Sea Fog Related Work

1、Dual-Branch Neural Network for Sea Fog Detection in Geostationary Ocean Color Imager

本文提出了一种 DB-SFNet 来实现准确和全面的海雾检测。 所提出的dual-branch sea fog detection network (DB-SFNet) DB-SFNet 由知识提取模块和双分支可选编码解码模块组成。 这两个模块共同从视觉和统计领域中提取判别特征。

The proposed DB-SFNet is composed of a knowledge extraction module and a dual-branch optional encoding decoding module. The two modules jointly extract discriminative features from both visual and statistical domains.

Y. Zhou, K. Chen and X. Li, "Dual-Branch Neural Network for Sea Fog Detection in Geostationary Ocean Color Imager," in IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1-17, 2022, Art no. 4208617, doi: 10.1109/TGRS.2022.3196177.

2、A scSE-LinkNet Deep Learning Model for Daytime Sea Fog Detection

本研究提出了一种用于白天海雾检测的 scSE-LinkNet 模型，该模型利用残差块到编码器特征图和注意模块，通过考虑节点的光谱和空间信息来学习海雾数据的特征。

This study proposes a scSE-LinkNet model for daytime sea fog detection that leverages residual blocks to encoder feature maps and attention module to learn the features of sea fog data by considering spectral and spatial information of nodes.

Guo X, Wan J, Liu S, et al. A scse-linknet deep learning model for daytime sea fog detection[J]. Remote Sensing, 2021, 13(24): 5163.

3、

此外，许多研究采用了不同的方法来使用机器学习进行海雾检测。 这包括诸如期望最大化算法 (EM) [21] 和决策树 (DT) [22] 之类的方法来精确区分层云和海雾。 虽然机器学习的引入进一步厘清了层云和海雾的界限，但由于检测结果的转化和可视化，过程更加繁琐。

Additionally, a number of studies have taken a different approach for sea fog detection using machine learning. This includes methods such as the expectation maximization algorithm (EM) [21] and decision tree (DT) [22] to precisely differentiate between stratus and sea fog. Although the introduction of machine learning further clarifies the stratus and sea fog boundaries, the process is more cumbersome because of the transformation and visualization of the detection results.

[21] Shin, D.; Kim, J.H. A New Application of Unsupervised Learning to Nighttime Sea Fog Detection. Asia Pac. J. Atmos. Sci. 2018, 54, 527–544. [Google Scholar] [CrossRef][Green Version

[22] Kim, D.; Park, M.S.; Park, Y.J.; Kim, W. Geostationary Ocean Color Imager (GOCI) Marine Fog Detection in Combination with Himawari-8 Based on the Decision Tree. Remote Sens. 2020, 12, 149. [Google Scholar] [CrossRef][Green Version]

4、Fast Cloud Segmentation Using Convolutional Neural Networks

本文提出了一种新的基于深度学习的云分类方法。 依靠卷积神经网络 (CNN) 架构进行图像分割，提出的云分割 CNN (CS-CNN) 同时对场景的所有像素进行分类，而不是单独分类

This paper proposes a novel cloud classification method based on deep learning. Relying on a Convolutional Neural Network (CNN) architecture for image segmentation, the presented Cloud Segmentation CNN (CS-CNN), classifies all pixels of a scene simultaneously rather than individually.

Drönner J, Korfhage N, Egli S, et al. Fast cloud segmentation using convolutional neural networks[J]. Remote Sensing, 2018, 10(11): 1782.

5、Sea Fog Identification from GOCI Images Using CNN Transfer Learning Models

本研究提出了一种通过应用卷积神经网络传输学习 (CNN-TL) 模型使用同步海洋彩色成像仪 (GOCI) 数据识别海雾的方法。 在这项研究中，VGG19 和 ResNet50 是预训练的 CNN 模型，因其高识别性能而被使用。

This study proposes an approaching method of identifying sea fog by using Geostationary Ocean Color Imager (GOCI) data through applying a Convolution Neural Network Transfer Learning (CNN-TL) model. In this study, VGG19 and ResNet50, pre-trained CNN models, are used for their high identification performance.

