融合数字表面模型的无人机遥感影像城市土地利用分类

doi:10.12082/dqxxkx.2018.170635

地球信息科学学报 ›› 2018, Vol. 20 ›› Issue (5): 703-711.doi: 10.12082/dqxxkx.2018.170635

• 遥感科学与应用技术 • 上一篇

融合数字表面模型的无人机遥感影像城市土地利用分类

宋晓阳^1,²(), 黄耀欢^3,^4,^*(), 董东林¹, 张飞²

1. 中国矿业大学（北京）地球科学与测绘工程学院, 北京 100083
2. 中国科学院声学研究所声场声信息国家重点实验室, 北京 100190
3. 中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室, 北京 100101
4. 中国科学院大学, 北京 100049

收稿日期:2017-12-25 修回日期:2018-01-27 出版日期:2018-05-29 发布日期:2018-05-20
通讯作者: 黄耀欢 E-mail:songxy@student.cumtb.edu.cn;huangyh@lreis.ac.cn
作者简介:
作者简介：宋晓阳(1988-),女,博士生,主要从事GIS应用研究。E-mail: songxy@student.cumtb.edu.cn
基金资助:
国家重点研发计划项目（2016YFC0401404）

Urban Land Use Classification from UAV Remote Sensing Images Based on Digital Surface Model

SONG Xiaoyang^1,²(), HUANG Yaohuan^3,^4,^*(), DONG Donglin¹, ZHANG Fei²

1. College of Geoscience and Surveying Engineering, China University of Mining & Technology, Beijing 100083, China;
2. State Key Laboratory of Acoustics, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China
3. State Key Laboratory of Resources and Environmental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences , Beijing 100101, China
4. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2017-12-25 Revised:2018-01-27 Online:2018-05-29 Published:2018-05-20
Contact: HUANG Yaohuan E-mail:songxy@student.cumtb.edu.cn;huangyh@lreis.ac.cn
Supported by:
National Key Research and Development Program of China, No.2016YFC0401404.

摘要/Abstract

摘要：

城市土地利用是城市生态学中的关键问题,深入了解城市的土地利用对合理规划城市功能分区、提升用地效益、促进区域经济与环境发展具有重要意义。因此,城市土地利用类型分类研究一直是城市规划学和城市地理学研究的核心内容之一。快速发展的无人机技术为城市土地利用分类提供了丰富的数据支撑,基于无人机遥感影像建立的数字表面模型（DSM）和数字正射影像（DOM）可以有效提高城市土地利用分类的精度。为了充分利用无人机遥感影像的丰富信息,本文提出了一种融合高分辨率DOM和DSM的城市土地利用分类方法。本文融合了DOM和DSM作为数据源。在面向对象分类方法的基础上,DSM分别被用于多尺度分割过程中像元融合的最终阈值和地物分类过程中的地物高度特征。该方法在天津市宝坻区的京津新城进行了验证,结果表明,相对于最初的多尺度分割方法,融合DSM后的多尺度分割方法的分割质量指数（QR）、过分割指数（OR）、欠分割指数（UR）和综合指数（CR）都有所降低,分割效果明显提高。优化后的面向对象分类方法,在分类精度上有所提高,尤其是道路、建筑物和其他建设用地。总体精度由85%提高到了87.25%,Kappa系数由0.79提高到0.82。由此可看出,优化后的面向对象分类方法可以更有效地进行城市土地利用分类。

关键词: 无人机遥感, 面向对象分类, 土地利用, 数字表面模型（DSM）, 数字正射影像（DOM）

Abstract:

Urban land use is a key issue of urban ecology. It is of great significance to understand the urban land use for planning urban functional zones, improving land use efficiency, estimating human population, analyzing urban landscape and promoting regional economic and environmental development. Therefore, urban land use classification research has been one of the core contents of urban planning and urban geography. With the rapid development of Unmanned Aerial Vechicle (UAV) technology, rich UAV data have widely been used in different kinds of fields, especially in the urban land use classification. Digital surface model (DSM) and digital orthophoto map (DOM) obtained from UAV remote sensing images can effectively improve the accuracy of urban land use classification. In order to make full use of the rich information of UAV remote sensing images, an urban land use classification method is proposed using high-resolution DOM and DSM. In this study, the composite bands of DOM and DSM were used as data source. Considering the characteristics of urban land use, the object-oriented classification method was optimized by combining DOM spectral information with DSM, which is used as the final threshold of the pixel merge in multi-resolution segmentation and as height feature in objects classification, respectively. The method was validated in Jingjinxincheng located in Baodi District, Tianjin City. The results showed that, comparing with the initial multi-resolution segmentation method, all of the segmentation quality rate (QR), over-segmentation rate (OR), under-segmentation rate (UR) and comprehensive rate (CR) of optimized multi-resolution segmentation method were reduced, and the effects of image segmentation has been improved significantly. The optimized object-oriented classification method improved the classification accuracy, especially for the extraction of roads, buildings and other constructions. The overall accuracy of the classification results increased from 85% to 87.25% and the Kappa coefficient also increased from 0.79 to 0.82. Therefore, the optimized object-oriented classification method can be used for urban land use study more effectively.

