基于多模态融合的GF-5号遥感图像云检测

大气与环境光学学报 ›› 2023, Vol. 18 ›› Issue (4): 371-382.

• 高分五号 02 星偏振载荷在轨测试和信息处理 • 上一篇下一篇

基于多模态融合的GF-5号遥感图像云检测

张苏贵 1,2, 张晶晶 1,2*, 寻丽娜 1,2, 孙晓兵 3, 熊伟 3, 阎庆 1,2, 李穗 4

1 安徽大学计算智能与信号处理教育部重点实验室, 安徽合肥 230601; 2 安徽大学电气工程与自动化学院, 安徽合肥 230601; 3 中国科学院通用光学定标与表征技术重点实验室, 安徽合肥 230031; 4 安徽文达信息工程学院, 安徽合肥 231201

收稿日期:2022-10-31 修回日期:2023-01-19 出版日期:2023-07-28 发布日期:2023-08-14
通讯作者: E-mail: 874878644@qq.com E-mail:874878644@qq.com
作者简介:张苏贵 (1997- ), 女, 江苏宿迁人, 硕士研究生, 主要从事遥感图像云检测方面的研究。 E-mail: zsg5802085@163.com
基金资助:
中国科学院通用光学定标与表征技术重点实验室开放研究基金

Cloud detection of GF-5 remote sensing image based on multimodal fusion

ZHANG Sugui 1,2, ZHANG Jingjing 1,2*, XUN Lina 1,2, SUN Xiaobing 3, XIONG Wei 3, YAN Qing 1,2, LI Sui 4

1 Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University, Hefei 230601, China; 2 School of Electrical Engineering and Automation, Anhui University, Hefei 230601, China; 3 Key Laboratory of Optical Calibration and Characterization, Chinese Academy of Sciences, Hefei 230031, China; 4 Anhui Wenda University of Information Engineering, Hefei 231201, China

Received:2022-10-31 Revised:2023-01-19 Published:2023-07-28 Online:2023-08-14
Contact: Jingjing ZHANG JingjingZhang E-mail:874878644@qq.com

摘要/Abstract

摘要： 云检测对于遥感图像的应用具有重要意义。目前已有的云检测方法关于遥感图像的偏振信息研究较少，性能和泛化能力有限。为有效利用遥感图像偏振信息，提出了一种基于深度学习的多模态融合遥感图像云检测方法并进行了初步实验评价。该网络是一种三参数输入流架构，具有编码器-解码器结构，利用通道空间注意模块对遥感图像中的反射率特征和偏振特征进行多模态融合。在解码器上采样阶段，利用迭代注意特征融合方法融合高、低级特征映射。评价实验数据集来源于多角度偏振成像仪 (DPC) 云产品和云掩码产品。评价实验结果表明，所提出的网络模型实现了良好的云检测性能，识别准确率达到93.91%。

关键词: 云检测, 偏振信息, 多模态融合, 通道空间注意, 迭代注意特征融合

Abstract: Cloud detection is of great significance for the application of remote sensing images. However, as for the existing cloud detection methods, there is limited research on the polarization information of remote sensing images, and their performance and generalization ability are also limited. To effectively utilize the polarization information of remote sensing images, a multimodal fusion remote sensing image cloud detection method based on depth learning is proposed and its preliminary experimental evaluation is conducted. In the method, the network is a three-parameter input stream architecture with an encoderdecoder structure, and the channel-spatial attention module is used to perfom multimodal fusion of reflectance and polarization features in remote sensing images. In the upsampling stage of the decoder, the iterative attention feature fusion method is used to fuse the high- and low-level feature maps. The evaluation experimental data set comes from Directional Polarization Camera (DPC) cloud products and cloud mask products. The evaluation results show that the proposed network model achieves good cloud detection performance, with a recognition accuracy of 93.91%.

