风云气象卫星影像自动精细云检测

doi:10.13474/j.cnki.11-2246.2019.0384

测绘通报 ›› 2019, Vol. 0 ›› Issue (12): 45-49.doi: 10.13474/j.cnki.11-2246.2019.0384

风云气象卫星影像自动精细云检测

刘军¹, 郑群峰^1,2, 邢秀为³, 陈训来^1,2, 陈潜^1,2, 钱静³

1. 深圳南方强天气研究重点实验室, 广东深圳 518040;
2. 深圳市气象局, 广东深圳 518040;
3. 中国科学院深圳先进技术研究院, 广东深圳 518055

收稿日期:2019-08-03 修回日期:2019-09-18 发布日期:2020-01-03
通讯作者: 陈训来。E-mail:cxlxun@163.com E-mail:cxlxun@163.com
作者简介:刘军(1984-),男,博士,副研究员,主要从事遥感影像分析研究。E-mail:rsliujun@163.com
基金资助:
中国科学院“西部之光”项目（2016-QNXZ-A-5）；国家自然基金项目（9154402）；中国气象局预报员专项（CMAYBY2019081）；广东省气象局重点项目（GRMC2018Z06）；广东省科技厅科技项目（2014A020218014；2016A020223016；2019B020208016）

Automatic and accurate cloud detection for Fengyun meteorological satellite

LIU Jun¹, ZHENG Qunfeng^1,2, XING Xiuwei³, CHEN Xunlai^1,2, CHEN Qian^1,2, QIAN Jing³

1. Shenzhen Key laboratory of Severe Weather in South China, Shenzhen 518040, China;
2. Shenzhen Meteorological Bureau, Shenzhen 518040, China;
3. Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China

Received:2019-08-03 Revised:2019-09-18 Published:2020-01-03

摘要/Abstract

摘要： 抠图技术能够准确细致地检测出前景与背景的差异，但是现有的大多数抠图算法均需事先给出前景与背景的标记，在海量影像处理业务中具有明显的局限性。本文将抠图技术引入风云气象卫星影像云检测中，提出了基于连通区域抠图的自动精细云检测算法。首先对影像的灰度图像进行多种阈值方法二值化，通过投票法集成得到初步二分图；在此基础上计算连通区域，以连通区域的重心为种子点，自动生成连通区域三分图；最后使用闭形式抠图法求解alpha值进而得到精细的云检测结果。将该方法与基于学习和稳健性抠图检测算法进行了对比，试验结果表明，该方法能够较好地检测出多种类型的云，具有更高的准确率。

关键词: 风云气象卫星, 云检测, 连通区域, 集成阈值, 闭形式抠图

Abstract: The matting technique can accurately detect the difference between the foreground and the background, but most of the existing matting algorithms need to give the foreground and background markings in advance, which has obvious limitations in the mass image processing. In this paper, the matting technology is introduced into the cloud detection of Fengyun meteorological satellite images, and an automatic fine cloud detection algorithm based on connected regions is proposed. Firstly, the gray visible image is binarized by ensemble threshold methods, and the preliminary bipartite map is obtained by the voting method. On this basis, the connected regions are calculated, and the center of gravity of the connected regions are taken as the seed point, and then triple map based on the connected regions is automatically generated. Finally, the closed-form matting algorithm is used to solve the alpha value to obtain fine cloud detection results. The proposed method is compared with the learning and robust matting-based cloud detection algorithms. The experiments show that the proposed method can automatically detect multiple types of clouds better and has higher accuracy.

Key words: Fengyun meteorological satellite, cloud detection, ensemble threshold, connected region, close-form matting

中图分类号:

P237

刘军, 郑群峰, 邢秀为, 陈训来, 陈潜, 钱静. 风云气象卫星影像自动精细云检测[J]. 测绘通报, 2019, 0(12): 45-49.

LIU Jun, ZHENG Qunfeng, XING Xiuwei, CHEN Xunlai, CHEN Qian, QIAN Jing. Automatic and accurate cloud detection for Fengyun meteorological satellite[J]. Bulletin of Surveying and Mapping, 2019, 0(12): 45-49.

