Optimum Features Selection for oil Spill Detection in SAR Image

Chehresa, Saeed; Amirkhani, Abdollah; Rezai-Rad, G.; Mosavi, Mohammad Reza

doi:10.1007/s12524-016-0553-x

Cited by 19 publications

(18 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The incorporation of features with reliable discriminatory power contributes to the improvement of classification accuracy in oil spill detection. Various studies have attempted to determine the optimal combination of different features for detecting and classifying oil spills [110,145,[177][178][179][180][181]. However, the lack of systematic research on the extraction and combination of various sets of features (i.e., SAR polarimetric, textural, geometrical, and other features) and their influence on classification accuracies has generally contributed to the arbitrary selection of features as inputs to numerous classification systems [177,180].…”

Section: Feature Extractionmentioning

confidence: 99%

“…The frequency of adopting feature categories in differentiating oil spills and lookalikes from SAR images are shown in Figure 4. Hu moment invariant [189] Invariant moments used to characterize object patterns [110,113,114,132,139,180,190] Circularity Measure of an image object compactness [104,139,180,190,191] Perimeter to area ratio Ratio of the perimeter to the area (…”

Section: Feature Categoriesmentioning

confidence: 99%

See 1 more Smart Citation

Sensors, Features, and Machine Learning for Oil Spill Detection and Monitoring: A Review

et al. 2020

View full text Add to dashboard Cite

Remote sensing technologies and machine learning (ML) algorithms play an increasingly important role in accurate detection and monitoring of oil spill slicks, assisting scientists in forecasting their trajectories, developing clean-up plans, taking timely and urgent actions, and applying effective treatments to contain and alleviate adverse effects. Review and analysis of different sources of remotely sensed data and various components of ML classification systems for oil spill detection and monitoring are presented in this study. More than 100 publications in the field of oil spill remote sensing, published in the past 10 years, are reviewed in this paper. The first part of this review discusses the strengths and weaknesses of different sources of remotely sensed data used for oil spill detection. Necessary preprocessing and preparation of data for developing classification models are then highlighted. Feature extraction, feature selection, and widely used handcrafted features for oil spill detection are subsequently introduced and analyzed. The second part of this review explains the use and capabilities of different classical and developed state-of-the-art ML techniques for oil spill detection. Finally, an in-depth discussion on limitations, open challenges, considerations of oil spill classification systems using remote sensing, and state-of-the-art ML algorithms are highlighted along with conclusions and insights into future directions.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Section: Feature Categoriesmentioning

confidence: 99%

Sensors, Features, and Machine Learning for Oil Spill Detection and Monitoring: A Review

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Feature extraction is crucial to the classification of oil slicks and lookalikes. Geometrical (such as area , perimeter, and perimeter to area ratio), textural, and polarimetric features are always considered to distinguish oil slicks from lookalikes [ 1 , 17 , 42 ]. As the input of the proposed classifier, the features discussed in this paper are pixel-based features, which can be selected from feature images one by one.…”

Section: Multi-feature Discrimination Analysismentioning

confidence: 99%

Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNN

Guo

2017

Sensors

View full text Add to dashboard Cite

Oil slicks and lookalikes (e.g., plant oil and oil emulsion) all appear as dark areas in polarimetric Synthetic Aperture Radar (SAR) images and are highly heterogeneous, so it is very difficult to use a single feature that can allow classification of dark objects in polarimetric SAR images as oil slicks or lookalikes. We established multi-feature fusion to support the discrimination of oil slicks and lookalikes. In the paper, simple discrimination analysis is used to rationalize a preferred features subset. The features analyzed include entropy, alpha, and Single-bounce Eigenvalue Relative Difference (SERD) in the C-band polarimetric mode. We also propose a novel SAR image discrimination method for oil slicks and lookalikes based on Convolutional Neural Network (CNN). The regions of interest are selected as the training and testing samples for CNN on the three kinds of polarimetric feature images. The proposed method is applied to a training data set of 5400 samples, including 1800 crude oil, 1800 plant oil, and 1800 oil emulsion samples. In the end, the effectiveness of the method is demonstrated through the analysis of some experimental results. The classification accuracy obtained using 900 samples of test data is 91.33%. It is here observed that the proposed method not only can accurately identify the dark spots on SAR images but also verify the ability of the proposed algorithm to classify unstructured features.

show abstract

“…Solberg et al ( 2003) designed a classifier for oil spill detection, defined 10 characteristics, and applied Bayesian theory to discriminate oil spills from lookalikes. Chehresa et al(2016) proposed an algorithm for selecting the optimal features from SAR images to distinguish oil spills from lookalikes . Nunziata and Migliaccio successfully detected ocean oil spills and distin-guished oil spills from biological oil films using co-polarized phase differences (Migliaccio et al, 2009).…”

Section: Introductionmentioning

confidence: 99%

Experimental study of C-band microwave scattering characteristics during the emulsification process of oil spills

et al. 2020

View full text Add to dashboard Cite

In this study, oil spill experiments were performed in a water tank to determine changes in the surface scattering characteristics during the emulsification of oil spills. A C-band fully-polarimetric microwave scatterometer and a vector network analyzer were used to observe films of the following oils: crude oil with an asphalt content below 3% that is prone to emulsification (type A), fresh crude oil extracted from an oilfield (type B), and industrial crude oil that was dehydrated and purified (type C). The difference in the backscatter results between the emulsified oil film and the calm water surface under C-band microwaves and the influence of the emulsification of the oil film on the backscatter were analyzed in detail. The results demonstrate that under a low-wind and no-waves condition (the maximum wave height was below than 3 mm), the emulsification of crude oil could modulated the backscatter through changes in the surface roughness and the dielectric constant, where the surface roughness had the dominant effect. The surface backscatters of the type B oil were greater than that of the type C oil in both the emulsified and non-emulsified states. In the non-emulsified state, the average differences in the backscatter between the type B and C oils were 2.19 dB, 2.63 dB, and 2.21 dB for the polarization modes of VV, HH, and HV/VH, respectively. Smaller corresponding average differences of 0.98 dB, 1.49 dB, and 1.5 dB were found for the emulsified state with a 20% moisture constant for the oil film. The results demonstrated that the surface roughness of the different oil films could vary due to the differences in the oil compositions and the oil film properties, which in turn affect the backscatter of the oil film surface.

show abstract

Optimum Features Selection for oil Spill Detection in SAR Image

Cited by 19 publications

References 38 publications

Sensors, Features, and Machine Learning for Oil Spill Detection and Monitoring: A Review

Sensors, Features, and Machine Learning for Oil Spill Detection and Monitoring: A Review

Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNN

Experimental study of C-band microwave scattering characteristics during the emulsification process of oil spills

Contact Info

Product

Resources

About