改进D-LinkNet模型在国产卫星影像云检测中的应用

doi:10.13474/j.cnki.11-2246.2021.338

测绘通报 ›› 2021, Vol. 0 ›› Issue (11): 54-58,64.doi: 10.13474/j.cnki.11-2246.2021.338

改进D-LinkNet模型在国产卫星影像云检测中的应用

刘广进^1,2, 王光辉^1,2, 毕卫华³, 刘慧杰², 杨化超¹

1. 中国矿业大学环境与测绘学院, 江苏徐州 221116;
2. 自然资源部国土卫星遥感应用中心, 北京 100048;
3. 皖北煤电集团有限责任公司, 安徽宿州 234002

收稿日期:2021-03-29 出版日期:2021-11-25 发布日期:2021-12-02
通讯作者: 王光辉。E-mail:wanggh@lasac.cn
作者简介:刘广进(1998-),男,硕士生,研究方向为遥感影像云检测。E-mail:1538868186@qq.com
基金资助:
国家重点研发计划；国家自然科学基金（2017YFE0119600）

Application of improved D-LinkNet model in cloud detection of domestic satellite image

LIU Guangjin^1,2, WANG Guanghui^1,2, BI Weihua³, LIU Huijie², YANG Huachao¹

1. School of Environment and Spatial Informatics, China University of Mining and Technology, Xuzhou 221116, China;
2. Land Satellite Remote Sensing Application Center, MNR, Beijing 100048, China;
3. Wanbei Coal and Electricity Co., Ltd., Suzhou 234002, China

Received:2021-03-29 Online:2021-11-25 Published:2021-12-02

摘要/Abstract

摘要： 大部分国产卫星波段少，利用传统方法难以进行云检测。本文提出了基于改进D-LinkNet模型的云检测算法，并应用于国产卫星遥感影像的云检测。首先，利用自然资源部国土卫星遥感应用中心提供的人工勾云样本生成二值图标签；其次，对D-LinkNet50的编码器进行改进，使用带有通道注意力机制的ResNeSt50-Block替换原始的ResNet50-Block；然后，对损失函数进行加权，测试分析发现只用交叉熵损失作为损失函数时，检测精度更高；最后，使用条件随机场（CRF）对预测结果进行后处理。试验结果表明，改进D-LinkNet模型在测试集上的IoU提升了1.93%，精度提升了2.45%，保持了较好的云边缘信息，云检测效果高于原D-LinkNet模型。

关键词: 云检测, D-LinkNet, 注意力机制, 国产卫星, 条件随机场

Abstract: Due to the lack of band of most domestic satellites, cloud detection is difficult using traditional methods. In this paper, a cloud detection algorithm based on improved D-LinkNet model is proposed and applied to domestic satellite remote sensing image cloud detection. Firstly, the binary image label is generated by using ResNeSt50-Block with channel attention mechanism. Secondly, the encoder of D-LinkNet50 is improved by using ResNeSt50-Block with channel attention mechanism to replace the original ResNet50-Block. And then the loss function is weighted, and it is found that the cross-entropy loss is the only loss function with higher precision. Finally, the conditional random field (CRF) is used to post-process the predicted results. The experimental results show that the MIoU and precision of the improved D-LinkNet model are improved by 1.93% and 2.45% respectively, and the cloud edge information is kept well. It can be used in cloud detection, and the effect is obviously higher than that of the original D-LinkNet model.

Key words: cloud detection, D-LinkNet, attention mechanism, domestic satellite, conditional random field

中图分类号:

P237

刘广进, 王光辉, 毕卫华, 刘慧杰, 杨化超. 改进D-LinkNet模型在国产卫星影像云检测中的应用[J]. 测绘通报, 2021, 0(11): 54-58,64.

LIU Guangjin, WANG Guanghui, BI Weihua, LIU Huijie, YANG Huachao. Application of improved D-LinkNet model in cloud detection of domestic satellite image[J]. Bulletin of Surveying and Mapping, 2021, 0(11): 54-58,64.

