Exploring the Potential of Active Learning for Automatic Identification of Marine Oil Spills Using 10-Year (2004-2013) RADARSAT Data

This paper intends to find a more cost-effective way for training oil spill classification systems by introducing active learning (AL) and exploring its potential, so that satisfying classifiers could be learned with reduced number of labeled samples. The dataset used has 143 oil spills and 124 look-alikes from 198 RADARSAT images covering the east and west coasts of Canada from 2004 to 2013. Six uncertainty-based active sample selecting (ACS) methods are designed to choose the most informative samples. A method for reducing information redundancy amongst the selected samples and a method with varying sample preference are considered. Four classifiers (k-nearest neighbor (KNN), support vector machine (SVM), linear discriminant analysis (LDA) and decision tree (DT)) are coupled with ACS methods to explore the interaction and possible preference between classifiers and ACS methods. Three kinds of measures are adopted to highlight different aspect of classification performance of these AL-boosted classifiers. Overall, AL proves its strong potential with 4% to 78% reduction on training samples in different settings. The SVM classifier shows to be the best one for using in the AL frame, with perfect performance evolving curves in different kinds of measures. The exploration and exploitation criterion can further improve the performance of the AL-boosted SVM classifier but not of the other classifiers.

[1]  Stan Matwin,et al.  Machine Learning for the Detection of Oil Spills in Satellite Radar Images , 1998, Machine Learning.

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

[3]  Grégoire Mercier,et al.  Partially Supervised Oil-Slick Detection by SAR Imagery Using Kernel Expansion , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[4]  Bin Li,et al.  A survey on instance selection for active learning , 2012, Knowledge and Information Systems.

[5]  Arnt-Børre Salberg,et al.  Oil Spill Detection in Hybrid-Polarimetric SAR Images , 2014, IEEE Transactions on Geoscience and Remote Sensing.

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

[7]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

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

[9]  Di Zhang,et al.  Global plus local: A complete framework for feature extraction and recognition , 2014, Pattern Recognit..

[10]  Ja-Chen Lin,et al.  A new LDA-based face recognition system which can solve the small sample size problem , 1998, Pattern Recognit..

[11]  Dario Tarchi,et al.  Long term monitoring of oil spills in European seas , 2009 .

[12]  J. Friedman.  Greedy function approximation: A gradient boosting machine. , 2001 .

[13]  Torsten Hothorn,et al.  Bundling Classifiers by Bagging Trees , 2002, Comput. Stat. Data Anal..

[14]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[15]  Alireza Khotanzad,et al.  Invariant Image Recognition by Zernike Moments , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[16]  David A. Clausi,et al.  Active learning for identifying marine oil spills using 10-year RADARSAT data , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[17]  A. Giancaspro,et al.  Automatic detection of oil spills from SAR images , 2005 .

[18]  Hongwei Zhu,et al.  An adaptive fuzzy evidential nearest neighbor formulation for classifying remote sensing images , 2005, IEEE Transactions on Geoscience and Remote Sensing.

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

[20]  Farid Melgani,et al.  Nearest Neighbor Classification of Remote Sensing Images With the Maximal Margin Principle , 2008, IEEE Transactions on Geoscience and Remote Sensing.

[21]  Joydeep Ghosh,et al.  An Active Learning Approach to Hyperspectral Data Classification , 2008, IEEE Transactions on Geoscience and Remote Sensing.

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

[23]  Hong Sun,et al.  Active sample-selecting and manifold learning-based relevance feedback method for synthetic aperture radar image retrieval , 2011 .

[24]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[25]  Vassilia Karathanassi,et al.  Potentiality of feed-forward neural networks for classifying dark formations to oil spills and look-alikes , 2009 .

[26]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[27]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[28]  Shiyong Cui,et al.  Semantic annotation in earth observation based on active learning , 2014 .

[29]  Dario Tarchi,et al.  On the monitoring of illicit vessel discharges using spaceborne sar remote sensing - a reconnaissance study in the Mediterranean sea , 2001, Ann. des Télécommunications.

[30]  Meng Wang,et al.  Active learning in multimedia annotation and retrieval: A survey , 2011, TIST.

[31]  Umar Mohammed,et al.  Probabilistic Models for Inference about Identity , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Peijun Du,et al.  Active extreme learning machines for quad-polarimetric SAR imagery classification , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[33]  Mark Goadrich,et al.  The relationship between Precision-Recall and ROC curves , 2006, ICML.

[34]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[35]  J A Swets,et al.  Measuring the accuracy of diagnostic systems. , 1988, Science.

[36]  Domenico Velotto,et al.  Near real time monitoring of platform sourced pollution using TerraSAR-X over the North Sea. , 2014, Marine pollution bulletin.

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

[38]  Michael R. Berthold,et al.  Active learning for object classification: from exploration to exploitation , 2009, Data Mining and Knowledge Discovery.

[39]  P. Pavlakis,et al.  Dark formation detection using neural networks , 2008 .

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

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

[42]  Jungho Im,et al.  Support vector machines in remote sensing: A review , 2011 .

[43]  Lorenzo Bruzzone,et al.  Batch-Mode Active-Learning Methods for the Interactive Classification of Remote Sensing Images , 2011, IEEE Transactions on Geoscience and Remote Sensing.

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

[45]  Marin Ferecatu,et al.  Interactive Remote-Sensing Image Retrieval Using Active Relevance Feedback , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[46]  Lorenzo Bruzzone,et al.  Active and Semisupervised Learning for the Classification of Remote Sensing Images , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[47]  Michele Vespe,et al.  Automatic Synthetic Aperture Radar based oil spill detection and performance estimation via a semi-automatic operational service benchmark. , 2013, Marine pollution bulletin.

[48]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[49]  Biao Zhang,et al.  Cross‐polarization geophysical model function for C‐band radar backscattering from the ocean surface and wind speed retrieval , 2015 .

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

[51]  Anne H. Schistad Solberg,et al.  Remote Sensing of Ocean Oil-Spill Pollution , 2012, Proceedings of the IEEE.

[52]  R. Tibshirani,et al.  Penalized Discriminant Analysis , 1995 .

[53]  Xiaogang Wang,et al.  Dual-space linear discriminant analysis for face recognition , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

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

[55]  Camilla Brekke,et al.  Oil Spill Detection in Radarsat and Envisat SAR Images , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[56]  Chih-Jen Lin,et al.  Probability Estimates for Multi-class Classification by Pairwise Coupling , 2003, J. Mach. Learn. Res..

[57]  David A. Cohn,et al.  Improving generalization with active learning , 1994, Machine Learning.

[58]  Pao-Ta Yu,et al.  A Nonparametric Feature Extraction and Its Application to Nearest Neighbor Classification for Hyperspectral Image Data , 2010, IEEE Transactions on Geoscience and Remote Sensing.

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

[60]  Guillaume Deffuant,et al.  Keep the Decision Tree and Estimate the Class Probabilities Using its Decision Boundary , 2007, IJCAI.