Please wait a minute...
img

官方微信

遥感技术与应用  2020, Vol. 35 Issue (4): 775-785    DOI: 10.11873/j.issn.1004-0323.2020.4.0775
甘肃遥感学会专栏     
基于面向对象的青海湖环湖区居民地信息自动化提取
连喜红1,2(),祁元1(),王宏伟1,张金龙1,杨瑞1,2
1.中国科学院西北生态环境资源研究院,甘肃 兰州 730000
2.中国科学院大学,北京 100049
Automatic Extraction of Residential Information based on Object-oriented in the Areas around the Qinghai Lake
Xihong Lian1,2(),Yuan Qi1(),Hongwei Wang1,Jinlong Zhang1,Rui Yang1,2
1.Northwest Institute of Eco-Environment and Resources, Chinese Academy of Sciences, Lanzhou 730000, China
2.University of Chinese Academy of Sciences, Beijing 100049, China
 全文: PDF(7961 KB)   HTML
摘要:

居民地的空间格局和密度直接反映着区域人类活动的强弱程度,影响着区域人地系统演变和生态环境可持续发展。基于高分辨率卫星遥感影像数据,提出了一种面向对象的青海湖环湖区居民地信息自动化提取方法。首先,利用尺度集理论对高分辨率卫星遥感影像进行多尺度分割,获取不同尺度的分割对象;其次,通过机器学习算法集对分割对象的自定义特征、光谱特征、几何特征和纹理特征进行训练,选取最优自动分类算法;最后,利用最优自动分类算法提取青海湖环湖区城镇居民地和农村居民地信息。采用平均召回率、平均准确率和平均F值评价指标对分类结果进行精度评价,其中,城镇居民地各评价指标均在93%以上,农村居民地各评价指标均在86%以上。结果表明:该方法提取城镇居民地和农村居民地总体精度较高,在大面积人类活动精细化监测中具有较好的科学意义和应用价值。

关键词: 高分辨率遥感影像面向对象居民地尺度集模型机器学习算法集    
Abstract:

The spatial pattern and density of residential areas directly reflect the intensity of regional human activities, and affect the evolution of a regional human-land system and the sustainable development of ecological environment. In this study, we proposed an objected-oriented automatic extraction method, which based on the high spatial resolution satellite remote sensing image data in the surrounding area of Qinghai lake watershed. Firstly, multi-scale segmentation of high-resolution satellite remote sensing image was carried out by using the scale sets theory to obtain segmentation objects in different scales. Secondly, the custom, spectral, geometric and texture features of the sample attributes were trained through the sets of machine learning algorithms, and the optimal automatic classification algorithm was selected. Finally, the optimal automatic classification algorithm was used to extract the information of urban and rural residential areas in the surrounding area of Qinghai lake watershed. The average recall rate, accuracy rate and F value were used to evaluate the classification results. Accuracy evaluation indexes of urban residential areas were more than 93%, and those of rural residential areas were more than 86%. The results show that this method has higher overall precision when extracting urban residential areas and rural residential areas, and has better scientific significance and application value in fine monitoring of human activities in large areas.

Key words: High resolution remote sensing image    Object-oriented    Residential information    The scale sets    Machine learning algorithm set
收稿日期: 2019-09-17 出版日期: 2020-09-15
ZTFLH:  TP75  
基金资助: 中国科学院A类战略性先导科技专项资助(XDA20100101)
通讯作者: 祁元     E-mail: lianxh@lzb.ac.cn;qiyuan@lzb.ac.cn
作者简介: 连喜红(1993-),男,甘肃渭源人,硕士研究生,主要从事生态遥感研究。E?mail: lianxh@lzb.ac.cn
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  
连喜红
祁元
王宏伟
张金龙
杨瑞

引用本文:

连喜红,祁元,王宏伟,张金龙,杨瑞. 基于面向对象的青海湖环湖区居民地信息自动化提取[J]. 遥感技术与应用, 2020, 35(4): 775-785.

