Please wait a minute...
img

官方微信

遥感技术与应用  2019, Vol. 34 Issue (6): 1252-1260    DOI: 10.11873/j.issn.1004-0323.2019.6.1252
数据与图像处理     
集成特征分量的高分二号影像阴影检测
李强(),冯德俊(),瑚敏君,伍燚垚,杨历辉
西南交通大学 地球科学与环境工程学院,四川 成都 611730
Shadow Detection of Integrated Characteristic Components for GF-2 Image
Qiang Li(),Dejun Feng(),Minjun Hu,Yiyao Wu,Lihui Yang
Faculty of Geosciences and Environmental Engineering, Southwest Jiaotong University, Chengdu 611730, China
 全文: PDF(3035 KB)   HTML
摘要:

针对高分辨率遥感影像中阴影检测精度易受水体、植被等因素干扰的问题,通过分析高分二号影像中典型地物的光谱特征,构建了一种集成特征分量与面向对象分类相结合的阴影检测方法。构建的特征分量包括:主成分第一分量PC1、亮度分量I、归一化差分植被指数NDVI及水体指数WI。将各特征分量进行归一化处理,建立包含波段均值、标准差等特征的规则集,对影像的I和PC1分量进行多尺度分割 ,结合面向对象的方法进行阴影检测。选取不同区域遥感影像进行实验,实验结果表明:与传统基于像素的阴影提取方法相比,该方法提取出的阴影斑块完整,且能有效地减弱水体和植被的影响。

关键词: 阴影检测特征分量面向对象分类GF-2影像    
Abstract:

The shadow detection accuracy in the high-resolution remote sensing images is easily disturbed by water, vegetation and so on. This study proposed a shadow detection method based on object-oriented method and established characteristic components by analyzing the spectral characteristics of typical features in GF-2 satellite images.The following components were constructed to detect shadow information: first principal component (PC1), brightness component I, Normalized Difference Vegetation Index (NDVI) and Water Index (WI). And then, we normalized each characteristic component to establish a rule set containing features such as band mean, standard deviation. Brightness I and PC1 were chosen as the main data source for multi-resolution segmentation, at last, performed object-oriented method on the segmented images to detect shadow. Selected different areas of GF-2 images for the proposed method, and experimental results show that the proposed method could extract complete shadow patches and effectively reduce the influence of water bodies and vegetation compared with pixel-based method.

Key words: Shadow detection    Characteristic components    Object-oriented classification    GF-2
收稿日期: 2018-08-21 出版日期: 2020-03-23
ZTFLH:  TP751  
基金资助: 国家重点研发计划项目(2016YFC0803105);四川省科技厅重点研发项目“自然资源资产评价关键技术研究及应用示范”(2017)资助
通讯作者: 冯德俊     E-mail: qiangli8898@gmail.com;fengdj@126.com
作者简介: 李 强(1990-),男,河南永城人,硕士研究生,主要从事遥感图像处理研究。E?mail:qiangli8898@gmail.com
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
李强
冯德俊
瑚敏君
伍燚垚
杨历辉

引用本文:

李强,冯德俊,瑚敏君,伍燚垚,杨历辉. 集成特征分量的高分二号影像阴影检测[J]. 遥感技术与应用, 2019, 34(6): 1252-1260.

Qiang Li,Dejun Feng,Minjun Hu,Yiyao Wu,Lihui Yang. Shadow Detection of Integrated Characteristic Components for GF-2 Image. Remote Sensing Technology and Application, 2019, 34(6): 1252-1260.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2019.6.1252        http://www.rsta.ac.cn/CN/Y2019/V34/I6/1252

