Object-oriented approach to oil spill detection using ENVISAT ASAR images

Abstract The growing importance of oil spill detection as part of a rapid response system to oil pollution requires the ongoing development of algorithms. The aim of this study was to create a methodology for improving manual classification at the scale of entire water bodies, focusing on its repeatability. This paper took an object-oriented approach to radar image analysis and put particular emphasis on adaptation to the specificity of seas like the Baltic. Pre-processing using optimised filters enhanced the capability of a multilevel hierarchical segmentation, in order to detect spills of different sizes, forms and homogeneity, which occur as a result of shipping activities. Confirmed spills detected in ENVISAT/ASAR images were used to create a decision-tree procedure that classifies every distinct dark object visible in SAR images into one out of four categories, which reflect growing probability of the oil spill presence: look-alikes, dubious spots, blurred spots and potential oil spills. Our objective was to properly mark known spills on ASAR scenes and to reduce the number of false-positives by eliminating (classifying as background or look-alike) as many objects as possible from the vast initial number of objects appearing on full-scale images. A number of aspects were taken into account in the classification process. The method’s performance was tested on a group of 26 oil spills recorded by HELCOM: 96.15% of them were successfully identified. The final target group was narrowed down to about 4% of dark objects extracted from ASAR images. Although a specialist is still needed to supervise the whole process of oil spill detection, this method gives an initial view, substantial for further evaluation of the scenes and risk estimation. It may significantly accelerate the pace of manual image analysis and enhance the objectivity of assessments, which are key aspects in operational monitoring systems.

[1]  Fahad Alawadi.  New pattern recognition methods for identifying oil spills from satellite remote sensing data , 2009, Remote Sensing.

[2]  Xiaofeng Li,et al.  Detection of the Hebei Spirit oil spill on SAR imagery and its temporal evolution in a coastal region of the Yellow Sea , 2015 .

[3]  M. Fingas,et al.  Review of oil spill remote sensing. , 2014, Marine pollution bulletin.

[4]  J. Karvonen,et al.  On C-Band SAR Based Oil Slick Detection in the Baltic Sea , 2006 .

[5]  Rune Solberg,et al.  Automatic detection of oil spills in ERS SAR images , 1999, IEEE Trans. Geosci. Remote. Sens..

[6]  Linlin Xu,et al.  A comparative study of different classification techniques for marine oil spill identification using RADARSAT-1 imagery , 2014 .

[7]  Cathleen E. Jones,et al.  State of the art satellite and airborne marine oil spill remote sensing: Application to the BP Deepwater Horizon oil spill , 2012 .

[8]  Kostas Topouzelis,et al.  Oil spill detection: SAR multiscale segmentation and object features evaluation , 2003, SPIE Remote Sensing.

[9]  Antony K. Liu,et al.  Towards an automated ocean feature detection, extraction and classification scheme for SAR imagery , 2003 .

[10]  Camilla Brekke,et al.  Classifiers and Confidence Estimation for Oil Spill Detection in ENVISAT ASAR Images , 2008, IEEE Geoscience and Remote Sensing Letters.

[11]  A. Solberg,et al.  Oil spill detection by satellite remote sensing , 2005 .

[12]  Thomas Blaschke,et al.  Object based image analysis for remote sensing , 2010 .

[13]  Konstantinos Topouzelis,et al.  Oil spill feature selection and classification using decision tree forest on SAR image data , 2012 .

[14]  M. Fingas.  Handbook of Oil Spill Science and Technology: Fingas/Handbook of Oil Spill Science and Technology , 2014 .

[15]  Zakarya Mihoub,et al.  Monitoring and identification of marine oil spills using advanced synthetic aperture radar images , 2014 .

[16]  H. Espedal.  Satellite SAR oil spill detection using wind history information , 1999 .

[17]  Fabio Del Frate,et al.  Neural networks for oil spill detection using ERS-SAR data , 2000, IEEE Trans. Geosci. Remote. Sens..

[18]  Ronald Pelot,et al.  Visualization of spatial patterns and temporal trends for aerial surveillance of illegal oil discharges in western Canadian marine waters. , 2008, Marine pollution bulletin.

[19]  Robert M. Haralick,et al.  Decision Making in Context , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  K. Topouzelis,et al.  Detection and discrimination between oil spills and look-alike phenomena through neural networks , 2007 .

[21]  José Manuel Cotos,et al.  Automatic decision support system based on SAR data for oil spill detection , 2014, Comput. Geosci..

[22]  Pavlakis Petros,et al.  A New Object-oriented Methodology to Detect Oil Spills using ENVISAT Images , 2007 .

[23]  Maged Marghany,et al.  RADARSAT automatic algorithms for detecting coastal oil spill pollution , 2001 .

[24]  P. Pavlakis,et al.  An object‐oriented methodology to detect oil spills , 2006 .

[25]  S. Issa.  Monitoring Oil Spills Offshore the United Arab Emirates Using Multi Satellite Data , 2010 .

[26]  Arno Schäpe,et al.  Multiresolution Segmentation : an optimization approach for high quality multi-scale image segmentation , 2000 .

[27]  P. Snoeij,et al.  Sentinel-1 - the radar mission for GMES operational land and sea services , 2007 .

[28]  Marina Mityagina,et al.  Operational satellite monitoring of oil spill pollution in the Southeastern Baltic Sea: 1.5 Years experience , 2006, 2006 IEEE US/EU Baltic International Symposium.

[29]  Demetris Stathakis,et al.  Investigation of genetic algorithms contribution to feature selection for oil spill detection , 2009 .

[30]  Sertac Akar,et al.  Detection and object-based classification of offshore oil slicks using ENVISAT-ASAR images , 2011, Environmental monitoring and assessment.

[31]  Konstantinos N. Topouzelis,et al.  Oil Spill Detection by SAR Images: Dark Formation Detection, Feature Extraction and Classification Algorithms , 2008, Sensors.

[32]  Maurizio Migliaccio,et al.  On the degree of polarization for SAR sea oil slick observation , 2013 .

[33]  Dario Tarchi,et al.  Detection, tracking and remote sensing: satellites and image processing (spaceborne oil spill detection) , 2015 .