Oil Slicks Detection From Polarimetric Data Using Stochastic Distances Between Complex Wishart Distributions

Genovez, Patrícia Carneiro; Freitas, Corina da Costa; Sant’Anna, Sidnei J. S.; Bentz, Cristina Maria; Lorenzzetti, João A.

doi:10.1109/jstars.2016.2628325

Cited by 10 publications

(10 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most satellite SAR instruments have little or no margin between the oil slick return and their noise floor [ 20 , 26 , 27 ], which seriously contaminates the returns and makes the instruments insensitive to oil characteristics. Observations indicate that the slick thickness is related to the damping of the capillary and gravity-capillary waves, with thicker layers causing more damping [ 16 , 28 ], i.e., less return power and darker images. Using imagery collected during the Deepwater Horizon oil spill in 2010, researchers have made advances in determining the volumetric oil fraction [ 16 ] and estimates of layer thickness [ 29 , 30 ] from SAR.…”

Section: Instrument and Methods: Airborne Sar For Oil Spill Responmentioning

confidence: 99%

Experimental L-Band Airborne SAR for Oil Spill Response at Sea and in Coastal Waters

Jones

Holt

2018

Sensors

View full text Add to dashboard Cite

Satellite synthetic aperture radar (SAR) is frequently used during oil spill response efforts to identify oil slick extent, but suffers from the major disadvantages of potential long latency between when a spill occurs and when a satellite can image the site and an inability to continuously track the spill as it develops. We show using data acquired with the Uninhabited Aerial Vehicle SAR (UAVSAR) instrument how a low noise, high resolution, L-band SAR could be used for oil spill response, with specific examples of tracking slick extent, position and weathering; determining zones of relatively thicker or more emulsified oil within a slick; and identifying oil slicks in coastal areas where look-alikes such as calm waters or biogenic slicks can confound the identification of mineral oil spills. From these key points, the essential features of an airborne SAR system for operational oil spill response are described, and further research needed to determine SAR’s capabilities and limitations in quantifying slick thickness is discussed.

show abstract

Section: Instrument and Methods: Airborne Sar For Oil Spill Responmentioning

confidence: 99%

Experimental L-Band Airborne SAR for Oil Spill Response at Sea and in Coastal Waters

Jones

Holt

2018

Sensors

View full text Add to dashboard Cite

show abstract

“…To quantitatively describe the similarity of the PDFs for each precipitation scenario, we employ the Hellinger distance statistic, which is used for various applications related to classification techniques [36][37][38][39][40]. This metric H, which is closely related to the Bhattacharyya distance [41,42], is dependent on two bivariate normal distributions, P ∼ N (µ 1 , Σ 1 ) and Q ∼ N (µ 2 , Σ 2 ), where µ and Σ are the mean and covariance matrix of the distributions, respectively.…”

Section: Hellinger Distancesmentioning

confidence: 99%

Vegetation Characterization through the Use of Precipitation-Affected SAR Signals

et al. 2018

View full text Add to dashboard Cite

Current space-based SAR offers unique opportunities to classify vegetation types and to monitor vegetation growth due to its frequent acquisitions and its sensitivity to vegetation geometry. However, SAR signals also experience frequent temporal fluctuations caused by precipitation events, complicating the mapping and monitoring of vegetation. In this paper, we show that the influence of a priori known precipitation events on the signals can be used advantageously for the classification of vegetation conditions. For this, we exploit the change in Sentinel-1 backscatter response between consecutive acquisitions under varying wetness conditions, which we show is dependent on the state of vegetation. The performance further improves when a priori information on the soil type is taken into account.

show abstract

“…In future research, the addition of a super-pixel segmentation method, the region-based CNN [65] or conditional random fields (CRF) [66] should be considered. Also, the multi-scale spatial information of the oil spill edge regions should be thoroughly investigated in order to optimize the classification results [71].…”

Section: ) Experimental Results Of Datasetmentioning

confidence: 99%

“…These problems increase the difficulty of oil spill detection at sea [35]. It would be important to comment that another way to classify this type of data is using region-based algorithms, which classify the images using regions, not pixels, as processing unities [48], [68], [71]. These studies all prove that the spatial information can suppress speckle noises and improve the accuracy of classification.…”

Section: Introductionmentioning

confidence: 98%

A Novel Marine Oil Spillage Identification Scheme Based on Convolution Neural Network Feature Extraction From Fully Polarimetric SAR Imagery

et al. 2020

View full text Add to dashboard Cite

Marine oil spill pollution has caused serious impacts on marine ecological environments, ecological resources and marine economy. Synthetic Aperture Radar (SAR), especially polarmetric SAR (PolSAR), has been proven to be a powerful and efficient tool for marine oil spill detection. In general, traditional oil spill detection methods mainly rely on artificially-extracted polarization characteristics, and the detection accuracy is limited by the quality of feature extraction. Recently proposed Convolutional neural network (CNN) is capable of mining spatial feature from large data set automatically. Inspired by these, in this paper we proposed a novel oil spill identification method based on multi-layer deep feature extraction by CNN. Firstly, PolSAR data are converted into a 9-channel data block to feed the CNN. Then, a 5-layer CNN architecture is built to extract two high-level features from the original data automatically. The features are fused after dimension reduction via principal component analysis (PCA). Finally, support vector machine method with radial basis function kernel (RBF-SVM) is utilized for classification. Three sets of RADARSAT-2 fully polarimetric SAR data were used in this study to validate the proposed method. The obtained results reveal that the proposed method provides competitive results in overall classification accuracy and kappa coefficient. Moreover, this method can improve the accuracy of oil spill detection, reduce the false alarm rate, and effectively distinguish an oil spill from a biogenic slick. INDEX TERMS Marine oil spill, RADARSAT-2, PolSAR, deep learning, feature extraction, convolutional neural network (CNN).

show abstract

Oil Slicks Detection From Polarimetric Data Using Stochastic Distances Between Complex Wishart Distributions

Cited by 10 publications

References 40 publications

Experimental L-Band Airborne SAR for Oil Spill Response at Sea and in Coastal Waters

Experimental L-Band Airborne SAR for Oil Spill Response at Sea and in Coastal Waters

Vegetation Characterization through the Use of Precipitation-Affected SAR Signals

A Novel Marine Oil Spillage Identification Scheme Based on Convolution Neural Network Feature Extraction From Fully Polarimetric SAR Imagery

Contact Info

Product

Resources

About