6、Sea fog detection based on unsupervised domain adaptation

我们提出了一种无监督域自适应方法来桥接丰富的标记陆雾数据和未标记海雾数据，以实现海雾检测。

we propose an unsupervised domain adaptation method to bridge the abundant labeled land fog data and the unlabeled sea fog data to realize the sea fog detection

7、

例如，基于从中国安徽省收集的 Himawari-8 标准数据 (HSD8)，卷积神经网络 (CNN) 用于雾图像分类。25 Qu 等人 26 使用深度卷积神经网络 (DCNN) 进行云检测任务 基于FY-3D/MERSI和EOS/MODIS数据。

For example, Convolutional Neural Network (CNN) was used in fog images classification based on Himawari-8 Standard Data (HSD8) collected from Anhui Province, China.[25] Qu et al.[26] used Deep Convolutional Neural Network (DCNN) for cloud detection task based on data of FY-3D/MERSI and EOS/MODIS.

[25] Deep convolutional neural network for fog detection.

[26] Research on the cloud detection model of FY3D/MERSI and EOS/MODIS based on deep learning

8、Daytime Sea Fog Detection Based on a Two-Stage Neural Network

针对这一难题，提出了一种基于两阶段深度学习策略的黄渤海白天海雾检测新方法。 我们首先利用全连接网络将晴朗的天空与海雾和云层分开。 然后，使用卷积神经网络在 16 个 Advanced Himawari Imager (AHI) 观测波段上提取低云和海雾之间的差异。

To address this difficulty, a new method based on a two-stage deep learning strategy was proposed to detect daytime sea fog in the Yellow Sea and Bohai Sea. We first utilized a fully connected network to separate the clear sky from sea fog and clouds. Then, a convolutional neural network was used to extract the differences between low clouds and sea fog on 16 Advanced Himawari Imager (AHI) observation bands.

Tang Y, Yang P, Zhou Z, et al. Daytime Sea Fog Detection Based on a Two-Stage Neural Network[J]. Remote Sensing, 2022, 14(21): 5570.

9、Cloud Image Retrieval for Sea Fog Recognition (CIR-SFR) Using Double Branch Residual Neural Network

因此，我们结合度量学习的优点，在深度学习 (DL) 框架中提出了一种用于海雾识别 (CIR-SFR) 的云图像检索方法。 CIR-SFR 包括特征提取模块和基于检索的 SFR 模块。 特征提取模块采用双分支残差神经网络（DBRNN）综合提取云图的全局和局部特征。 通过引入本地分支和使用激活掩码，DBRNN 可以专注于云图像中的感兴趣区域。 此外，通过引入多重相似性损失，将云图特征投影到语义空间，有效提高了海雾和低层云的辨别能力。

Thus, we propose a cloud image retrieval method for sea fog recognition (CIR-SFR) in a deep learning (DL) framework by combining the advantages of metric learning. CIR-SFR includes the feature extraction module and the retrieval-based SFR module. The feature extraction module adopts the double branch residual neural network (DBRNN) to comprehensively extract the global and local features of cloud images. By introducing local branches and using activation masks, DBRNN can focus on regions of interest in cloud images. Moreover, cloud image features are projected into the semantic space by introducing multisimilarity loss, which effectively improves the discrimination ability of sea fog and low-level clouds. or the retrieval-based SFR module, similar cloud images are retrieved from the cloud image dataset according to the distance in the feature space, and accurate SFR results are obtained by counting the percentage of various cloud image types in the retrieval results.

Hu T, Jin Z, Yao W, et al. Cloud Image Retrieval for Sea Fog Recognition (CIR-SFR) Using Double Branch Residual Neural Network[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2023, 16: 3174-3186.