Xihong Lian,Yuan Qi,Hongwei Wang,Jinlong Zhang,Rui Yang. Automatic Extraction of Residential Information based on Object-oriented in the Areas around the Qinghai Lake. Remote Sensing Technology and Application, 2020, 35(4): 775-785.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2020.4.0775        http://www.rsta.ac.cn/CN/Y2020/V35/I4/775

图1  研究区位置与地势图
影像名称成像时间行列号云量
GF1_PMS1_E99.1_N37.2_20170813_L1A0002539236.tif2017081393/294%
GF1_PMS1_E101.2_N36.4_20171005_L1A0002653985.tif2017100595/254%
GF1_PMS2_E100.3_N37.7_20170527_L1A0002384098.tif2017052792/2711%
GF2_PMS1_E100.5_N37.2_20171013_L1A0002678101.tif20171013146/425%
GF2_PMS1_E100.5_N37.4_20171013_L1A0002678097.tif20171013145/421%
GF2_PMS1_E100.6_N37.6_20171013_L1A0002678096.tif20171013145/423%
GF2_PMS2_E100.3_N37.4_20170810_L1A0002534662.tif20170810145/434%
GF2_PMS2_E100.5_N36.7_20170805_L1A0002526723.tif20170805147/429%
GF2_PMS2_E100.7_N37.2_20171013_L1A0002672923.tif20171013146/417%
GF2_PMS2_E100.7_N37.4_20171013_L1A0002672921.tif20171013145/4112%
ZY3_TLC_E99.8_N36.6_20171011_L1A0003817439.tif20171011133/410%
ZY3_TLC_E99.9_N37.0_20171011_L1A0003817438.tif20171011132/410%
ZY3_TLC_E100.0_N37.4_20171011_L1A0003817437.tif20171011131/410%
ZY3_TLC_E100.1_N36.6_20170625_L1A0003746917.tif20170625133/4018%
ZY3_TLC_E100.8_N36.6_20170710_L1A0003748580.tif20170710133/381%
ZY3_TLC_E100.9_N37.0_20170710_L1A0003748579.tif20170710132/383%
ZY302_PMS_E98.8_N37.4_20170707_L1A0000156704.tif20170707131/447%
ZY302_PMS_E100.4_N37.0_20171127_L1A0000217243.tif20171127132/390%
ZY302_TMS_E99.5_N37.0_20170717_L1A0000160059.tif20170717132/410%
ZY302_TMS_E100.3_N36.6_20171127_L1A0000217279.tif20171127133/390%
ZY302_TMS_E100.4_N37.0_20170529_L1A0000139947.tif20170529132/398%
表1  高分辨率遥感影像数据列表
图2  技术流程图
一级特征二级特征
光谱特征亮度、均值(1,2,3,4)、最大差异、标准差(1,2,3,4)
几何特征

