Deep multi-scale learning for automatic tracking of internal layers of ice in radar data
Deep multi-scale learning for automatic tracking of internal layers of ice in radar data
复制标题
DOI：
10.1017/jog.2020.80
复制
发表时间：
2020-10
影响因子：
3.4
通讯作者：
M. Rahnemoonfar;M. Yari;J. Paden;L. Koenig;O. Ibikunle
中科院分区：
文献类型：
--
作者：
M. Rahnemoonfar;M. Yari;J. Paden;L. Koenig;O. Ibikunle
摘要 在这项研究中，我们的目标是通过 NASA 冰桥行动收集的雪雷达数据来跟踪内部冰层。我们研究了深度学习方法在从极地收集的雷达数据上的应用。人工智能技术在许多实际领域取得了令人瞩目的成功。深度神经网络的成功归功于大量标记数据的可用性。然而，在许多现实世界的问题中，即使有大型数据集可用，由于缺乏大型标记数据集、数据中存在噪声或数据缺失等原因，深度学习方法的成功率也较低。在我们的雷达数据中，噪声的存在是利用迁移学习等流行深度学习方法的主要障碍之一。我们的实验表明，如果训练神经网络来检测光电图像中物体的轮廓，它只能跟踪雷达数据中一小部分轮廓。微调和进一步培训并不能提供任何更好的结果。然而，我们表明，选择正确的模型并从一开始就在雷达图像上对其进行训练会产生更好的结果。
Abstract In this study, our goal is to track internal ice layers on the Snow Radar data collected by NASA Operation IceBridge. We examine the application of deep learning methods on radar data gathered from polar regions. Artificial intelligence techniques have displayed impressive success in many practical fields. Deep neural networks owe their success to the availability of massive labeled data. However, in many real-world problems, even when a large dataset is available, deep learning methods have shown less success, due to causes such as lack of a large labeled dataset, presence of noise in the data or missing data. In our radar data, the presence of noise is one of the main obstacles in utilizing popular deep learning methods such as transfer learning. Our experiments show that if the neural network is trained to detect contours of objects in electro-optical imagery, it can only track a low percentage of contours in radar data. Fine-tuning and further training do not provide any better results. However, we show that selecting the right model and training it on the radar imagery from the start yields far better results.