AI Radar Sensor: Creating Radar Depth Sounder Images Based on Generative Adversarial Network
AI Radar Sensor: Creating Radar Depth Sounder Images Based on Generative Adversarial Network
复制标题
DOI：
10.3390/s19245479
复制
发表时间：
2019-12
期刊：
影响因子：
--
通讯作者：
M. Rahnemoonfar;Jimmy Johnson;J. Paden
中科院分区：
文献类型：
--
作者：
M. Rahnemoonfar;Jimmy Johnson;J. Paden
在昂贵的北极和南极实地考察期间，已经花费了大量资源来收集和存储大型且异构的雷达数据集。现有的绝大多数数据都没有标注，而标注过程既耗时又昂贵。标注过程的一种可能替代方案是利用人工智能生成合成数据。我们可以基于任意标签生成合成数据，而不是对真实图像进行标注。通过这种方式，可以用额外的图像快速扩充训练数据。在这项研究中，我们基于改进的循环一致对抗网络评估了合成生成的雷达图像的性能。我们进行了几次实验来测试生成的雷达图像的质量。我们还在合成数据以及真实数据和合成数据的不同组合上测试了一种最先进的轮廓检测算法的质量。我们的实验表明，由生成对抗网络（GAN）生成的合成雷达图像可与真实图像结合用于数据扩充和深度神经网络的训练。然而，GAN生成的合成图像不能单独用于训练神经网络（在合成数据上训练，在真实数据上测试），因为它们无法模拟所有雷达特性，如噪声或多普勒效应。据我们所知，这是基于生成对抗网络创建雷达测深仪图像的第一项工作。
Significant resources have been spent in collecting and storing large and heterogeneous radar datasets during expensive Arctic and Antarctic fieldwork. The vast majority of data available is unlabeled, and the labeling process is both time-consuming and expensive. One possible alternative to the labeling process is the use of synthetically generated data with artificial intelligence. Instead of labeling real images, we can generate synthetic data based on arbitrary labels. In this way, training data can be quickly augmented with additional images. In this research, we evaluated the performance of synthetically generated radar images based on modified cycle-consistent adversarial networks. We conducted several experiments to test the quality of the generated radar imagery. We also tested the quality of a state-of-the-art contour detection algorithm on synthetic data and different combinations of real and synthetic data. Our experiments show that synthetic radar images generated by generative adversarial network (GAN) can be used in combination with real images for data augmentation and training of deep neural networks. However, the synthetic images generated by GANs cannot be used solely for training a neural network (training on synthetic and testing on real) as they cannot simulate all of the radar characteristics such as noise or Doppler effects. To the best of our knowledge, this is the first work in creating radar sounder imagery based on generative adversarial network.