面积、长度、长宽比、非对称性、

紧致性、密度、椭圆拟合、主要方向、

形状指数、矩形拟合

纹理特征

GLCM 同质性、GLCM 反差、GLCM 差异性、GLCM熵、

GLCM 均值、GLCM 相关性、GLDV 熵、

GLDV均值、

DLDV 反差、GLDV 相关性、GLDV 同质性、

GLDV 差异性

自定义特征

归一化植被指数、归一化水体指数、

土壤调节植被指数、植被覆盖度

表2  输出特征
图3  多尺度层次结构(GF-1影像)
图4  分割结果对比分析(GF-2影像)(a)多尺度分割(ESP) (b)多层次多尺度分割(ESP2) (c)尺度集最优尺度
图5  多层次多尺度构架
图6  人工解译及提取结果细部
图7  居民地精度评定
图8  环湖区居民地提取结果
1 Braat L C, de Groo R. The Ecosystem Services Agenda: Bridging the Worlds of Natural Science and Economics, Conservation and Development, and Public and Private Policy[J]. Ecosystem Services, 2012, 1(1): 4-15.
2 Tan Fanglin, Huang Li, Pan Hui, et al. Investigation on Human Activities Condition in Wetlands of the Zhang Jiang River Estuary, Fujian Province[J]. Wetland Science, 2006, 4(3): 198-203.
2 谭芳林,黄丽,潘辉,等.福建漳江口湿地人类活动状况调查[J].湿地科学,2006,4(3):198-203.
3 Li Xiangyun, Wang Lixin, Zhang Yushu. Analysis of Roles of Human Activities in Land Desertification in Arid Area of Northwest China[J]. Scientia Geographica Sinica, 2004, 24(1): 68-75.
3 李香云,王立新,章予舒.西北干旱区土地荒漠化中人类活动作用及其指标选择[J].地理科学, 2004, 24(1):68-75.
4 Agapiou A, Papadopoulos N, Sarris A. Detection of Olive Oil Mill Waste (OOMW) Disposal Areas Using High Resolution GeoEye's OrbView-3 and Google Earth Images[J]. Open Geosciences, 2016, 8(1): 700-710.
5 Zeng Y, Wang S, Zhao T, et al. An Application of Tree Species Classification Using High-resolution Remote Sensing Image based on the Rough Set Theory[J]. Multimedia Tools and Applications, 2016, 76(21): 22999–23015.
6 Wu Yiquan, Tao Feixiang, Cao Zhaoqing. Remote Sensing Image Classification based on Log-Gabor Wavelet and Krawtchouk Moments[J]. Geomatics and Information Science of Wuhan University, 2016, 41(7): 861-867.
6 吴一全, 陶飞翔,曹照清. 基于Log-Gabor小波和Krawtchouk矩的遥感图像分类[J]. 武汉大学学报·信息科版, 2016, 41(7): 861-867.
7 Lu Chen, Yang Xiaomei, Wang Zhihua. Supervised Dense Rural Residential Extraction from High-resolution Remote Sensing Images based on Automatically Augmentation of Training Samples[J]. Journal of Geo-Information Science, 2018, 20(9): 1306-1315.
7 陆尘,杨晓梅,王志华.基于样本自动扩充的街区式农村居民地遥感提取方法[J].地球信息科学学报, 2018, 20(9): 1306-1315.
8 Qian Y, Zhou W, Yan J, et al. Comparing Machine Learning Classifiers for Object-based Land Cover Classification Using Very High Resolution Imagery[J]. Remote Sensing, 2015,7(1): 153-168.
9 Van der Sande C J, de Jong S M, de Roo A P J. A Segmentation and Classification Approach of IKONOS-2 Imagery for Land Cover Mapping to Assist Flood Risk and Flood Damage Assessment[J]. International Journal of Applied Earth Observation and Geoinformation, 2003, 4(3): 217-229.
10 Blaschke T. Object based Image Analysis for Remote Sensing[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2010,65(1):2-16.
11 Burnett C, Blaschke T. A Multi-Scale Segmentation/Object Relationship Modelling Methodology for Landscape Analysis[J]. Ecological Modelling, 2003, 168(3): 233-249.
12 Labib S M, Harris A. The Potentials of Sentinel-2 and LandSat-8 Data in Green Infrastructure Extraction, Using Object based Image Analysis (OBIA) Method[J]. European Journal of Remote Sensing, 2018, 51(1): 231-240.
13 Wang C, Xu W, Pei X, et al. An Unsupervised Multi-Scale Segmentation Method based on Automated Parameterization[J]. Arabian Journal of Geosciences, 2016, 9(15): 1-10.
14 Lucian D, Dirk T, Shaun R. ESP: A Tool to Estimate Scale Parameter for Multiresolution Image Segmentation of Remotely Sensed Data[J]. International Journal of Geographical Information Science, 2010, 24(6): 859-871.
15 Dragut L, Csillik O, Eisank C, et al. Automated Parameterisation for Multi-scale Image Segmentation on Multiple Layers[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2014,88(100):119-127.
16 Rau J Y, Jhan J P, Rau R J. Semiautomatic Object Oriented Landslide Recognition Scheme from Multisensor Optical Imagery and DEM[J]. IEEE Transactions on Geoscience and Remote Sensing, 2014, 52(2): 1336-1349.
17 Mohan V A, Kamala P, Martha T R, et al. A Tool Assessing Optimal Multi-Scale Image Segmentation[J]. Journal of the Indian Society of Remote Sensing, 2017, 46(1): 31-41.
18 Guigues L, Cocquerez J P, Le M H. Scale-Sets Image Analysis[J]. International Journal of Computer Vision, 2006, 68(3): 289–317.
19 Niu X, Ban Y. Multi-temporal Radarsat-2 Polarimetric SAR Data for Urban Land-cover Classification Using an Object-based Support Vector Machine and a Rule-based Approach[J].International Journal of Remote Sensing,2013,34(1):1-26.
20 Karsli F, Dihkan M, Acar H, et al. Automatic Building Extraction from very High-resolution Image and LiDAR Data with SVM Algorithm[J]. Arabian Journal of Geosciences, 2016, 9(14):635.
21 Pan Li, Wang Hua, Zhang Jianqiang. Residential Areas Detection on Panchromatic Remote Sensing Images based on Naive Bayesian Networks[J]. Geomatics and Information Science of Wuhan University, 2007, 32(12): 1103-1106.
21 潘励,王华,张剑清.遥感影像居民地目标Bayesian网络识别方法研究[J].武汉大学学报·信息科学版,2007,32 (12):1103-1106.
22 Zhao Ping, Feng Xuezhi, Lin Guangfa. The Decision Tree Algorithm of Automatically Extracting Residential Information from SPOT Images[J]. Journal of Remote Sensing, 2003,7(4):309-315, 340.
22 赵萍,冯学智,林广发.SPOT卫星影像居民地信息自动提取的决策树方法研究[J].遥感学报,2003,7(4):309-315, 340.
23 Kadavi P R, Lee C. Land Cover Classification Analysis of Volcanic Island in Aleutian Arc Using An Artificial Neural Network (ANN) and A Support Vector Machine (SVM) from Landsat Imagery[J]. Geosciences Journal, 2018,22(4): 653–665.
24 Fu Ying, Guo Qiaozhen, Pan Yingyang, et al. Research on Building Extraction Rules based on SPOT6 Data[J]. Remote Sensing for Land & Resources, 2017,29(3):65-69.
24 付盈,国巧真,潘应阳,等.基于SPOT6数据的建筑物提取规则研究[J].国土资源遥感,2017,29(3):65-69.
25 Happ P N, Feitosa R Q, Bente C, et al. A Region-growing Segmentation Algorithm for GPUs[J]. IEEE Geoscience and Remote Sensing Letters, 2013, 10(6): 1612-1616.
26 Elnashar A I. Speed Up Improvement of Parallel Image Layers Generation Constructed by Edge Detection Using Message Passing Interface[J]. International Journal of Applied Engineering Research, 2018, 13(10): 7323-7332.
27 Hu Z, Li Q, Zou Q, et al. A Bilevel Scale-sets Model for Hierarchical Representation of Large Remote Sensing Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(12): 7366-7377.
28 Bazi Y, Melgani F. Toward an Optimal SVM Classification System for Hyperspectral Remote Sensing Images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(11): 3374-3385.
29 Wang M, Wan Y, Ye Z, et al. Remote Sensing Image Classification based on the Optimal Support Vector Machine and Modified Binary Coded Ant Colony Optimization Algorithm[J]. Information Sciences, 2017, 3(402): 50-68.
30 Bo C, Wang D, Lu H. Hyperspectral Image Classification via a Joint Weighted K-Nearest Neighbour Approach[C]∥ Asian Conference on Computer Vision,Cham.2016.
31 Zhao Ping, Fu Yunfei, Zheng Liugen, et al. Cart-based Land Use/Cover Classification of Remote Sensing Images[J]. Journal of Remote Sensing, 2005, 9(6): 708-716.
31 赵萍,傅云飞,郑刘根,等.基于分类回归树分析的遥感影像土地利用/覆被分类研究[J].遥感学报,2005,9(6):708-716.
32 Alfaro E, Gamez M, Garcia N, et al. Adabag: An R Package for Classification with Boosting and Bagging[J]. Journal of Statistical Software, 2013, 54(2): 1-35.
33 Polikar R. Ensemble based Systems in Decision Making[J]. IEEE Circuits and Systems Magazine, 2006, 6(3): 21–45.
34 Zhang C, Ma Y. Ensemble Machine Learning: Methods and Applications[M]. New York: Springer Science and Business Media, 2012.
35 Wang Z, Yang X. An Edge-suppressed Points Voting Method for Extracting Rural Residential Areas from High Spatial Resolution Images[J]. Remote Sensing Letters, 2017, 8(4): 380-388.
[1] 王卓,闫浩文,禄小敏,冯天文,李亚珍. 一种改进U-Net的高分辨率遥感影像道路提取方法[J]. 遥感技术与应用, 2020, 35(4): 741-748.
[2] 郝睿,李兆富,张舒昱,潘剑君,姜小三,张文敏,宋金超. 整合无人机和面向对象的农村居住环境信息提取[J]. 遥感技术与应用, 2020, 35(3): 576-586.
[3] 王芳,杨武年,王建,谢兵,任金铜. 遥感影像多尺度分割中最优尺度的选取及评价[J]. 遥感技术与应用, 2020, 35(3): 623-633.
[4] 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.
[5] 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.
[6] 刘立, 刘勇. 基于优化分割分类层次体系的土地覆被分类制图方法探讨[J]. 遥感技术与应用, 2019, 34(1): 79-89.
[7] 程凯, 王卷乐, Jaahanaa Davaadorj, 韩雪华. 近30 a来蒙古国乌兰巴托市城镇扩张及其驱动力分析[J]. 遥感技术与应用, 2019, 34(1): 90-100.
[8] 李哲, 宫兆宁, 刘先林, 关晖, 王颖. 基于面向对象多端元混解模型的植被覆盖度反演及其时空分布研究[J]. 遥感技术与应用, 2018, 33(6): 1149-1158.
[9] 闫鹏飞,明冬萍. 尺度自适应的高分辨率遥感影像分水岭分割方法[J]. 遥感技术与应用, 2018, 33(2): 321-330.
[10] 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.
[11] 田峰,陈冬花,黄新利,李虎,姚国慧. 基于形态学阴影指数的高分二号影像建筑物高度估计#br#[J]. 遥感技术与应用, 2017, 32(5): 844-850.
[12] 林齐根,邹振华,祝瑛琦,王瑛. 基于光谱、空间和形态特征的面向对象滑坡识别[J]. 遥感技术与应用, 2017, 32(5): 931-937.
[13] 姬忠林,张月平,李乔玄,刘绍贵,李淑娟,任红艳. 基于GF-1影像的冬小麦和油菜种植信息提取[J]. 遥感技术与应用, 2017, 32(4): 760-765.
[14] 王苏芸,孙中昶,郭华东,申维. 基于面向对象的东营市城乡建设用地信息提取[J]. 遥感技术与应用, 2017, 32(4): 780-786.
[15] 施佩荣,陈永富,刘华,吴云华,魏新,钟泽兵. 基于改进的面向对象遥感影像分类方法研究—以西藏米林县典型林区为例[J]. 遥感技术与应用, 2017, 32(3): 466-474.