Offshore Oil Slicks Detection From SAR Images Through The Mask-RCNN Deep Learning Model

This paper introduces a method for offshore oil slick detection. At present, Synthetic Aperture Radar (SAR) is an image acquisition technology useful for oil slick detection in all weather conditions. It is used to carry out the detection, with notable limitations under certain conditions (surfaces, weather conditions). Manual SAR images analysis is expensive and, given the increasing amount of data collected from available sensors, automation becomes mandatory. To achieve this objective, instance object detection relying on deep neural networks is interesting to adapt to the data variability. Relying on such an approach, this article explores the capabilities of generalizing the detection of slicks on large datasets using the Mask-RCNN model. A detailed performance analysis is established in two complementary directions: (i) the impact of the SAR image characteristics(sensor, geographical areas, lookalike presence), (ii) the impact of the neural network architecture, transferred capabilities and training procedures. The main findings of this analysis show that Mask-RCNN features promising performance for pollution detection.

[1]  Ross B. Girshick,et al.  Mask R-CNN , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Diogo Almeida,et al.  Resnet in Resnet: Generalizing Residual Architectures , 2016, ArXiv.

[3]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

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

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

[6]  Yoshua Bengio,et al.  The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[7]  A. De Maio,et al.  On CFAR detection of oil slicks on the ocean surface by a multifrequency and/or multipolarization SAR , 2001, Proceedings of the 2001 IEEE Radar Conference (Cat. No.01CH37200).

[8]  Luis Perez,et al.  The Effectiveness of Data Augmentation in Image Classification using Deep Learning , 2017, ArXiv.

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

[10]  Razvan Pascanu,et al.  Deep Learners Benefit More from Out-of-Distribution Examples , 2011, AISTATS.

[11]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[12]  G. O'Brien,et al.  Evaluation of hydrocarbon seepage in the Great Australian Bight , 2002 .

[13]  Frédéric Jurie,et al.  Recent Advances in Object Detection in the Age of Deep Convolutional Neural Networks , 2018, ArXiv.

[14]  Jubai An,et al.  Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNN , 2017, Sensors.

[15]  Anne H. Schistad Solberg,et al.  Incorporation of prior knowledge in automatic classification of oil spills in ERS SAR images , 1997, IGARSS'97. 1997 IEEE International Geoscience and Remote Sensing Symposium Proceedings. Remote Sensing - A Scientific Vision for Sustainable Development.

[16]  R. Fergus,et al.  OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks , 2013, ICLR.

[17]  Peerapon Vateekul,et al.  Semantic Segmentation on Remotely Sensed Images Using an Enhanced Global Convolutional Network with Channel Attention and Domain Specific Transfer Learning , 2018, Remote. Sens..

[18]  Vishal M. Patel,et al.  SAR Image Despeckling Using a Convolutional Neural Network , 2017, IEEE Signal Processing Letters.

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

[20]  Quoc V. Le,et al.  Adding Gradient Noise Improves Learning for Very Deep Networks , 2015, ArXiv.

[21]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[22]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Matti Pietikäinen,et al.  Deep Learning for Generic Object Detection: A Survey , 2018, International Journal of Computer Vision.

[24]  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.

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

[26]  Chris Yakopcic,et al.  A State-of-the-Art Survey on Deep Learning Theory and Architectures , 2019, Electronics.

[27]  Benjamin Holt,et al.  SAR Imagery for Detecting Sea Surface Slicks: Performance Assessment of Polarization-Dependent Parameters , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[28]  E. Tonyé,et al.  MULTISCALE SEGMENTATION OF OIL SLICK IN SAR IMAGES BASED ON MORPHOLOGICAL PYRAMID , 2005 .

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

[30]  Ying Li,et al.  Semi-Automatic Oil Spill Detection on X-Band Marine Radar Images Using Texture Analysis, Machine Learning, and Adaptive Thresholding , 2019, Remote. Sens..

[31]  Maode Ma,et al.  Intelligent Image Recognition System for Marine Fouling Using Softmax Transfer Learning and Deep Convolutional Neural Networks , 2017, Complex..

[32]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Benjamin Holt,et al.  Oil spill detection by imaging radars: Challenges and pitfalls , 2017, 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[34]  V. Zatyagalova,et al.  APPLICATION OF ENVISAT SAR IMAGERY FOR MAPPING AND ESTIMATION OF NATURAL OIL SEEPS IN THE SOUTH CASPIAN SEA , 2007 .

[35]  Bingliang Hu,et al.  Attention Mask R-CNN for Ship Detection and Segmentation From Remote Sensing Images , 2020, IEEE Access.

[36]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[37]  Guangmin Sun,et al.  Application of Deep Networks to Oil Spill Detection Using Polarimetric Synthetic Aperture Radar Images , 2017 .