A new oil spill detection algorithm based on Dempster-Shafer evidence theory -- Journal of Oceanology and Limnology,2022,40(2):456-469

	Cite this paper:
	Tianlong ZHANG, Jie GUO, Chenqi XU, Xi ZHANG, Chuanyuan WANG, Baoquan LI. A new oil spill detection algorithm based on Dempster-Shafer evidence theory[J]. Journal of Oceanology and Limnology, 2022, 40(2): 456-469

A new oil spill detection algorithm based on Dempster-Shafer evidence theory

Tianlong ZHANG^1,4, Jie GUO^1,2,3, Chenqi XU^1,4, Xi ZHANG⁵, Chuanyuan WANG^1,2,3, Baoquan LI^1,2,3

1 Yantai Institute of Coastal Zone Research(YIC), Chinese Academy of Sciences(CAS), CAS Key Laboratory of Coastal Environmental Processes and Ecological Remediation, Yantai 264003, China;
2 Shandong Key Laboratory of Coastal Environmental Processes, Yantai Institute of Coastal Zone Research, Chinese Academy of Sciences, Yantai 264003, China;
3 Center for Ocean Mega-Science, Chinese Academy of Sciences, Qingdao 266071, China;
4 University of the Chinese Academy of Sciences, Beijing 100049, China;
5 Frist Institute of Oceanography(FIO), Ministry of Natural Resources(MNR), Qingdao 266061, China

Abstract:

Features of oil spills and look-alikes in polarimetric synthetic aperture radar (SAR) images always play an important role in oil spill detection. Many oil spill detection algorithms have been implemented based on these features. Although environmental factors such as wind speed are important to distinguish oil spills and look-alikes, some oil spill detection algorithms do not consider the environmental factors. To distinguish oil spills and look-alikes more accurately based on environmental factors and image features, a new oil spill detection algorithm based on Dempster-Shafer evidence theory was proposed. The process of oil spill detection taking account of environmental factors was modeled using the subjective Bayesian model. The Faster-region convolutional neural networks (RCNN) model was used for oil spill detection based on the convolution features. The detection results of the two models were fused at decision level using Dempster-Shafer evidence theory. The establishment and test of the proposed algorithm were completed based on our oil spill and look-alike sample database that contains 1 798 image samples and environmental information records related to the image samples. The analysis and evaluation of the proposed algorithm shows a good ability to detect oil spills at a higher detection rate, with an identification rate greater than 75% and a false alarm rate lower than 19% from experiments. A total of 12 oil spill SAR images were collected for the validation and evaluation of the proposed algorithm. The evaluation result shows that the proposed algorithm has a good performance on detecting oil spills with an overall detection rate greater than 70%.

Key words: synthetic aperture radar (SAR) data|oil spill detection|subjective Bayesian|Faster-region convolutional neural networks (RCNN)|Dempster-Shafer evidence theory

Received: 2020-07-04 Revised:

