmentation from SAR images using a vector HMC model. Pattern Recogn. 40(3), 1135-147 (2007)CrossRef
  Mercier, G., Ardhuin, F.G.: Oil Slick Detection by SAR Imagery using Support Vector Machines, pp. 21-23. Oceans 05 Europe (2005)
  Lounis, B., Mercier, G., Belhadj-Aissa, A.: Combination of statistical similarity measure and derivative morphological profile approach for oil slick detection in SAR images. J. Math. Model. Algorithms JMMA 11(4), 409-32 (2012). doi:10.-007/?s10852-012-9206-4.-/span> ISSN: 1570-1166, Springer Netherlands publisherCrossRef MathSciNet
  Marghany, M., Van Genderen, J.L.: Texture algorithms for oil pollution detection and tidal current effects on oil spill spreading. Asian J. Geoinform. 13, 33-3 (2001)
  Topouzelis, K., Karathanassai, V., Pavlakis, P., Rokos, D.: Oil spill detection: SAR multi-scale segmentation and object features evaluation. In: Proceedings Remote Sensing Ocean and Sea Ice, September 23-7, pp. 77-7. Crete (2002)
  Topouzelis, K., Karathanassi, V., Pavlakis, P., Rokos, D.: Dark formation detection using neural networks. Int. J. Remote Sens. 29, 4705-720 (2008)CrossRef
  Kanaa, T., Tonyé, E., Mercier, G., Onana, V.P., Garello, R., Rudant, J.-P., Mvogo, J.: Detection of oil slick signatures in SAR images by fusion of hysteresis thresholding responses. In: Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (2003)
  Pavlakis, P., Tarchi, D., Sieber, A.: On the Monitoring of Illicit Vessel Discharges, a Reconnaissance Study in the Mediterranean Sea. European Commission Report EUR 19906 EN (2001)
  Lounis, B., Belhadj-Aissa, A.: Thresholding algorithms for oil slick detection in Radar SAR images. In: Proceedings of the 13th International Conference on Computational and Mathematical Methods in Science and Engineering, CMMSE 2013, 24-7 June, pp. 1667-674. ISBN: 978-84-616-2723-3 (2013)
  Cocquerez, J.P., Philip, S.: Analyse d’Image: Filtrage et Segmentation. Edition MASSON (1995)
  Gonzalez, R., Woods, R.: Digital Image Processing, 2nd edn. Prentice
• 作者单位：Bahia Lounis (1)
  Aichouche Belhadj-Aissa (1)
  
  1. Université des Sciences & Technologie Houari Boumediene (USTHB), BP 32 El Alia, Bab Ezzouar - Fac. d’Electronique & Informatique / LTIR, 16111, Alger, Algérie
  
• 刊物类别：Operations Research, Management Science; Optimization; Algorithms; Mathematical Modeling and Industr
• 刊物主题：Operations Research, Management Science; Optimization; Algorithms; Mathematical Modeling and Industrial Mathematics; Data Mining and Knowledge Discovery;
• 出版者：Springer Netherlands
• ISSN：2214-2495

文摘

In this paper, we investigate the performance of partition features derived from histogram analysis to isolate dark spots which are candidates to be oil spills in SAR images. The first partition is carried out to obtain preliminary clusters of the pixels on the basis of their grey level intensities and threshold values deduced from the histogram. The detection process is achieved by a contextual partition where the conflict pixels are attributed to their region involving local information about pre-etiqueted pixels neighbouring the pixel in question. For pixel’s assignment, we propose two decision criteria: the first based on Local Probability Maximization (LPM) while the second uses a Chi-squared test (χ 2). We considered variable context in order to characterize the sea texture and dark spots. This method is tested on ERS-2 SAR Precision Image (PRI) covering Algerian coasts and gave promising results which are useful for the identification process. Keywords Oil slicks detection SAR image analysis Histogram partition Contextual information Thresholding