Multi-Feature Based Ocean Oil Spill Detection for Polarimetric SAR Data Using Random Forest and the Self-Similarity Parameter

Tong, Shengwu; Liu, Xiuguo; Chen, Qihao; Zhang, Zhengjia; Xie, Guangqi

doi:10.3390/rs11040451

Cited by 54 publications

(50 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is not easy to over-fit and it has a shorter running time when training high-dimensional data. The RF algorithm has been widely used in remote sensing classification [30][31][32]. Two parameters, the number of trees and the number of variables, were set beforehand.…”

Section: Random Forest Classification Methodsmentioning

confidence: 99%

Assessment of the X- and C-Band Polarimetric SAR Data for Plastic-Mulched Farmland Classification

et al. 2019

View full text Add to dashboard Cite

We present a classification of plastic-mulched farmland (PMF) and other land cover types using full polarimetric RADARSAT-2 data and dual polarimetric (HH, VV) TerraSAR-X data, acquired from a test site in Hebei, China, where the main land covers include PMF, bare soil, winter wheat, urban areas and water. The main objectives were to evaluate the outcome of using high-resolution TerraSAR-X data for classifying PMF and other land covers and to compare classification accuracies based on different synthetic aperture radar bands and polarization parameters. Initially, different polarimetric indices were calculated, while polarimetric decomposition methods were used to obtain the polarimetric decomposition components. Using these polarimetric components as input, the random forest supervised classification algorithm was applied in the classification experiments. Our results show that in this study full-polarimetric RADARSAT-2 data produced the most accurate overall classification (94.81%), indicating that full polarization is vital to distinguishing PMF from other land cover types. Dual polarimetric data had similar levels of classification error for PMF and bare soil, yielding mapping accuracies of 53.28% and 59.48% (TerraSAR-X), and 59.56% and 57.1% (RADARSAT-2), respectively. We found that Shannon entropy made the greatest contribution to accuracy in all three experiments, suggesting that it has great potential to improve agricultural land use classifications based on remote sensing.

show abstract

Section: Random Forest Classification Methodsmentioning

confidence: 99%

Assessment of the X- and C-Band Polarimetric SAR Data for Plastic-Mulched Farmland Classification

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Support vector machine (SVM), decision tree (DT), and Random Forest (RF), the classical machine learning techniques for target extraction and classification [44,62,63,64,65], were used to further demonstrate the advantages and robustness of the proposed method. To provide the same calculation conditions, the same training samples were used as inputs.…”

Section: Resultsmentioning

confidence: 99%

“…It is not necessary to use every Pol-SAR feature in the target recognition and classification process because every feature varies in its ability to distinguish between oil slicks and seawater, and even between thick and thin slicks. The J–M distance is an index used widely to measure similarities in the field of pattern recognition and oil slick detection based on an SAR image, which is simple and has good universality [43,44,45,46,47]. The advantage of the JM distance is the fact that it is a simple and easily implemented criterion, which have a fixed range of values between 0 and 2 [45].…”

Section: Methodsmentioning

confidence: 99%

“…The exponential factor in JM distance definition gives an exponentially decreasing weight to increasing separation between the classes [48], then the JM distance will have a saturation behavior with the increase of the degree of separation due to the contribution of the exponential character, which overcomes the limitation of the transformation divergence [48,49]. The JM distance has been demonstrated to be effective, easily implemented, and good universality in polarimetric features selection for oil spill detection [44,46,47].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Marine Oil Slick Detection Based on Multi-Polarimetric Features Matching Method Using Polarimetric Synthetic Aperture Radar Data

Liu

et al. 2019

Sensors

View full text Add to dashboard Cite

Polarimetric synthetic aperture radar is an important tool in the effective detection of marine oil spills. In this study, two cases of Radarsat-2 Fine mode quad-polarimetric synthetic aperture radar datasets are exploited to detect a well-known oil seep area that collected over the Gulf of Mexico using the same research area, sensor, and time. A novel oil spill detection scheme based on a multi-polarimetric features model matching method using spectral pan-similarity measure (SPM) is proposed. A multi-polarimetric features curve is generated based on optimal polarimetric features selected using Jeffreys–Matusita distance considering its ability to discriminate between thick and thin oil slicks and seawater. The SPM is used to search for and match homogeneous unlabeled pixels and assign them to a class with the highest similarity to their spectral vector size, spectral curve shape, and spectral information content. The superiority of the SPM for oil spill detection compared to traditional spectral similarity measures is demonstrated for the first time based on accuracy assessments and computational complexity analysis by comparing with four traditional spectral similarity measures, random forest (RF), support vector machine (SVM), and decision tree (DT). Experiment results indicate that the proposed method has better oil spill detection capability, with a higher average accuracy and kappa coefficient (1.5–7.9% and 1–25% higher, respectively) than the four traditional spectral similarity measures under the same computational complexity operations. Furthermore, in most cases, the proposed method produces valuable and acceptable results that are better than the RF, SVM, and DT in terms of accuracy and computational complexity.

show abstract

“…The possibility of acquiring PolSAR images by microwave earth observation sensors has provided unprecedented informative remote sensing data and has been applied successfully for different applications such as land use classification (Saito et al 2018;Santana-Cedrés et al 2019) and reliable accuracy has been achieved. Due to the unique features of polarimetric data, several researchers have evaluated the possibility of oil spill detection with PolSAR data through various algorithms (Migliaccio et al 2009(Migliaccio et al , 2015Kumar et al 2014;Li et al 2018;Tong et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Oil Spill Four-Class Classification Using UAVSAR Polarimetric Data

2020

View full text Add to dashboard Cite

Oil pollution of oceans from various sources is a devastating environmental problem and immediate detection of oil spills is crucial. Remote sensing techniques have provided an unprecedented opportunity for early oil spill detection and classification with an easy, quick, and cheap approach. Moreover, Fully Polarimetric Synthetic Aperture Radar (PolSAR) data with unique capabilities and informative features is an immense data source for oil spill detection on large scales. The objective of the present study is to utilize PolSAR data not only for oil spill detection, but also to classify the detected oil spill in the ocean into four classes: thick oil, thin oil, oil/water mixture, and clear water. In this study, numerous polarimetric decomposition parameters and texture features are extracted from the PolSAR image. A two-phase feature selection method, manually selection based on oil and water surface backscattering behavior and an optimization algorithm, has been employed on the extracted features to select the optimum feature set. The selected feature set has been used to classify the PolSAR image into oil and water classes. Moreover, the high sensitivity and discriminative power of the validation PolSAR dataset, UAVSAR L-band quad-pol data, is exploited by classifying the image into four classes. Remarkable acquired classification accuracies of 90.21% and 85.41% and Kappa coefficient of 0.8052 and 0.7905 for two-class and four-class classifications, respectively, demonstrate the robustness and high potential of the proposed methodology for oil spill detection and classification.

show abstract

Multi-Feature Based Ocean Oil Spill Detection for Polarimetric SAR Data Using Random Forest and the Self-Similarity Parameter

Cited by 54 publications

References 46 publications

Assessment of the X- and C-Band Polarimetric SAR Data for Plastic-Mulched Farmland Classification

Assessment of the X- and C-Band Polarimetric SAR Data for Plastic-Mulched Farmland Classification

Marine Oil Slick Detection Based on Multi-Polarimetric Features Matching Method Using Polarimetric Synthetic Aperture Radar Data

Oil Spill Four-Class Classification Using UAVSAR Polarimetric Data

Contact Info

Product

Resources

About