统计值波段阴影水体植被深色地物
均值方差均值方差均值方差均值方差
341.7112.11387.092.82457.4033.82415.366.21
绿200.6110.37263.563.28313.1625.69267.275.51
131.6910.94171.284.08225.9521.01209.674.62
近红外80.4710.9763.263.27277.8428.06175.656.11
表1  阴影及典型地物光谱值
图1  阴影及相关典型地类的光谱曲线
图2  PC1分量亮度直方图
图3  I分量亮度直方图
图4  NDVI分量亮度直方图
图5  阴影与水体在各波段亮度直方图
图6  WI分量亮度直方图
图7  WI分量采样区域阴影和水体亮度直方图
图8  阴影检测流程图
图9  阴影检测规则集
图10  实验区一、二阴影提取结果
实验区阴影像元个数精度/%
本文方法最大似然法人工提取本文方法最大似然法
实验区一21 84923 75920 44093.11%83.76%
实验区二65 09245 67260 43192.29%75.58%
表2  阴影提取结果精度对比
1 Salvador E, Cavallaro A, Ebrahimi T. Cast Shadow Segmentation Using Invariant Color Features[J]. Compater vision and Image Understanding, 2004, 95(2):238-259.
2 Nakajima T, Tao G, Yasuoka Y. Simulated Recovery of Information in Shadow Areas on IKONOS Image by Combing ALS Data[C]∥Proceedings of Asian Conference on Remote sensing, Kathmandu, 2002:25-29.
3 Guo Haitao, Xu Qqing, Zhang Baoming. Shadow Extraction of Building based on Multiple Constraints[J]. Editorial Board of Geomatics & Information Science of Wuhan University, 2005, 30(12):1059-1062.
3 郭海涛, 徐青, 张保明. 多重约束下的建筑物阴影提取[J]. 武汉大学学报(信息科学版), 2005, 30(12):1059-1062.
4 Arévalo V, González J, Ambrosio G. Shadow Detection in Colour High-resolution Satellite Images[J]. International Journal of Remote Sensing, 2008, 29(7):1945-1963.
5 Tsai V J D. A Comparative Study on Shadow Compensation of Color Aerial Images in Invariant Color Models[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(6):1661-1671.
6 Wang Junli,Wang Shugen. A Shadow Detection Method of Color Image based on RGB Color Space[J]. Information Technology, 2002(12):7-8.
6 王军利, 王树根. 一种基于RGB彩色空间的影像阴影检测方法[J]. 信息技术, 2002(12):7-8.
7 Guo Jianhong,Tian Qingjiu. A Shadow Detection and Removal Method for IKONOS Images[J]. Remote Sensing Information, 2004,19(4):32-34.
7 虢建宏, 田庆久. 一种IKONOS影像阴影检测与去除的方法[J]. 遥感信息, 2004,19(4):32-34.
8 Wang Yue,Wang Shugen. Detection and Compensation of Shadows in High Resolution Remote Sensing Images Using PCA[J]. Journal of Applied Sciences, 2010, 28(2):136-141.
8 王玥, 王树根. 高分辨率遥感影像阴影检测与补偿的主成分分析方法[J]. 应用科学学报, 2010, 28(2):136-141.
9 Liu Hui, Xie Tianwen. Study on Shadow Detection in High Resolution Remote Sensing Image based of PCA and HIS Model[J]. Remote Sensing Technology and Application, 2013, 28(1):78-84.
9 刘辉, 谢天文. 基于PCA与HIS模型的高分辨率遥感影像阴影检测研究[J]. 遥感技术与应用, 2013, 28(1):78-84.
10 Liu Xinyan, Sun Lin, Yang Yikun. Cloud and Cloud Shadow Detection Algorithm for Gaofen-4 Satellite Data[J]. Acta Optica Sinica, 2019, 39(1):446-457.
10 刘心燕, 孙林, 杨以坤, 等. 高分四号卫星数据云和云阴影检测算法[J]. 光学学报, 2019, 39(1):446-457.
11 Yue Zhaoxi, Zhang Yongjun, Duan Yansong, et al. DEM Assisted Shadow Detection and Topography Correction of Satellite Remote Sensing Images in Mountainous Area[J]. Acta Geodaetica et Cartographica Sinica, 2018, 47(1):113-122.
11 岳照溪, 张永军, 段延松, 等. DEM辅助的卫星光学遥感影像山体阴影检测与地形辐射校正[J].测绘学报,2018, 47(1):113-122.
12 Yang Xingwang, Yang Shuwen, Liu Zhengjun, et al. Shadow Detection for Urban Tall Standing Objects based on ZY-3 Satellite Imagery[J]. Science of Surveying and Mapping, 2015, 40(9):98-101.
12 杨兴旺, 杨树文, 刘正军,等. 资源三号影像中城市高大地物阴影检测方法[J]. 测绘科学, 2015, 40(9):98-101.
13 Duan Guangyao, Gong Huili, Li Xiaojuan, et al. Shadow Extraction based on Characteristic Components and Object -oriented Method for High-resolution Images[J]. Journal of Remote Sensing, 2014, 18(4):760-770.
13 段光耀, 宫辉力, 李小娟,等. 结合特征分量构建和面向对象方法提取高分辨率卫星影像阴影[J]. 遥感学报, 2014, 18(4):760-770.