Key words: UAV remote sensing, object-oriented classification, land use, Digital Surface Model (DSM), digital orthophoto map (DOM)

宋晓阳, 黄耀欢, 董东林, 张飞. 融合数字表面模型的无人机遥感影像城市土地利用分类[J]. 地球信息科学学报, 2018, 20(5): 703-711.DOI:10.12082/dqxxkx.2018.170635

SONG Xiaoyang,HUANG Yaohuan,DONG Donglin,ZHANG Fei. Urban Land Use Classification from UAV Remote Sensing Images Based on Digital Surface Model[J]. Journal of Geo-information Science, 2018, 20(5): 703-711.DOI:10.12082/dqxxkx.2018.170635

图/表 10

图1

图2

图3

图4

表1

分割结果评价指标"

评价指数	公式	说明
QR	$QR = 1 - a (x i ? y j) a (x i ? y j), y j ∈ Y i *$	x是指实际的地物对象,y是指的分割结果。 $Y i $ 是指和x_i有重叠的分割结果的部分图斑。a()是指图斑‘’的面积。 $Y i $ 主要包括三种情况的y_j：① x_i的中心点位于y_j;② y_j的中心点位于x_i;③ x_i和y_j的交集面积大于y_j或x_i面积的1/2。
OR	$OR = a (x i) - a (x i ? y j) a (x i), y j ∈ Y i *$
UR	$UR = a (y j) - a (x i ? y j) a (y j), y j ∈ Y i *$
CR	$CR = O R 2 + U R 2 2$

表1

表2

分类结果评价指标"

评价指标	公式	说明
UA	$UA = x ii ∑ 1 r x + i$	r是混淆矩阵中总列数(即总的类别数);x_ii是混淆矩阵中第i行第i列上像元数量(即正确分类的数目);x_i₊和x₊_i分别是第i行和第i列的总像元数量;N是总的用于精度评估的像元数量
PA	$PA = x ii ∑ 1 r x i +$
OA	$OA = ∑ 1 r x ii N$
Ka	$Ka = N ∑ 1 r x ii - ∑ 1 r x i + x + i N 2 - ∑ 1 r x i + x + i$