参考文献

[1] 付华联,冯杰,李军,等.基于随机森林的FY-2G云检测方法[J].测绘通报,2019(3):61-66.
[2] 武艳,银燕,师春香,等.基于动态阈值法的NOAA系列卫星云检测结果检验[J].高原气象,2012(3):745-751.
[3] 杨俊,吕伟涛,马颖,等.基于自适应阈值的地基云自动检测方法[J].应用气象学报,2009,20(6):713-721.
[4] 殷亚秋,冷玥,赵玉灵,等.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(5):109-112.
[5] 董志鹏,王密,李德仁,等.利用对象光谱与纹理实现高分辨率遥感影像云检测方法[J].测绘学报,2018,47(7):996-1006.
[6] 徐启恒,黄滢冰,陈洋.结合超像素和卷积神经网络的国产高分辨率遥感影像云检测方法[J].测绘通报,2019(1):50-55.
[7] 高军,荆益国.基于全卷积神经网络的卫星遥感图像云检测方法[J].红外技术,2019,41(7):607-615.
[8] BERMAN A, DARDOURIAN A, VLAHOS P. Method for removing from an image the background surrounding a selected object:U S, 6134346[P]. 2000-01-03.
[9] RUZON M, TOMASI C. Alpha estimation in natural images[C]//IEEE Conference on Computer Vision and Pattern Recognition (CVPR). South Carolina:[s.n.], 2000:18-25
[10] SHAHRIAN E, RAJAN D. Weighted color and texture sample selection for image matting[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos:IEEE Computer Society Press, 2012:718-726.
[11] ZHENG Y, KAMBHAMETTU C. Learning based digital matting[C]//IEEE 12th International Conference on Computer Vision.[S.l.]:IEEE, 2009.
[12] WANG J, COHEN M. Optimized color sampling for robust matting[C]//2007 IEEE Conference on Computer Vision and Pattern Recognition IEEE Computer Society.[S.l.]:IEEE, 2007.
[13] 林生佑,石教英.基于感知颜色空间的自然图像抠图[J]. 计算机辅助设计与图形学学报,2005,17(5):915-920.
[14] HE B, WANG G J, RUAN Z W, et al. Local matting based on sample-pair propagation and iterative refinement[C]//IEEE Conference on Computer Vision and Pattern Recognition. Los Alamitos:IEEE Computer Society Press, 2012:285-288.
[15] 侯金鑫,张军.改进的Closed-Form Solution方法进行前景物体运动模糊抠图[J].计算机应用研究,2013,30(5):1554-1557.
[16] DONG W, XIAO S, QU J. Matting model-based algorithm for remote sensing image fusion[J]. Journal of Applied Remote Sensing, 2018, 12(1):1-11.
[17] HENNEGHAN A M, PALESH O, HARRISON M, et al. Identifying cytokine predictors of cognitive functioning in breast cancer survivors up to 10 years post chemotherapy using machine learning[J]. Journal of neuroimmunology. 2018, 320:38-47.
[18] FU H, SHEN Y, LIU J, et al. Cloud detection for FY meteorology satellite based on ensemble thresholds and random forests approach[J]. Remote Sensing. 2019, 11(1):44.

风云气象卫星影像自动精细云检测

Automatic and accurate cloud detection for Fengyun meteorological satellite

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

[1]	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.
[2]	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.
[3]	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.
[4]	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.
[5]	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.
[6]	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.
[7]	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.
[8]	徐启恒, 黄滢冰, 陈洋. 结合超像素和卷积神经网络的国产高分辨率遥感影像云检测方法[J]. 测绘通报, 2019, 0(1): 50-55.
[9]	李爱勤, 王环东, 王静怡, 胡翔云. 高分辨率遥感影像中云和似云目标的自动区分[J]. 测绘通报, 2017, 0(6): 31-35.
[10]	陈翠婵, 黄国森, 王越, 钟静. 含云卫星影像配准算法研究[J]. 测绘通报, 2016, 0(10): 81-84.