基于多层次分割分类模型及其特征空间优化的建筑物提取方法

doi:10.6046/gtzyyg.2019.03.15

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF(9150 KB)

HTML
输出: BibTeX | EndNote (RIS)

摘要

针对高空间分辨率遥感影像城市地物信息提取中的尺度效应、光谱多样性及分类特征优化等问题,基于面向对象影像分析方法,结合数据挖掘与机器学习技术,提出了一种多层次分割分类模型及其特征空间优化的建筑物提取方法。首先,根据遥感信息多尺度特性,针对地物特征差异设立层级关系,再结合光谱多样性特征定义地物包含的子类型,建立基于不透水面分割分类提取建筑物的层次化结构; 然后,利用提出的Relief F-PSO组合特征选择方法,优化构建相应层次的影像特征空间; 最后,在多尺度分割和特征优化的基础上,基于随机森林模型获取不透水面分布,进而采用J48决策树算法分类提取建筑物。实验结果表明,该方法能够利用较少数量的影像特征,获得高精度的建筑物提取成果。

	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
	党涛
	宋起
	刘勇
	徐安建
	徐波
	张宏刚

关键词 ：基于对象影像分析, 建筑物, 多层次模型, 特征选择

Abstract：

In view of the problems of scale effect, spectral diversity and classification feature optimization in the extraction of urban objects information from high spatial resolution remote sensing images,the authors, based on the object-based image analysis method and combined with data mining and machine learning,propose a multi-level segmentation and classification hierarchical model and its feature space optimization method for building extraction. First, according to the multi-scale characteristics of remote sensing information, a hierarchical relationship is set up for the difference of features of ground objects, and then a hierarchical structure based on information segmentation and classification is established based on the characteristics of spectral diversity to define the subtypes of ground objects. After that, the proposed Relief F-PSO combination feature selection method is used. Finally,on the basis of multiscale segmentation and feature optimization, the water surface distribution is obtained based on the random forest model, and finally the building information is extracted by the J48 decision tree algorithm. Experimental results show that the method can utilize a small number of image feature attributes to get high-precision building extraction results.

Key words： object-based image analysis buildings segmentation and classification hierarchical model feature selection

收稿日期: 2018-05-16 出版日期: 2019-08-30

TP79

基金资助:国家自然科学基金项目“遥感影像多尺度分割质量评价与参数优选方法研究”资助(41271360)

作者简介: 党涛(1988-),男,硕士研究生,主要从事遥感影像分析与信息提取方面的研究。Email: 764873716@qq.com.。

引用本文:

党涛, 宋起, 刘勇, 徐安建, 徐波, 张宏刚. 基于多层次分割分类模型及其特征空间优化的建筑物提取方法[J]. 国土资源遥感, 2019, 31(3): 111-122.
Tao DANG, Qi SONG, Yong LIU, Anjian XU, Bo XU, Honggang ZHANG. Extraction of buildings in remote sensing imagery based on multi-level segmentation and classification hierarchical model and feature space optimization. Remote Sensing for Land & Resources, 2019, 31(3): 111-122.

链接本文:

https://www.gtzyyg.com/CN/10.6046/gtzyyg.2019.03.15 或 https://www.gtzyyg.com/CN/Y2019/V31/I3/111

Tab.1 多层次影像分割分类结构

Fig.1 Relief F-PSO特征选择算法流程

Fig.2 研究区WorldView3 B3(R),B2(G),B1(B)合成影像

Fig.3 ED2值与尺度因子的关系

Fig.4 研究区建筑物提取分割层次

Fig.5 研究区影像分割结果(局部)

Fig.6 研究区典型地物各波段亮度均值及亮度箱线图

Fig.7 研究区典型地物各波段亮度值

Fig.8 特征重要性程度分析

Fig.9 典型地物样本特征分析

Fig.10 总体精度和Kappa系数与特征数量之间的关系图

Tab.2 不透水面提取最优特征集

Fig.11 基于RF算法的不透水面提取结果

Tab.3 建筑物提取最优特征集

Fig.12 典型地物样本特征分析

Tab.4 研究区地物提取规则集

Fig.13 研究区影像建筑物最终提取结果

Fig.14 不同分类方法建筑物提取结果

Tab.5 不同分类方法相关数据统计比较

[1]	王俊, 秦其明, 叶昕 , 等. 高分辨率光学遥感图像建筑物提取研究进展[J]. 遥感技术与应用, 2016,31(4):653-660. doi: 10.11873/j.issn.1004-0323.2016.4.0653
	Wang J, Qin Q M, Ye X , et al. A survey of building extraction methods from optical high resolution remote sensing imagery[J]. Remote Sensing Technology and Application, 2016,31(4):653-662.
[2]	孙庆玲, 冯险峰 . 基于GeoEye-1影像的城区建筑物提取方法研究[J]. 遥感信息, 2013,28(4):8-12.
	Sun Q L, Feng X F . Extraction of urban building based on GeoEye-1 image[J]. Remote Sensing Information, 2013,28(4):8-12.
[3]	郭怡帆, 张锦, 卫东 . 面向对象的高分辨遥感影像建筑物轮廓提取研究[J]. 测绘通报, 2014,( s2):300-303.
	Guo Y F, Zhang J, Wei D . The research of object-oriented building contour extraction of high-resolution remote sensing image[J].Bulletin of Surveying and Mapping, 2014(s2):300-303.
[4]	唐羊洋, 叶华平, 吴书金 , 等. 基于波段与形状特征的遥感影像建筑物分类提取[J]. 后勤工程学院学报, 2016,32(1):93-96.
	Tang Y Y, Ye H P, Wu S J , et al. Building classification and extraction form remote sensing image based on wave range and shape features[J]. Journal of Logistical Engineering University, 2016,32(1):93-96.
[5]	王宏涛, 王变利 . 融合LiDAR和多光谱影像的建筑物自动检测[J]. 测绘科学, 2015,40(8):64-67.
	Wang H T, Wang B L . Automatic building detection fusing LiDAR and multispectral imagery[J]. Science of Surveying and Mapping, 2015,40(8):64-67.
[6]	王旭东, 段福洲, 屈新原 , 等. 面向对象和SVM结合的无人机数据建筑物提取[J]. 国土资源遥感, 2017,29(1):97-101.doi: 10.6046/gtzyyg.2017.01.15.
	Wang X D, Duan F Z, Qu X Y , et al. Building extraction based on UAV imagery data with the synergistic use of objected-based method and SVM clsssifier[J]. Remote Sensing for Land and Resources, 2017,29(1):97-101.doi: 10.6046/gtzyyg.2017.01.15.
[7]	Turker M, Koc-San D . Building extraction from high-resolution optical spaceborne images using the integration of support vector machine (SVM) classification,Hough transformation and perceptual grouping[J]. International Journal of Applied Earth Observation and Geoinformation, 2016,34:58-69.
[8]	Dornaika F, Moujahida A, Merabet Y E , et al. Building detection from orthophotos using a machine learning approach:An empirical study on image segmentation and descriptors[J]. Expert Systems With Applications, 2016,58:130-142.
[9]	Chen L, Zhao S H, Han W Q , et al. Building detection in an urban area using LiDAR data and QuickBird imagery[J]. International Journal of Remote Sensing, 2012,33:5135-5148.
[10]	Awrangjeb M, Zhang C, Fraser C S . Automatic extraction of building roofs using LiDAR data and multispectral imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2013,83:1-18.
[11]	胡婷 . 遥感图像典型地物特征提取的尺度效应研究[D]. 西安:西北大学, 2010.
	Hu T . The Study of Scale Effects in Typical Objects’ Feature Extraction from Remote Sensing Image[D]. Xi’an:Northwest University, 2010.
[12]	黄慧萍, 吴炳方 . 地物提取的多尺度特征遥感应用分析[J]. 遥感技术与应用, 2003,18(5):276-281.
	Huang H P, Wu B F . Analysis of the mutli-scale characteristics with objects extraction[J]. Remote Sensing Technology and Application, 2003,18(5):276-281.
[13]	李秦, 高锡章, 张涛 , 等. 最优分割尺度下的多层次遥感地物分类实验分析[J]. 地球信息科学学报, 2011,13(3):409-416. doi: 10.3724/SP.J.1047.2011.00409
	Li Q, Gao X Z, Zhang T , et al. Optimal segmentation scale selection and evaluation for multi-layer image recognition and classification[J]. Journal of Geo-Information Science, 2011,13(3):409-416.
[14]	吴俐民, 左小清, 倪曙 , 等. 卫星遥感影像专题信息提取技术与应用[M]. 成都: 西南交通大学出版社, 2013.
	Wu L M, Zuo X Q, Ni S , et al. Special Information Extraction Technology and Application of Satellite Remote Sensing Images[M]. Chengdu: Southwest Jiaotong University press, 2013.
[15]	吕凤华, 舒宁, 龚龑 , 等. 利用多特征进行航空影像建筑物提取[J]. 武汉大学学报信息科学版, 2017,42(5):656-660.
	Lyu F H, Shu N, Gong Y , et al. Regular building extraction from high resolution image based on multilevel-features[J]. Geomatics and Information Science of Wuhan University, 2017,42(5):656-660.
[16]	吴炜, 骆剑承, 沈占锋等. 光谱和形状特征相结合的高分辨遥感图像的建筑物提取方法[J]. 武汉大学学报信息科学版, 2012,37(7):800-804.
	Wu W, Luo J C, Shen Z F , et al. Building extraction from high resolution remote sensing imagery based on spatial-spectral method[J]. Geomatics and Information Science of Wuhan University, 2012,37(7):800-805.
[17]	谭衢霖 . 高分辨率多光谱影像城区建筑物提取研究[J]. 测绘学报, 2010,39(6):618-623.
	Tan Q L . Urban building extraction from VHR multi-spectral images using object-based classification[J]. Acta Geodaetica et Cartographica Sinica, 2010,39(6):618-623.
[18]	蒋胜利 . 高维数据的特征选择与特征提取研究[D]. 西安:西安电子科技大学, 2011.
	Jiang S L . Research on Feature Selection and Feature Extraction for High-Dimensional Data[D]. Xi’an:Xidian University, 2011.
[19]	刘舒, 姜琦刚, 马玥 , 等. 基于多目标遗传随机森林特征选择的面向对象湿地分类[J]. 农业机械学报, 2017,48(1):119-127.
	Liu S, Jiang Q G, Ma Y , et al. Object-oriented wetland classification based on hybrid feature selection method combing with Relief F,multi-objective genetic algorithm and random forest[J]. Transactions of the Chinese Society for Agricultural Machinery, 2017,48(1):119-127.
[20]	薛章鹰, 刘兴权 . 结合ReliefF、GA和SVM的面向对象建筑物目标识别特征选择方法[J]. 测绘工程, 2017,26(2):52-56.
	Xue Z Y, Liu X Q . Feature selection method for object-oriented building targets recognition based on ReliefF,GA and SVM[J]. Engineering of Surveying and Mapping, 2017,26(2):52-56.
[21]	吴卿 . 基于高分辨率遥感影像的水土保持生态建设监测方法研究[D]. 北京:北京林业大学, 2007.
	Wu Q . Study on Monitoring Method for Ecological Construction of Water and Soil Conservation Based On High-Resolution Remote Sensing Images[D]. Beijing:Beijing Forestry University, 2007.
[22]	李晓霞, 汪云甲 . 面向对象的高分辨率影像采煤塌陷地提取[J]. 计算机工程与应用, 2011,47(23):239-241. doi:
	Li X X, Wang Y J . Coal mine subsidence area extraction for high-resolution remote sensing imagery based on object-oriented classification method[J]. Computer Engineering and Application, 2011,47(23):239-241.
[23]	肖艳, 姜琦刚, 王斌 , 等. 基于ReliefF和PSO混合特征选择的面向对象土地利用分类[J]. 农业工程学报, 2016,32(4):211-215.
	Xiao Y, Jiang Q G, Wang B , et al. Object based land-use classification based on hybrid feature selection method of combining ReliefF and PSO[J]. Transaction of the Chinese Society of Agricultural Engineering, 2016,32(4):211-215.
[24]	Liu Y, Bian L, Meng Y , et al. Discrepancy measures for selecting optimal combination of parameter values in object-based image analysis[J].ISPRS Journal of Photogrammetry and Remote Sensing, 2012(68):144-156.
[25]	孙宇翼, 赵军利, 王苗苗 , 等. 基于J48决策树的面向对象方法的土地覆被信息提取[J]. 国土资源遥感, 2016,28(4):156-63.doi: 10.6046/gtzyyg.2016.04.24. doi: 10.6046/gtzyyg.2016.04.24
	Sun Y Y, Zhao J L, Wang M M , et al. Land cover information extraction from remote sensing images using object-based image analysis method integrated with decision tree[J]. Remote Sensing for Land and Resources, 2016,28(4):156-63.doi: 10.6046/gtzyyg.2016.04.24.
[26]	袁梅宇 . 数据挖掘与机器学习:WEKA应用技术与实践[M]. 2版.北京: 清华大学出版社, 2016: 85-94.
	Yuan M Y. Data Mining and Machine Learning:WEKA Application Technology and Practice[M].2nd ed. Beijing: Tsinghua University Press, 2016: 85-94.

[1]	宋仁波, 朱瑜馨, 郭仁杰, 赵鹏飞, 赵珂馨, 朱洁, 陈颖. 基于多源数据集成的城市建筑物三维建模方法[J]. 自然资源遥感, 2022, 34(1): 93-105.
[2]	何陈临秋, 程博, 陈金奋, 张晓平. 基于GF-3全极化SAR数据的滨海湿地信息提取方法[J]. 自然资源遥感, 2021, 33(4): 105-110.
[3]	郭文, 张荞. 基于注意力增强全卷积神经网络的高分卫星影像建筑物提取[J]. 国土资源遥感, 2021, 33(2): 100-107.
[4]	武宇, 张俊, 李屹旭, 黄康钰. 基于改进U-Net的建筑物集群识别研究[J]. 国土资源遥感, 2021, 33(2): 48-54.
[5]	卢麒, 秦军, 姚雪东, 吴艳兰, 朱皓辰. 基于多层次感知网络的GF-2遥感影像建筑物提取[J]. 国土资源遥感, 2021, 33(2): 75-84.
[6]	朱茂, 沈体雁, 黄松, 白书建, 葛春青, 胡琼. InSAR技术地铁沿线建筑物形变监测[J]. 国土资源遥感, 2019, 31(2): 196-203.
[7]	周阳, 张云生, 陈斯飏, 邹峥嵘, 朱耀晨, 赵芮雪. 基于DCNN特征的建筑物震害损毁区域检测[J]. 国土资源遥感, 2019, 31(2): 44-50.
[8]	吴柳青, 胡翔云. 基于多尺度多特征的高空间分辨率遥感影像建筑物自动化检测[J]. 国土资源遥感, 2019, 31(1): 71-78.
[9]	闫利, 李瑶, 谢洪. 基于机载与车载LiDAR数据的LoD3城市建筑物模型自动重建[J]. 国土资源遥感, 2018, 30(4): 97-101.
[10]	李云帆, 谭德宝, 刘瑞, 邬建伟. 顾及建筑物屋顶结构的改进RANSAC点云分割算法[J]. 国土资源遥感, 2017, 29(4): 20-25.
[11]	付盈, 国巧真, 潘应阳, 汪东川. 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.
[12]	王世新, 田野, 周艺, 刘文亮, 林晨曦. 基于后向散射模型的多极化SAR影像建筑物高度提取[J]. 国土资源遥感, 2017, 29(2): 37-45.
[13]	王旭东, 段福洲, 屈新原, 李丹, 余攀锋. 面向对象和SVM结合的无人机数据建筑物提取[J]. 国土资源遥感, 2017, 29(1): 97-103.
[14]	王春林, 孙金彦, 周绍光, 钱海明, 黄祚继. 影像辅助下LiDAR数据建筑物轮廓信息提取[J]. 国土资源遥感, 2017, 29(1): 78-85.
[15]	王雪, 李培军, 姜莎莎, 刘婧, 宋本钦. 利用机载LiDAR数据和高分辨率图像提取复杂城区建筑物[J]. 国土资源遥感, 2016, 28(2): 106-111.

Viewed

Full text

Abstract

Cited

Shared

Discussed