表2

表3

图5

图6

表4

参考文献 30

[1]	Feddema J J, Oleson K W, Bonan G B, et al.The importance of land-cover change in simulating future climates[J]. Science, 2005,310(5754):1674. doi: 10.1126/science.1118160
[2]	陈溪,王子彦,匡文慧.土地利用对气候变化影响研究进展与图谱分析[J].地理科学进展,2011,30(7):930-937. doi: 10.11820/dlkxjz.2011.07.020
	[ Chen X, Wang Z Y, Kuang H W.Research progress and TUPU analysis on the impacts of land use on climate change[J]. Progress in Geography, 2011,30(7):930-937. ] doi: 10.11820/dlkxjz.2011.07.020
[3]	Foley J A, Defries R, Asner G P, et al.Global consequences of land use[J]. Science, 2005,309(5734): 570-574. doi: 10.1126/science.1111772
[4]	Zomer R J, Trabucco A, Bossio D A, et al.Climate change mitigation: A spatial analysis of global land suitability for clean development mechanism afforestation and reforestation[J]. Agriculture Ecosystems & Environment, 2008,126(1):67-80. doi: 10.1016/j.agee.2008.01.014
[5]	翟天林,金贵,邓祥征,等.基于多源遥感影像融合的武汉市土地利用分类方法研究[J].长江流域资源与环境,2016,25(10):1594-1602. doi: 10.11870/cjlyzyyhj201610014
	[ Zhai T L, Jin G, Deng X Z, et al.Research of wuhan city land use classification method based on multi-source remote sensing image fusion[J]. Resources and Environment in the Yangtze Basin, 2016, 25(10):1594-1602. ] doi: 10.11870/cjlyzyyhj201610014
[6]	Stow D, Lopez A, Lippitt C, et al.Object-based classification of residential land use within Accra, Ghana based on QuickBird satellite data[J]. International Journal of Remote Sensing, 2007,28(22):5167. doi: 10.1080/01431160701604703 pmid: 2677813
[7]	郑盛,曹春香,程锦泉,等.基于国产卫星数据的深圳城市化进程中土地利用/覆盖变化探讨[J].中国科学:信息科学, 2011,s1:140-152.
	[ Zheng S, Cao C X, Cheng J Q, et al.A study on land use and land cover change during urbanization in Shenzhen using data from Chinese satellites[J]. Scientia Sinica Informationis, 2011,s1:140-152. ]
[8]	Myint S W, Gober P, Brazel A, et al.Per-pixel vs. object-based classification of urban land cover extraction using high spatial resolution imagery[J]. Remote Sensing of Environment, 2011,115(5):1145-1161. doi: 10.1016/j.rse.2010.12.017
[9]	周亦,张亚亚.利用eCognition进行高分一号卫星数据土地利用现状解译能力测试[J].测绘通报,2016,8:77-80.
	[ Zhou Y, Zhang Y Y.A test of land use status interpretation ability based on GF-1 satellite data using eCognition[J]. Bulletin of Surveying and Mapping, 2016,8:77-80. ]
[10]	满其霞. 激光雷达和高光谱数据融合的城市土地利用分类方法研究[D].上海:华东师范大学,2015.
	[ Man Q X.Fusion of hyperspectral and LiDAR data for urban land use classification[J]. Shanghai: East China Normal University, 2015. ]
[11]	Powell R L, Roberts D A, Dennison P E, et al.Sub-pixel mapping of urban land cover using multiple endmember spectral mixture analysis: Manaus, Brazil[J]. Remote Sensing of Environment, 2007,106(2):253-267. doi: 10.1016/j.rse.2006.09.005
[12]	Watanachaturaporn P, Arora M K, varshney P K. Multisource classification using support vector machines[J]. Photogrammetric Engineering & Remote Sensing, 2008,74(2):239-246. doi: 10.14358/PERS.74.2.239
[13]	Zhou W.An object-based approach for urban land cover classification: integrating LiDAR height and intensity data[J]. IEEE Geoscience & Remote Sensing Letters, 2013,10(4):928-931. doi: 10.1109/LGRS.2013.2251453
[14]	Awrangjeb M, Fraser C.Automatic segmentation of raw LIDAR data for extraction of building roofs[J]. Remote Sensing, 2014,6(5):3716-3751. doi: 10.3390/rs6053716
[15]	李德仁,李明.无人机遥感系统的研究进展与应用前景[J].武汉大学学报·信息科学版,2014,39(5):505-513. doi: 10.13203/j.whugis20140045
	[ Li D R, Li M.Research advance and application prospect of unmanned aerial vehicle remote sensing system[J]. Geomatics and Information Science of Wuhan University, 2014,39(5):505-513. ] doi: 10.13203/j.whugis20140045
[16]	胡勇,张孝成,马泽忠,等.无人机遥感影像中农村房屋信息快速提取[J].国土资源遥感,2016,28(3):96-101. doi: 10.6046/gtzyyg.2016.03.16
	[ Hu Y, Zhang X C, Ma Z Z, et al.Rural residential area extraction from UAV remote sensing imagery[J]. Remote Sensing for Land & Resources, 2016,28(3):96-101. ] doi: 10.6046/gtzyyg.2016.03.16
[17]	付萧,鲁恒,朱庆,等.利用无人机影像进行山区土地利用信息动态监测[J].山地学报,2016,34(1):121-126.
	[ Fu X, Lu H, Zhu Q, et al.Landuse information of mountain areas dynamic monitoring based on uav images[J]. Mountain Reserach, 2016,34(1):121-126. ]
[18]	Benz U C, Hofmann P, Willhauck G, et al.Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information[C]. Isprs Journal of Photogrammetry & Remote Sensing, 2004,58(3-4):239-258.
[19]	Baatz M, Sch Pe A.An optimization approach for high quality multi-scale image segmentation[C]. Proceedings of the Beiträge zum AGIT-Symposium, F, 2000.
[20]	Tian J, Chen D M.Optimization in multi-scale segmentation of high-resolution satellite images for artificial feature recognition[J]. International Journal of Remote Sensing, 2007,28(20):4625-4644. doi: 10.1080/01431160701241746
[21]	Gmbh M T G. ECognition Developer8.7 reference book[M]. Trimble: Munich, 2011.
[22]	Shuxi L I, Song Y, Changhui L I.Quick Extraction of Buildings Based on DSM and RGB-Aerial Image[J]. Bulletin of Surveying & Mapping, 2012,27(1):33-32. doi: 10.1007/s11783-011-0280-z
[23]	黎树禧,宋杨,李长辉.利用DSM以及彩色遥感航空影像快速提取建筑物目标信息[J].测绘通报,2012(1):33-35.
	[ Li S X, Song Y, Li C H.Quick extraction of buildings based on dsm and rgb-aerial image[J]. Bulletin of Surveying and Mapping, 2012(1):33-35. ]
[24]	陈松林,刘强,余珊,等.福州市晋安区土地适宜性评价[J].地球信息科学学报,2002,4(1):61-65. doi: 10.3969/j.issn.1560-8999.2002.01.014
	[ Chen S L, Liu Q, Yu S, et al.The evaluation of land resource suitability in Jinan district of Fuzhou supported by GIS[J]. Geo-Information Science, 2002,4(1):61-65. ] doi: 10.3969/j.issn.1560-8999.2002.01.014
[25]	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):409-417. doi: 10.3724/SP.J.1047.2011.00409
	[ Li Q, Gao X X, 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):409-417. ] doi: 10.3724/SP.J.1047.2011.00409
[26]	杨俊,孙静,葛全胜.大连市城区绿地时空特征的热环境效应研究[J].地球信息科学学报,2016,18(8):1087-1093. doi: 10.3724/SP.J.1047.2016.01087
	[ Yang J, Sun J, Ge Q S.Study on thermal environmental effect of spatial-temporal characteristics of urban green space in the city of Dalian[J]. Journal of Geo-information Science, 2016,18(8):1087-1093. ] doi: 10.3724/SP.J.1047.2016.01087
[27]	Clinton N, Holt A, Scarborough J, et al.Accuracy Assessment Measures for Object-based Image Segmentation Goodness[J]. Photogrammetric Engineering & Remote Sensing, 2010,76(3):289-299. doi: 10.14358/PERS.76.3.289
[28]	Drăguţ L, Csillik O, Eisank C, et al.Automated parameterisation for multi-scale image segmentation on multiple layers[J]. Isprs Journal of Photogrammetry & Remote Sensing Official Publication of the International Society for Photogrammetry & Remote Sensing, 2014,88(100):119.
[29]	陈扬洋,明冬萍,徐录,等.高空间分辨率遥感影像分割定量实验评价方法综述[J].地球信息科学学报,2017,19(6):818-830. doi: 10.3969/j.issn.1560-8999.2017.06.011
	[ Chen Y Y, Ming D P, Xu L, et al.An overview of quantitative experimental methods for segmentation evaluation of high spatial remote sensing images[J]. Journal of Geo-information Science, 2017,19(6):818-830. doi: 10.3969/j.issn.1560-8999.2017.06.011
[30]	杨雪峰,王雪梅.基于决策树的多角度遥感影像分类[J].地球信息科学学报,2016,18(3):416-422. doi: 10.3724/SP.J.1047.2016.00416
	[ Yang X F, Wang X M.Classification of MISR multi- angle imagery based on decision tree classifier[J]. Journal of Geo-information Science, 2016,18(3):416-422. ] doi: 10.3724/SP.J.1047.2016.00416