Key words: cloud detection, polarization information, multimodal fusion, channel-spatial attention; iterative attention feature fusion

中图分类号:

P407

张苏贵, 张晶晶, 寻丽娜, 孙晓兵, 熊伟, 阎庆, 李穗 . 基于多模态融合的GF-5号遥感图像云检测[J]. 大气与环境光学学报, 2023, 18(4): 371-382.

ZHANG Sugui , ZHANG Jingjing , XUN Lina , SUN Xiaobing , XIONG Wei , YAN Qing , LI Sui . Cloud detection of GF-5 remote sensing image based on multimodal fusion[J]. Journal of Atmospheric and Environmental Optics, 2023, 18(4): 371-382.

参考文献 20

[1]	Guo Q, Zhao Y H, Li A. Cloud detection for DSCOVR EPIC data [C]. Proceedings of the 2018 2nd International Conference
	on Video and Image Processing. December 29-31, 2018, Hong Kong. New York: ACM, 2018: 55-59.
[2]	Dubovik O, Li Z Q, Mishchenko M I, et al. Polarimetric remote sensing of atmospheric aerosols: Instruments,
	methodologies, results, and perspectives [J]. Journal of Quantitative Spectroscopy and Radiative Transfer, 2019, 224:
47	4-511.
[3]	Shao M, Zou Y. Multi-spectral cloud detection based on a multi-dimensional and multi-grained dense cascade forest [J].
	Journal of Applied Remote Sensing, 2021, 15(2): 028507.
[4]	Sun Y Z, Jiang G W, Li Y D, et al. GF-5 satellite: Overview and application prospects [J]. Spacecraft Recovery & Remote
	Sensing, 2018, 39(3): 1-13.
	孙允珠, 蒋光伟, 李云端, 等.“ 高分五号”卫星概况及应用前景展望 [J]. 航天返回与遥感, 2018, 39(3): 1-13.
[5]	Yan Q, Liu H, Zhang J J, et al. Cloud detection of remote sensing image based on multi-scale data and dual-channel attention
	mechanism [J]. Remote Sensing, 2022, 14(15): 3710.
[6]	Zhu Z, Woodcock C E. Object-based cloud and cloud shadow detection in Landsat imagery [J]. Remote Sensing of
	Environment, 2012, 118: 83-94.
[7]	Kriebel K T, Gesell G, Kästner M, et al. The cloud analysis tool APOLLO: Improvements and validations [J]. International
	Journal of Remote Sensing, 2003, 24(12): 2389-2408.
[8]	Liu Z L, Yang J J, Wang W J, et al. Cloud detection methods for remote sensing images: A survey [J]. Chinese Space Science
	and Technology, 2023, 43(1): 1-17.
	刘子力, 杨家俊, 王文静, 等. 遥感图像云检测方法综述 [J]. 中国空间科学技术, 2023, 43(1): 1-17.
[9]	Rossi R, Basili R, Frate F D, et al. Techniques based on Support Vector Machines for cloud detection on QuickBird satellite
	imagery [C]. 2011 IEEE International Geoscience and Remote Sensing Symposium. July 24-29, 2011, Vancouver, BC,
	Canada. IEEE, 2011: 515-518.
[10]	Li P F, Dong L M, Xiao H C, et al . A cloud image detection method based on SVM vector machine [J]. Neurocomputing,
20	15, 169: 34-42.
[11]	Chen G, Dong C E. Support vector machines for cloud detection over ice-snow areas [J]. Geo-spatial Information Science,
20	07, 10(2): 117-120.
[12]	Zhan Y J, Wang J, Shi J P, et al. Distinguishing cloud and snow in satellite images via deep convolutional network [J]. IEEE
	Geoscience and Remote Sensing Letters, 2017, 14(10): 1785-1789.
[13]	Li J X, Zhao P, Fang W, et al. Cloud detection of multi-angle remote sensing image based on deep learning [J]. Journal of
	Atmospheric and Environmental Optics, 2020, 15(5): 380-392.
	李佳欣, 赵鹏, 方薇, 等. 基于深度学习的多角度遥感影像云检测方法 [J]. 大气与环境光学学报, 2020, 15(5): 380-392.
[14]	Yang J Y, Guo J H, Yue H J, et al. CDnet: CNN-Based cloud detection for remote sensing imagery [J]. IEEE Transactions on
	Geoscience and Remote Sensing, 2019, 57(8): 6195-6211.
[15]	Zhang J J, Ge K, Xun L N, et al. MFCD-net: Cross attention based multimodal fusion network for DPC imagery cloud
	detection [J]. Remote Sensing, 2022, 14(16): 3905.
[16]	Wang J J, Sun X B, Ti R F, et al. Multi-angle polarization radiation threshold detection method of cloud cover over ocean [J].
	Journal of Atmospheric and Environmental Optics, 2021, 16(3): 247-255.
	王佳佳, 孙晓兵, 提汝芳, 等. 海洋上空云多角度偏振辐射阈值检测方法研究 [J]. 大气与环境光学学报, 2021, 16(3):
24	7-255.
[17]	Dai Y M, Gieseke F, Oehmcke S, et al. Attentional Feature Fusion [C]. IEEE Winter Conference on Applications of Computer
	Vision (WACV). January 05―09, 2021, Electr Network, 2021: 3559-3568..
[18]	Wang J J. Cloud Detection and Cloud Phase Inversion and Examples Analysis of Strong Convective Cloud Clusters Based on
	DPC Polarized Remote Sensing Data of Gaofen-5 Satellite [D]. Hefei: University of Science and Technology of China, 2021.
	王佳佳. 高五DPC偏振遥感云检测相态反演及强对流云团个例研究 [D]. 合肥: 中国科学技术大学, 2021.
[19]	Parol F, Buriez J C, Vanbauce C, et al. First results of the POLDER "Earth Radiation Budget and Clouds" operational
	algorithm [J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(3): 1597-1612.
[20]	Sèze G, Vanbauce C, Burie J C, et al. Cloud cover observed simultaneously from FOLDER and METEOSAT [J]. Physics
	and Chemistry of the Earth, Part B: Hydrology, Oceans and Atmosphere, 1999, 24(8): 921-926.