14 Zhang Xianpeng, Chen Fan, He Hongjie. Shadow Detection in High Resolution Remote Sensing Images Using Multiple Features[J]. Acta Automatica Sinica, 2016, 42(2):290-298.
14 张先鹏, 陈帆, 和红杰. 结合多种特征的高分辨率遥感影像阴影检测[J]. 自动化学报, 2016, 42(2):290-298.
15 Dong Yue, Feng Huajun, Xu Zhihai, et al. Attention Res-Unet: An Efficient Shadow Detection Algorithm[J]. Journal of Zhejiang University (Engineering Science Edition), 2019, 53(2):373-381.
15 董月, 冯华君, 徐之海, 等. Attention Res-Unet:一种高效阴影检测算法[J]. 浙江大学学报(工学版), 2019, 53(2):373-381.
16 Meng Fanlian.Multimedia Retriveal based on the Statistical Analysis of Heterogeneous Characteristics[D]. Wuhan: Wuhan University of Science and Technology, 2010.
16 孟凡炼. 基于异构特征统计分析的跨媒体检索研究[D].武汉:武汉科技大学, 2010.
17 Yang Meng,Yang Shuwen,Yong Wanling, et al. Multiscale Shadow Segmentation Method based on Characteristic Component [J]. Remote Sensing Information2017, 32(1):109-114.
17 杨猛, 杨树文, 雍万铃, 等. 集成特征分量的阴影多尺度分割方法[J]. 遥感信息, 2017, 32(1):109-114.
18 Mcfeeters S K. The Use of the Normalized Difference Water Index (NDWI) in the Delineation of Open Water Features[J]. International Journal of Remote Sensing, 1996, 17(7):1425-1432.
19 Zhang Heng. Research on Buildings Shadow Detection Method and Height Inversion with High Resolution Sensed Image[D]. Chengdu: Southwest Jiaotong University, 2017.
19 张珩. 高分影像建筑物阴影检测方法及其高度反演研究[D].成都:西南交通大学, 2017.
20 Tan Qulin,Liu Zhengjun,Shen Wei,et al. An Algorithm for Object-oriented Multi-scale Remote Sensing Image Segmentation[J]. Journal of Beijing Jiaotong University, 2007, 31(4):111-114.
20 谭衢霖, 刘正军, 沈伟,等. 一种面向对象的遥感影像多尺度分割方法[J]. 北京交通大学学报, 2007, 31(4):111-114.
21 Shi Peirong, Chen Yongfu, Liu Hua, et al. Parameters of Multi-segmentation based on Segmentation Evaluation Function[J]. Remote Sensing Technology and Application, 2018,33(4):628-637.
21 施佩荣,陈永富,刘华,等. 基于分割评价函数的多尺度分割参数的选择[J]. 遥感技术与应用, 2018, 33(4):628-637.
22 Zhang Jun,Wang Yunjia,Li Yan,et al. An Object-oriented Optimal Scale Choice Method for High Spatial Resolution Remote Sensing Image[J]. Science and Technology Review, 2009, 27(21):91-94.
22 张俊, 汪云甲, 李妍,等. 一种面向对象的高分辨率影像最优分割尺度选择算法[J]. 科技导报, 2009, 27(21):91-94.
[1] 徐凡, 张雪红, 石玉立. 基于激光雷达和航拍影像的城市地物分类研究[J]. 遥感技术与应用, 2019, 34(2): 253-262.
[2] 江东,陈帅,丁方宇,付晶莹,郝蒙蒙. 基于面向对象的遥感影像分类研究——以河北省柏乡县为例[J]. 遥感技术与应用, 2018, 33(1): 143-150.
[3] 朱钟正,陈玉福,朱文泉,郑周涛. 适用于多目标遥感自动解译的最佳专题指数筛选[J]. 遥感技术与应用, 2017, 32(3): 564-574.
[4] 满卫东,李春景,王宗明,贾明明,毛德华,刘明月,路春燕. 基于面向对象分类方法的乌苏里江流域中俄跨境区域湿地景观动态研究[J]. 遥感技术与应用, 2016, 31(2): 378-387.
[5] 徐菲楠,祁元,王建华,张金龙. 面向对象的黑河下游河岸林植被覆盖信息分类[J]. 遥感技术与应用, 2015, 30(5): 996-1005.
[6] 白晓燕,陈晓宏,王兆礼. 基于面向对象分类的土地利用信息提取及其时空变化研究[J]. 遥感技术与应用, 2015, 30(4): 798-809.
[7] 陈阳,范建容,文学虎,曹伟超,王蕾. 基于时空数据融合模型的TM影像云去除方法研究[J]. 遥感技术与应用, 2015, 30(2): 312-320.
[8] 邓琳,邓明镜,张力树. 高分辨率遥感影像阴影检测与补偿方法优化[J]. 遥感技术与应用, 2015, 30(2): 277-284.
[9] 余婧峰,余银普. 规则化城市建筑物阴影提取及校正模型研究[J]. 遥感技术与应用, 2014, 29(1): 172-175.
[10] 王少伟,张晓祥,杨晓英. 太湖湖滨敏感区的土地利用遥感分类研究[J]. 遥感技术与应用, 2014, 29(1): 114-121.
[11] 丁辉,张茂省,李林. 基于多特征面向对象区域滑坡现象识别[J]. 遥感技术与应用, 2013, 28(6): 1107-1113.
[12] 王贺,陈劲松,余晓敏. HJ数据的LBV变换及其在面向对象分类中的应用[J]. 遥感技术与应用, 2013, 28(6): 1020-1026.
[13] 刘 辉,谢天文. 基于PCA与HIS模型的高分辨率遥感影像阴影检测研究[J]. 遥感技术与应用, 2013, 28(1): 78-84.
[14] 陈燕丽,莫伟华,莫建飞,王君华,钟仕全. 基于面向对象分类的南方水稻种植面积提取方法[J]. 遥感技术与应用, 2011, 26(2): 163-168.
[15] 阿依提拉·吾加布都拉, 塔西甫拉提·特依拜, 古丽加玛丽·吾不力. 基于面向对象方法的遥感土壤盐渍化信息监测——以渭干河—库车河三角洲绿洲为例[J]. 遥感技术与应用, 2010, 25(3): 373-378.