| 基于混合损失U-Net的SAR图像渤海海冰检测研究 |
| |
| 引用本文： | 徐欢,任沂斌.基于混合损失U-Net的SAR图像渤海海冰检测研究[J].海洋学报,2021,43(6):157-170. |
| |
| 作者姓名： | 徐欢 任沂斌 |
| |
| 作者单位： | 江苏海洋大学 海洋技术与测绘学院,江苏 连云港 222005;中国科学院海洋研究所 海洋环流与波动重点实验室,山东 青岛 266071;中国科学院海洋大科学研究中心,山东 青岛 266071 |
| |
| 基金项目： | 中国博士后科学基金(2019M662452)；中国科学院战略先导专项(XDA19060101，XDA19090103)；山东省重大科技创新工程(2019JZZY010102) |
| |
| 摘 要： | 渤海是我国重要的经济区，海冰灾害严重威胁着人类生产活动。合成孔径雷达具有全天候成像能力，研究渤海区域的SAR图像海冰检测具有重要意义。传统海冰检测方法受限于特征提取方法和建模方式，检测精度有待提升。深度学习具有极强的特征自学习能力，适用于图像检测问题。本文基于深度学习框架U-Net，以Sentinel-1双极化（VV和VH）合成孔径雷达图像为输入信息，设计混合损失函数优化传统U-Net模型，形成了基于混合损失U-Net的渤海海冰检测模型。将本文模型与传统海冰检测方法脉冲耦合神经网络（PCNN）、马尔科夫随机场（MRF）和分水岭算法]和基于深度卷积神经网络（CNN）的深度学习方法进行了对比。实验结果表明:本文基于混合损失U-Net的海冰检测模型在重叠度、F1分数、精确度和召回率4项度量指标上分别达到了97.567%、98.769%、98.767%和98.771%，检测效果明显优于对比方法；双极化信息输入的检测结果比VV单极化输入的检测结果在F1分数、精确度、召回率和重叠度上分别提高了0.375%、0.111%、0.639%和0.740%；混合损失函数的检测结果比非混合损失函数的检测结果在F1分数、精确度、召回率和重叠度上分别提高了1.129%、0.947%、1.794%和2.231%；模型能对冰水沿线、冰间水道、冰间隙等细节进行有效检测；可应用于渤海区域整幅SAR图像的海冰检测，为海冰监测、海冰变化分析、海冰预报提供技术支撑。
|
| 关 键 词： | 合成孔径雷达图像 海冰检测 深度学习 U-Net 混合损失函数 |
| 收稿时间： | 2020-07-18 |
Detecting sea ice of Bohai Sea using SAR images based on a hybrid loss U-Net model |
| |
| Institution: | 1.School of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang 222005, China2.Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao 266071, China3.Center for Ocean Mega-Science, Chinese Academy of Sciences, Qingdao 266071, China |
| |
| Abstract: | The Bohai Sea is an important economic zone of China. Sea ice has been a significant threat to the human activities around the Bohai Sea. As the imaging capability of synthetic aperture radar (SAR) is independent of sun illumination and cloud condition, it is of great significance to detect the sea ice of the Bohai Sea from SAR images. Due to the limitation of the feature extraction mechanism, the accuracies of traditional sea ice detection methods need to be improved. Deep learning has a strong self-learning ability and is suitable for image detection. Here, we employ the well-known deep learning framework, U-Net, as the basic structure, and design a hybrid loss function to optimize the U-Net model, forming a hybrid loss U-Net model for sea ice detection in the Bohai Sea. The Sentinel-1 dual-polarization (VV and VH) SAR images are the inputs of the model. We compare the hybrid loss U-Net model with several traditional methods (Pulse Coupled Neural Network, Markov Random Field and Watershed Algorithm) and deep learning method based on CNN. Experiments show that the hybrid loss U-Net-based model achieves 97.567%, 98.769%, 98.767% and 98.771% in IoU, F1_Score, Precision and Recall respectively, outperforming the other methods. Compared with VV single-polarized input, the detection results of dual-polarized information input are 0.375%, 0.111%, 0.639% and 0.740% higher in F1_Score, Precision, Recall and IoU respectively. The detection results of the hybrid loss model are 1.129%, 0.947%, 1.794% and 2.231% higher than those of the non-hybrid loss function in F1_Score, Precision, Recall and IoU respectively. The model could effectively detect details such as ice water line, inter-ice water and ice gap. Our model is applied to detect the sea ice of a whole SAR image in the Bohai Sea, which can provide technical supports for sea ice monitoring, sea ice change analysis and sea ice prediction. |
| |
| Keywords: | |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《海洋学报》浏览原始摘要信息 |
| 点击此处可从《海洋学报》下载免费的PDF全文 |
|