基于多模态融合的GF-5号遥感图像云检测

Cloud detection of GF-5 remote sensing image based on multimodal fusion

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 20

相关文章 8

编辑推荐

Metrics

本文评价

[1]	郭庭威, 黄红莲, 孙晓兵, 刘晓, 提汝芳 . 环境二号卫星多光谱图像的薄云检测及去除[J]. 大气与环境光学学报, 2023, 18(4): 383-400.
[2]	侯梦雨, 李正强∗, 谢一凇, 乔瑞, 谢艳清, 伽丽丽, 史正, . 国产卫星多角度偏振传感器的光谱特征云检测方法研究[J]. 大气与环境光学学报, 2022, 17(6): 598-612.
[3]	吴文涵, 麻金继∗, 孙二昌, 郭金雨, 杨光, 王宇瑶. 基于深度学习的云参量反演方法研究[J]. 大气与环境光学学报, 2022, 17(4): 453-464.
[4]	王佳佳, 孙晓兵∗, 提汝芳, 余海啸, . 海洋上空云多角度偏振辐射阈值检测方法研究[J]. 大气与环境光学学报, 2021, 16(3): 247-255.
[5]	张波, 胡亚东∗, 洪津. 基于多特征融合的层次支持向量机遥感图像云检测[J]. 大气与环境光学学报, 2021, 16(1): 58-66.
[6]	李佳欣, 赵鹏, 方薇∗, 宋尚香, . 基于深度学习的多角度遥感影像云检测方法[J]. 大气与环境光学学报, 2020, 15(5): 380-392.
[7]	夏雨崔生成杨世植. 综合高分卫星图像多维特征的云检测方法[J]. 大气与环境光学学报, 2017, 12(6): 465-.
[8]	刘显通刘奇傅云飞程静. 基于TRMM VIRS可见光和红外五通道的白天云检测方案[J]. 大气与环境光学学报, 2010, 5(2): 128-140.