Oil spill segmentation in SAR images using convolutional neural networks. A comparative analysis with clustering and logistic regression algorithms

Abstract Synthetic aperture radar (SAR) images are a valuable source of information for the detection of marine oil spills. For their effective analysis, it is important to have segmentation algorithms that can delimit possible oil spill areas. This article addresses the application of clustering, logistic regression and convolutional neural network algorithms for the detection of oil spills in Envisat and Sentinel-1 satellite images. Large oil spills do not occur frequently so that the identification of a pixel as oil is relatively uncommon. Metrics based on Precision–Recall curves have been employed because they are useful for problems with an imbalance in the number of samples from the classes. Although logistic regression and clustering algorithms can be considered useful for oil spill segmentation, the combination of convolutional techniques and neural networks achieves the best results with low computing time. A convolutional neural network has been integrated into a decision support system in order to facilitate decision-making and data analysis of possible oil spill events.

[1]  Junyu Dong,et al.  An Overview on Data Representation Learning: From Traditional Feature Learning to Recent Deep Learning , 2016, ArXiv.

[2]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[3]  Dao-Qiang Zhang,et al.  A novel kernelized fuzzy C-means algorithm with application in medical image segmentation , 2004, Artif. Intell. Medicine.

[4]  Oscar Garcia-Pineda,et al.  Adaptive thresholding algorithm based on SAR images and wind data to segment oil spills along the northwest coast of the Iberian Peninsula. , 2012, Marine pollution bulletin.

[5]  Scott A. King,et al.  Metaheuristic Search Algorithms for Oil Spill Detection Using SAR Images , 2018, 2018 8th International Conference on Computer Science and Information Technology (CSIT).

[6]  Curt H. Davis,et al.  Fusion of Deep Convolutional Neural Networks for Land Cover Classification of High-Resolution Imagery , 2017, IEEE Geoscience and Remote Sensing Letters.

[7]  Carlos Dafonte,et al.  A comparison between functional networks and artificial neural networks for the prediction of fishing catches , 2004, Neural Computing & Applications.

[8]  Martin J. Wainwright,et al.  Noisy matrix decomposition via convex relaxation: Optimal rates in high dimensions , 2011, ICML.

[9]  Fabio Del Frate,et al.  Fully Automatic Dark-Spot Detection From SAR Imagery With the Combination of Nonadaptive Weibull Multiplicative Model and Pulse-Coupled Neural Networks , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Nelson F. F. Ebecken,et al.  Intelligent hybrid system for dark spot detection using SAR data , 2017, Expert Syst. Appl..

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

[12]  Olga Lavrova,et al.  Satellite Survey of Inner Seas: Oil Pollution in the Black and Caspian Seas , 2016, Remote. Sens..

[13]  Frank Klawonn,et al.  What Is Fuzzy about Fuzzy Clustering? Understanding and Improving the Concept of the Fuzzifier , 2003, IDA.

[14]  K. Topouzelis,et al.  Oil Spill Detection Using Space-Borne Sentinel-1 SAR Imagery , 2017 .

[15]  Patrick M. Pilarski,et al.  First steps towards an intelligent laser welding architecture using deep neural networks and reinforcement learning , 2014 .

[16]  Suman Singha,et al.  Satellite Oil Spill Detection Using Artificial Neural Networks , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[17]  Amparo Alonso-Betanzos,et al.  On the use of feature selection to improve the detection of sea oil spills in SAR images , 2017, Comput. Geosci..

[18]  Ali A. Ghosn,et al.  SAR images thresholding for oil spill detection , 2013, 2013 Saudi International Electronics, Communications and Photonics Conference.

[19]  Charu C. Aggarwal,et al.  Neural Networks and Deep Learning , 2018, Springer International Publishing.

[20]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

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

[22]  Andrew J Davies,et al.  Bayesian inference-based environmental decision support systems for oil spill response strategy selection. , 2015, Marine pollution bulletin.

[23]  Yang Zhao,et al.  An improved Otsu method for oil spill detection from SAR images , 2017 .

[24]  José Hernández-Orallo,et al.  An experimental comparison of performance measures for classification , 2009, Pattern Recognit. Lett..

[25]  Roy Fielding,et al.  Architectural Styles and the Design of Network-based Software Architectures"; Doctoral dissertation , 2000 .

[26]  Erfu Yang,et al.  Energy Minimization With One Dot Fuzzy Initialization for Marine Oil Spill Segmentation , 2019, IEEE Journal of Oceanic Engineering.

[27]  T. Collier,et al.  Environmental effects of the Deepwater Horizon oil spill: A review. , 2016, Marine pollution bulletin.

[28]  Carlos Dafonte,et al.  Integration of remote sensing techniques and connectionist models for decision support in fishing catches , 2007, Environ. Model. Softw..

[29]  A. Ribotti,et al.  The Mediterranean Decision Support System for Marine Safety dedicated to oil slicks predictions , 2016 .

[30]  Jianchao Fan,et al.  Oil Spill Monitoring Based on SAR Remote Sensing Imagery , 2015 .

[31]  Bianca Zadrozny,et al.  Obtaining calibrated probability estimates from decision trees and naive Bayesian classifiers , 2001, ICML.

[32]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[33]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[34]  Peng Zhao,et al.  Feature extraction and classification of ocean oil spill based on SAR image , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[35]  Shivaprakash Muruganandham.  Semantic Segmentation of Satellite Images using Deep Learning , 2016 .

[36]  Carlos Dafonte,et al.  Cloud Integrated Web Platform for Marine Monitoring Using GIS and Remote Sensing: Application to Oil Spill Detection through SAR Images , 2012, UCAmI.

[37]  Lena Chang,et al.  A region-based GLRT detection of oil spills in SAR images , 2008, Pattern Recognit. Lett..

[38]  J. Senthil Murugan,et al.  AETC: Segmentation and classification of the oil spills from SAR imagery , 2017 .

[39]  Waldo Kleynhans,et al.  An Image-Segmentation-Based Framework to Detect Oil Slicks From Moving Vessels in the Southern African Oceans Using SAR Imagery , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[40]  T. M. Lillesand,et al.  Remote Sensing and Image Interpretation , 1980 .

[41]  François Chollet,et al.  Deep Learning with Python , 2017 .

[42]  Mark Hess,et al.  Detection of Oil near Shorelines during the Deepwater Horizon Oil Spill Using Synthetic Aperture Radar (SAR) , 2017, Remote. Sens..

[43]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[44]  Carl E. Brown,et al.  A Review of Oil Spill Remote Sensing , 2017, Sensors.

[45]  Geoffrey E. Hinton,et al.  Machine Learning for Aerial Image Labeling , 2013 .