参考文献

[1] ZHANG Y C, ROSSOW W B, LACIS A A, et al. Calcula-tion of radiative fluxes from the surface to top of atmosphere based on ISCCP and other global data sets:refinements of the radiative transfer model and the input data[J]. Journal of Geophysical Research:Atmospheres,2004,109(D19):105-115.
[2] JU J C, ROY D P. The availability of cloud-free Landsat ETM+ data over the conterminous United States and globally[J]. Remote Sensing of Environment,2008,112(3):1196-1211.
[3] ZHU Z, WOODCOCK C E. Object-based cloud and cloud shadow detection in Landsat imagery[J]. Remote Sensing of Environment, 2012, 118:83-94.
[4] XIE F Y, SHI M Y, SHI Z W, et al. Multilevel cloud detection in remote sensing images based on deep learning[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017,10(8):3631-3640.
[5] 陈曦东,张肖,刘良云,等.增强型多时相云检测[J].遥感学报,2019,23(2):280-290.
[6] 刘云峰,杨珍,韩骁,等.国产高分辨率卫星影像云检测方法分析[J].测绘通报,2020(11):66-70.
[7] 张家强,李潇雁,李丽圆,等.基于深度残差全卷积网络的Landsat 8遥感影像云检测方法[J].激光与光电子学进展,2020,57(10):364-371.
[8] 张永宏,蔡朋艳,陶润喆,等.基于改进U-Net网络的遥感图像云检测[J].测绘通报,2020(3):17-20.
[9] ZHOU L C, ZHANG C, WU M. D-LinkNet:LinkNet with pretrained encoder and dilated convolution for high resolution satellite imagery road extraction[C]//IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Salt Lake City:IEEE,2018.
[10] 彭博.基于深度学习的遥感图像道路信息提取算法研究[D].成都:电子科技大学,2019.
[11] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of 2018 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Salt Lake City:IEEE,2018:7132-7141.
[12] LI X,WANG W H,HU X L,et al.Selective kernel networks[C]//Proceedings of 2019 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Long Beach:IEEE,2019:510-519.
[13] XIE S N, GIRSHICK R, DOLLÁR P, et al. Aggregated residual transformations for deep neural networks[C]//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). Honolulu:IEEE,2017.
[14] HE K M,ZHAN X Y, REN S Q. Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR). LasVegas:IEEE,2016:770-778.
[15] JOHN L, ANDREW M, PEREIRA FERNANDO C N. Conditional random fields:probabilistic models for segmenting and labeling sequence data[C]//Proceedings of the 18th International Conference on Machine Learning.[S.l.]:Publisher URL,2001.

改进D-LinkNet模型在国产卫星影像云检测中的应用

Application of improved D-LinkNet model in cloud detection of domestic satellite image

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	潘建平, 李鑫, 孙博文, 胡勇, 李明明. 基于注意力密集连接金字塔网络的新增建设用地变化检测[J]. 测绘通报, 2022, 0(3): 41-46,59.
[2]	郁汀, 王铎, 陈钦. 基于伪语义相似度模型的中文地址匹配方法[J]. 测绘通报, 2022, 0(3): 101-106.
[3]	杨景玉, 贾多科, 王阳萍. 基于超像素分割与CRF的高分辨率遥感影像变化检测[J]. 测绘通报, 2022, 0(2): 25-30,49.
[4]	杨勇, 崔丽珍, 郭倩倩, 薛中浩. 煤矿井下基于Attention机制的LSTM地磁定位算法[J]. 测绘通报, 2022, 0(1): 72-78.
[5]	吴永静, 吴锦超, 林超, 窦宝成, 黎珂. 基于深度学习的高分辨率遥感影像光伏用地提取[J]. 测绘通报, 2021, 0(5): 96-101.
[6]	段雅鸣, 张锦水, 朱爽. 基于深度卷积神经网络的云检测方法[J]. 测绘通报, 2021, 0(4): 33-39.
[7]	马林飞, 倪欢, 周子涵. 基于注意力机制的高分遥感图像采石场识别[J]. 测绘通报, 2021, 0(11): 96-100.
[8]	胡建朗, 罗亚荣, 郭迟. 一种用于运动姿态评估的视觉伺服机器人[J]. 测绘通报, 2020, 0(8): 33-38.
[9]	张永宏, 蔡朋艳, 陶润喆, 王剑庚, 田伟. 基于改进U-Net网络的遥感图像云检测[J]. 测绘通报, 2020, 0(3): 17-20,34.
[10]	林晓萍. 基于国产卫星影像的自然资源动态监测[J]. 测绘通报, 2020, 0(11): 28-32.
[11]	刘云峰, 杨珍, 韩骁, 付俊. 国产高分辨率卫星影像云检测方法分析[J]. 测绘通报, 2020, 0(11): 66-70.
[12]	张朕通, 单玉刚, 袁杰. 改进注意力机制的遥感地貌识别算法[J]. 测绘通报, 2020, 0(10): 93-96,100.
[13]	余长慧, 于海威, 张文, 孟令奎. 神经网络支持下的Sentinel-2卫星影像自动云检测[J]. 测绘通报, 2019, 0(8): 39-43.
[14]	殷亚秋, 冷玥, 赵玉灵, 安娜, 鞠星. 面向对象和GURLS结合的高空间分辨率遥感数据云检测[J]. 测绘通报, 2019, 0(5): 109-112,142.
[15]	付华联, 冯杰, 李军, 刘军. 基于随机森林的FY-2G云检测方法[J]. 测绘通报, 2019, 0(3): 61-66.