Tools

PDF (5143 KB) Free

Print this page

Add to favorites

Email this article to others

Authors

Articles by Tianlong ZHANG

Articles by Jie GUO

Articles by Chenqi XU

Articles by Xi ZHANG

Articles by Chuanyuan WANG

Articles by Baoquan LI

References:
Bern T I, Wahl T, Anderssen T, Olsen R.1993.Oil spill detection using satellite based SAR:experience from a field experiment.Photogrammetric Engineering and Remote Sensing, 59(3):423-428.
Bodla N, Singh B, Chellappa R, Davis L S.2017.Soft-NMS-improving object detection with one line of code.In:Proceedings of the IEEE International Conference on Computer Vision (ICCV).Venice, Italy.p.5562-5570.
China Cartographic Publishing House.2015.The World Port Traffic Atlas (2015 Edition).China Cartographic Publishing House.Beijing, China. (in Chinese)
Commander Department of the Navy (Navigation Guarantee Department).2005a.Guide to Chinese Port:Bohai Sea and Yellow Sea.Chinese Navigation Publications Press, Tianjin, China. (in Chinese)
Commander Department of the Navy (Navigation Guarantee Department).2005b.Guide to Chinese Ports:South China Sea.Chinese Navigation Publications Press, Tianjin, China. (in Chinese)
Dempster A P.1967.Upper and lower probabilities induced by a multivalued mapping.The Annals of Mathematical Statistics, 38(2):325-339, https://doi.org/10.1214/aoms/1177698950.
Duda R O, Hart P E, Nilsson N J.1976.Subjective Bayesian methods for rule-based inference systems.In:Proceedings of National Computer Conference and Exposition.ACM, New York.p.1075-1082.
Gullaya W.2012.Petroleum pollution in the Gulf of Thailand:a historical review.Coastal Marine Science, 35(1):234-245.
Guo H, Wei G, An J B.2018.Dark spot detection in SAR images of oil spill using Segnet.Applied Sciences, 8(12):2670, https://doi.org/10.3390/app8122670.
Guo J, Liu X, Xie Q.2013.Characteristics of the Bohai Sea oil spill and its impact on the Bohai Sea ecosystem.Chinese Science Bulletin, 58(19):2276-2281, https://doi.org/10.1007/s11434-012-5355-0.
Han C, Gao G Y, Zhang Y.2019.Real-time small traffic sign detection with revised Faster-RCNN.Multimedia Tools and Applications, 78(10):13263-13278, https://doi.org/10.1007/s11042-018-6428-0.
Huang H S, Deng J Z, Lan Y B, Yang A Q, Deng X L, Zhang L.2018.A fully convolutional network for weed mapping of unmanned aerial vehicle (UAV) imagery.PLoS One, 13(4):e0196302, https://doi.org/10.1371/journal.pone.0196302.
Karathanassi V, Topouzelis K, Pavlakis P, Rokos D.2006.An object-oriented methodology to detect oil spills.International Journal of Remote Sensing, 27(23):5235-5251, https://doi.org/10.1080/01431160600693575.
Krestenitis M, Orfanidis G, Ioannidis K, Avgerinakis K, Vrochidis S, Kompatsiaris L.2019.Oil spill identification from satellite images using deep neural networks.Remote Sensing, 11(15):1762, https://doi.org/10.3390/rs11151762.
LabelImg.2018.Available online:https://github.com/tzutalin/labelImg (accessed on 18 April 2018).
Lee J S, Grunes M R, de Grandi G.1999.Polarimetric SAR speckle filtering and its implication for classification.IEEE Transactions on Geoscience and Remote Sensing, 37(5):2363-2373, https://doi.org/10.1109/36.789635.
Leifer I, Lehr W J, Simecek-Beatty D, Bradley E, Clark R, Dennison P, Hu Y X, Matheson S, Jones C E, Holt B, Reif M, Roberts D A, Svejkovsky J, Swayze G, Wozencraft J.2012.State of the art satellite and airborne marine oil spill remote sensing:application to the BP Deepwater Horizon oil spill.Remote Sensing of Environment, 124:185-209, https://doi.org/10.1016/j.rse.2012.03.024.
Li M M, Stein A, Bijker W, Zhan Q M.2016.Urban land use extraction from Very High Resolution remote sensing imagery using a Bayesian network.ISPRS Journal of Photogrammetry and Remote Sensing, 122:192-205, https://doi.org/10.1016/j.isprsjprs.2016.10.007.
Li X F, Li C Y, Yang Z Z, Pichel W.2013.SAR imaging of ocean surface oil seep trajectories induced by near inertial oscillation.Remote Sensing of Environment, 130:182-187, https://doi.org/10.1016/j.rse.2012.11.019.
Manana M, Tu C L, Owolawi P A.2018.Preprocessed Faster RCNN for Vehicle Detection.2018 International Conference on Intelligent and Innovative Computing Applications (ICONIC).p.1-4, https://doi.org/10.1109/ICONIC.2018.8601243.
Ren S Q, He K M, Girshick R, Sun J.2017.Faster R-CNN:towards real-time object detection with region proposal networks.IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(6):1137-1149, https://doi.org/10.1109/TPAMI.2016.2577031.
Shafer G.1976.A Mathematical Theory of Evidence.Princeton University Press, NJ, USA.314p.
Simonyan K, Zisserman A.2015.Very deep convolutional networks for large-scale image recognition.In:Proceedings of the International Conference on Learning Representations (ICLR).San Diego, CA, USA.
Solberg A H S, Brekke C, Husoy P O.2007.Oil spill detection in Radarsat and Envisat SAR images.IEEE Transactions on Geoscience and Remote Sensing, 45(3):746-755, https://doi.org/10.1109/TGRS.2006.887019.
Solberg A H S, Dokken S T, Solberg R.2003.Automatic detection of oil spills in ENVISAT, RADARSAT and ERS SAR images.In:Proceedings of the IEEE IGARSS.Toulouse, France.p.2747-2749.
Tong S W, Liu X G, Chen Q H, Zhang Z J, Xie G Q.2019.Multi-feature based ocean oil spill detection for polarimetric SAR data using random forest and the selfsimilarity parameter.Remote Sensing, 11(4):451, https://doi.org/10.3390/rs11040451.
Vaezzadeh V, Zakaria M P, Bong C W.2017.Aliphatic hydrocarbons and triterpane biomarkers in mangrove oyster (Crassostrea belcheri) from the west coast of Peninsular Malaysia.Marine Pollution Bulletin, 124(1):33-42, https://doi.org/10.1016/j.marpolbul.2017.07.008.
Yang F B, Wei H, Feng P P.2020.A hierarchical DempsterShafer evidence combination framework for urban area land cover classification.Measurement, 151:105916, https://doi.org/10.1016/j.measurement.2018.09.058.
Zeng H, Yang B, Wang X Q, Liu J W, Fu D M.2019.RGB-D object recognition using multi-modal deep neural network and DS evidence theory.Sensors, 19(3):529, https://doi.org/10.3390/s19030529.
Zhang B, Perrie W, Li X, Pichel W G.2011.Mapping sea surface oil slicks using RADARSAT-2 quad-polarization SAR image.Geophysical Research Letters, 38(10):L10602, https://doi.org/10.1029/2011GL047013.
Zhao J, Temimi M, Al Azhar M, Ghedira H.2015.Satellitebased tracking of oil pollution in the Arabian Gulf and the Sea of Oman.Canadian Journal of Remote Sensing, 41(2):113-125, https://doi.org/10.1080/07038992.2015.1 042543.