Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNN
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 sl...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/17/8/1837 |
| _version_ | 1828742457990316032 |
|---|---|
| author | Hao Guo Danni Wu Jubai An |
| author_facet | Hao Guo Danni Wu Jubai An |
| author_sort | Hao Guo |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-13T01:20:08Z |
| format | Article |
| id | doaj.art-a658f3f6efdc4de8aedc59f04c63b0a1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-13T01:20:08Z |
| publishDate | 2017-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a658f3f6efdc4de8aedc59f04c63b0a12022-12-22T03:08:48ZengMDPI AGSensors1424-82202017-08-01178183710.3390/s17081837s17081837Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNNHao Guo0Danni Wu1Jubai An2Information Science and Technology College, Dalian Maritime University, Dalian 116026, ChinaInformation Science and Technology College, Dalian Maritime University, Dalian 116026, ChinaInformation Science and Technology College, Dalian Maritime University, Dalian 116026, ChinaOil 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.https://www.mdpi.com/1424-8220/17/8/1837Synthetic Aperture Radar (SAR)pattern recognitionoil slickslookalikesfeature fusionConvolutional Neural Network (CNN) |
| spellingShingle | Hao Guo Danni Wu Jubai An Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNN Sensors Synthetic Aperture Radar (SAR) pattern recognition oil slicks lookalikes feature fusion Convolutional Neural Network (CNN) |
| title | Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNN |
| title_full | Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNN |
| title_fullStr | Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNN |
| title_full_unstemmed | Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNN |
| title_short | Discrimination of Oil Slicks and Lookalikes in Polarimetric SAR Images Using CNN |
| title_sort | discrimination of oil slicks and lookalikes in polarimetric sar images using cnn |
| topic | Synthetic Aperture Radar (SAR) pattern recognition oil slicks lookalikes feature fusion Convolutional Neural Network (CNN) |
| url | https://www.mdpi.com/1424-8220/17/8/1837 |
| work_keys_str_mv | AT haoguo discriminationofoilslicksandlookalikesinpolarimetricsarimagesusingcnn AT danniwu discriminationofoilslicksandlookalikesinpolarimetricsarimagesusingcnn AT jubaian discriminationofoilslicksandlookalikesinpolarimetricsarimagesusingcnn |