Oil spill segmentation in SAR images using convolutional neural networks. A comparative analysis with clustering and logistic regression algorithms
| Autor: | Diego Cantorna, Bernardino Arcay, Carlos Dafonte, Alfonso Iglesias |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Synthetic aperture radar
0209 industrial biotechnology Decision support system Artificial neural network Pixel Computer science 02 engineering and technology Convolutional neural network Identification (information) 020901 industrial engineering & automation Oil spill 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Cluster analysis Algorithm Software |
| Zdroj: | Applied Soft Computing. 84:105716 |
| ISSN: | 1568-4946 |
| DOI: | 10.1016/j.asoc.2019.105716 |
| Popis: | Synthetic aperture radar (SAR) images are a valuable source of information for the detection of marine oil spills. For their effective analysis, it is important to have segmentation algorithms that can delimit possible oil spill areas. This article addresses the application of clustering, logistic regression and convolutional neural network algorithms for the detection of oil spills in Envisat and Sentinel-1 satellite images. Large oil spills do not occur frequently so that the identification of a pixel as oil is relatively uncommon. Metrics based on Precision–Recall curves have been employed because they are useful for problems with an imbalance in the number of samples from the classes. Although logistic regression and clustering algorithms can be considered useful for oil spill segmentation, the combination of convolutional techniques and neural networks achieves the best results with low computing time. A convolutional neural network has been integrated into a decision support system in order to facilitate decision-making and data analysis of possible oil spill events. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect