[1]杨 帆,赵增鹏*,张 磊.基于高斯混合模型的遥感影像云检测技术[J].南京林业大学学报(自然科学版),2018,42(04):134-140.[doi:10.3969/j.issn.1000-2006.201708009]
 YANG Fan,ZHAO Zengpeng*,ZHANG Lei.Cloud detection technology based on Gaussian mixture model for high-resolution remote sensing imagery[J].Journal of Nanjing Forestry University(Natural Science Edition),2018,42(04):134-140.[doi:10.3969/j.issn.1000-2006.201708009]
点击复制

基于高斯混合模型的遥感影像云检测技术
分享到:

《南京林业大学学报(自然科学版)》[ISSN:1000-2006/CN:32-1161/S]

卷:
42
期数:
2018年04期
页码:
134-140
栏目:
研究论文
出版日期:
2018-07-12

文章信息/Info

Title:
Cloud detection technology based on Gaussian mixture model for high-resolution remote sensing imagery
文章编号:
1000-2006(2018)04-0134-07
作者:
杨 帆赵增鹏*张 磊
辽宁工程技术大学测绘与地理科学学院,辽宁 阜新 123000
Author(s):
YANG Fan ZHAO Zengpeng* ZHANG Lei
College of Mapping and Geographic Sciences, Liaoning Technical University, Fuxin 123000, China
关键词:
遥感影像 云检测 Otsu阈值分割 高斯混合模型 云区形态学处理
Keywords:
Keywords:remote sensing image cloud detection Otsu threshold Gaussian mixture model cloud morphology processing
分类号:
P237.4
DOI:
10.3969/j.issn.1000-2006.201708009
文献标志码:
A
摘要:
【目的】高分辨率遥感影像云检测技术一直是遥感影像处理亟待解决的难题,尤其是边缘薄云和散云的检测。针对高分辨率遥感影像的成像特点,利用形态学运算、多边形简化技术,实现含云影像的准确提取。【方法】首先对影像进行高斯低通滤波平滑,取得一致均匀的明暗效果; 然后将影像分为多云、少云、无云3种情况,对多云影像采用Otsu阈值分割,对少云影像采用高斯混合模型进行阈值分割; 最后对云区进行形态学处理得到最终云区。【结果】高分辨遥感影像云检测方法目视效果较好,可有效提高云检测精度,该方法准确率为98.60%,查全率在90%左右,错误率约为2.58%,可以较为准确地检测出厚云、薄云、散云,同时还可有效地减少对房屋、道路、裸地的误判。【结论】基于Otsu阈值分割和高斯混合模型的高分辨率遥感影像云检测技术算法复杂度适中,计算量小,运算速度快,检测精度高,适用性广。
Abstract:
Abstract: 【Objective】 Developing cloud detection technology for high-resolution remote-sensing images is difficult, especially for thin edge and scattered clouds. We used morphological operations and polygon simplification techniques to accurately extract cloud-containing, high-resolution remote-sensing images.【Method】First, the Gaussian low-pass filter was used to smooth the image and create uniform shading. The image was then divided into three categories: cloudy, partly cloudy and cloudless. The Otsu threshold method was used on cloudy images, and Gaussian mixture model segmentation was used on partly cloudy images. Finally, the cloud area was morphologically processed to determine the final cloud area. 【Result】The high-resolution remote-sensing image cloud-detection algorithm based on Otsu threshold segmentation and Gaussian mixture model has good visual effect and can effectively improve the accuracy of cloud detection. The accuracy rate is 98.60%, recall rate of the method is approximately 90%, and the error rate is approximately 2.58%. It can accurately detect thick, thin and scattered clouds, and can also effectively reduce the misidentification of houses, roads and bare land. 【Conclusion】The high-resolution remote-sensing image cloud-detection algorithm based on Otsu threshold segmentation and Gaussian mixture model is moderately complex, and has a small computation size, fast operation speed, high-precision detection and wide applicability.

参考文献/References:

[1] 潘红播,张过,唐新明,等.资源三号测绘卫星传感器校正产品几何模型[J].测绘学报,2013,42(4):516-522. PAN H B, ZHANG G, TANG X M, et al. The geometrical model of sensor corrected products for ZY-3 Satellite[J]. Acta Geodaetica et Cartographica Sinica, 2013, 42(4):516-522.
[2] 陈荣元,郑晨,王雷光,等. MRF框架下的区域增长模型在城镇识别中的应用[J]. 测绘学报,2011,40(2):163-168. CHEN R Y, ZHEGN C, WANG L G, et al. A region growing model under the framework of MRF for urban detection[J]. Acta Geodaetica et Cartographica Sinica, 2011,40(2):163-168.
[3] CHEN G, DONG C E, WANG L G, et al. Support vector machines for cloud detection over ice-snow areas[J].Geo-spatial Information Science,2007,10(2):117-120.
[4] 梁栋,孔颉,胡根生,等.基于支持向量机的遥感影像厚云及云阴影去除[J].测绘学报,2012,41(2):225-231,238. LIANG D, KONG J, HU G S, et al. The Removal of thick cloud and cloud shadow of remote sensing image based on support vector machine[J]. Acta Geodaetica et Cartographica Sinica, 2012,41(2):225-231,238.
[5] 陈奋,闫冬梅,赵忠明.基于无抽样小波的遥感影像薄云监测与去除[J].武汉大学学报(信息科学版),2007,32(1):71-74. CHEN F, YAN D M, ZHAO Z M. Haze detection and removal in remote sensing images based on undecimated wavelet transform[J].Geomatics and Information Science of Wuhan University, 2007,32(1):71-74.
[6] 刘海波,沈晶,岳振勋,等.Visual C++数字图像处理技术详解[M].北京:机械工业出版社, 2014.
[7] 姒绍辉,胡伏原,顾亚军,等. 一种基于不规则区域的高斯滤波去噪算法[J]. 计算机科学,2014,41(11):313-316. DOI: 10.11896/j.issn.1002-137X.2014.11.062. SI S H, HU F Y, GU Y J, et al. Improved denoising algorithm based on non-regular area Gaussian filtering[J]. Computer Science, 2014,41(11):313-316.
[8] 陈万海,赵春晖. 基于高斯低通滤波的超光谱遥感图像分类研究[J]. 黑龙江大学自然科学学报,2007,24(6):751-756. DOI: 10.13482/j.issn1001-7011.2007.06.032. CHEN W H, ZHAO C H. Hyperspectral remote sensing classification based on Gaussian low pass filter[J]. Journal of Natural Science of Hei Long Jiang University, 2007,24(6):751-756.
[9] XIAN J P, ZHENG X W, SUN L, et al. Image segmentation based on 2D OTSU and simplified swarm optimization[R]. 2016 International Conference on Machine Learning and Cybernetics(ICMLC), 2016.
[10] 邓小炼,王星,艾思敏,等. 奇异值分解和阈值分割的遥感自适应变化检测[J]. 测绘科学,2016,41(8):38-42. DOI: 10.16251/J.CNKI.1009-2307.2016.08.008. DENG X L, WANG X, AI S M, et al. Adaptive change detective algorithm of remote sensing images based on SVD and OTSU[J]. Science of Surveying and Mapping, 2016,41(8):38-42.
[11] 许凯,秦昆,刘修国,等. 高斯混合模型云变换算法及其在图像分割中的应用[J]. 武汉大学学报(信息科学版),2013,38(10):1163-1166,1183. XU K, QIN K, LIU X G, et al. Cloud transformation method based on Gaussian mixed model and its application to image segmentation[J]. Geomatics and Information Science of Wuhan University, 2013,38(10):1163-1166,1183.
[12] RAFAEL C G, RICHARD E W, STEVEN L E. Digital image processing using MATLAB[M].Beijing:Publishing House of Electronics Industry,2013.
[13] 禹铭月,王卫安. 多边形形状简化及其质量评价[J]. 测绘与空间地理信息,2011,34(6):152-155. YU M Y, WANG W A. Polygonsimplification and quality evaluation[J]. Geomatics & Spatial Information Technology, 2011,34(6):152-155.

相似文献/References:

[1]何柏华,李春干.基于DEM与SPOT5的小班边界自动提取[J].南京林业大学学报(自然科学版),2010,34(05):047.[doi:10.3969/j.jssn.1000-2006.2010.05.010]
 HE Bai hua,LI Chun gan.Boundary autoextracting of forest subcompartment based on DEM and SPOT5[J].Journal of Nanjing Forestry University(Natural Science Edition),2010,34(04):047.[doi:10.3969/j.jssn.1000-2006.2010.05.010]
[2]史云松,史玉峰*.基于核模糊聚类的遥感影像分类[J].南京林业大学学报(自然科学版),2010,34(06):164.[doi:10.3969/j.jssn.1000-2006.2010.06.036]
 SHI Yun song,SHI Yu feng*.Classification of remote sensing image based on kernel fuzzy Cmeans[J].Journal of Nanjing Forestry University(Natural Science Edition),2010,34(04):164.[doi:10.3969/j.jssn.1000-2006.2010.06.036]

备注/Memo

备注/Memo:
基金项目:辽宁省教育厅重点实验室基础研究项目(LJZS001); 卫星测绘技术与应用国家测绘地理信息局重点实验室经费资助项目(KLSMTA-201707) 第一作者:杨帆(yangfan2008beijing@126.com),教授,博士。*通信作者:赵增鹏(1300714651@qq.com)。
更新日期/Last Update: 2018-07-27