1
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: not found
      Is Open Access

      A Deep Convolutional Neural Network for Oil Spill Detection from Spaceborne SAR Images

      ,
      Remote Sensing
      MDPI AG

      Read this article at

      ScienceOpenPublisher
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Classification algorithms for automatically detecting sea surface oil spills from spaceborne Synthetic Aperture Radars (SARs) can usually be regarded as part of a three-step processing framework, which briefly includes image segmentation, feature extraction, and target classification. A Deep Convolutional Neural Network (DCNN), named the Oil Spill Convolutional Network (OSCNet), is proposed in this paper for SAR oil spill detection, which can do the latter two steps of the three-step processing framework. Based on VGG-16, the OSCNet is obtained by designing the architecture and adjusting hyperparameters with the data set of SAR dark patches. With the help of the big data set containing more than 20,000 SAR dark patches and data augmentation, the OSCNet can have as many as 12 weight layers. It is a relatively deep Deep Learning (DL) network for SAR oil spill detection. It is shown by the experiments based on the same data set that the classification performance of OSCNet has been significantly improved compared to that of traditional machine learning (ML). The accuracy, recall, and precision are improved from 92.50%, 81.40%, and 80.95% to 94.01%, 83.51%, and 85.70%, respectively. An important reason for this improvement is that the distinguishability of the features learned by OSCNet itself from the data set is significantly higher than that of the hand-crafted features needed by traditional ML algorithms. In addition, experiments show that data augmentation plays an important role in avoiding over-fitting and hence improves the classification performance. OSCNet has also been compared with other DL classifiers for SAR oil spill detection. Due to the huge differences in the data sets, only their similarities and differences are discussed at the principle level.

          Related collections

          Most cited references12

          • Record: found
          • Abstract: not found
          • Conference Proceedings: not found

          Adam: a method for stochastic optimization

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            Dropout: A simple way to prevent neural networks from ooverfitting

              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              The Effectiveness of Data Augmentation in Image Classification using Deep Learning

              In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping, rotating, and flipping input images. We artificially constrain our access to data to a small subset of the ImageNet dataset, and compare each data augmentation technique in turn. One of the more successful data augmentations strategies is the traditional transformations mentioned above. We also experiment with GANs to generate images of different styles. Finally, we propose a method to allow a neural net to learn augmentations that best improve the classifier, which we call neural augmentation. We discuss the successes and shortcomings of this method on various datasets. 8 pages, 12 figures
                Bookmark

                Author and article information

                Contributors
                Journal
                Remote Sensing
                Remote Sensing
                MDPI AG
                2072-4292
                March 2020
                March 22 2020
                : 12
                : 6
                : 1015
                Article
                10.3390/rs12061015
                20b7291f-f507-410e-87a1-ca3dfff07b91
                © 2020

                https://creativecommons.org/licenses/by/4.0/

                Product
                Self URI (article page): https://www.mdpi.com/2072-4292/12/6/1015

                Comments

                Comment on this article