	QR	OR	UR	CR
原分割方法	0.69	0.49	0.33	0.42
优化后分割方法	0.64	0.42	0.32	0.38

类型		实际土地利用
类型		耕地	绿地	水体	道路	建筑物	其他建设用地	总计	用户精度/%
优化前土地利用分类	耕地	28	3	0	2	0	0	33	84.85
	绿地	4	171	9	6	7	2	199	85.93
	水体	0	3	59	1	0	1	64	92.19
	道路	0	2	0	24	4	3	33	72.73
	建筑物	0	2	0	2	36	3	43	83.72
	其他建设用地	0	3	0	0	3	22	28	78.57
	总计	32	184	68	35	50	31	400
	制图精度/%	87.50	92.93	86.76	68.57	72.00	70.97
优化后土地利用分类	耕地	28	3	0	2	0	0	33	84.85
	绿地	4	173	9	6	8	0	200	86.50
	水体	0	3	59	1		1	64	92.19
	道路	0	2	0	26	0	5	33	78.79
	建筑物	0	0	0	0	40	2	42	95.24
	其他建设用地	0	3	0	0	2	23	28	82.14
	总计	32	184	68	35	50	31	400
	制图精度/%	87.50	94.02	86.76	74.29	80.00	74.19

融合数字表面模型的无人机遥感影像城市土地利用分类

Urban Land Use Classification from UAV Remote Sensing Images Based on Digital Surface Model

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 30

相关文章 15

Metrics

本文评价

推荐阅读 0

[1]	王志华, 杨晓梅, 周成虎. 面向遥感大数据的地学知识图谱构想[J]. 地球信息科学学报, 2021, 23(1): 16-28.
[2]	张世伟, 魏璐瑶, 金星星, 陆玉麒. 基于FLUS-UGB的县域土地利用模拟及城镇开发边界划定研究[J]. 地球信息科学学报, 2020, 22(9): 1848-1859.
[3]	赵鹏军, 曹毓书. 基于多源地理大数据与机器学习的地铁乘客出行目的识别方法[J]. 地球信息科学学报, 2020, 22(9): 1753-1765.
[4]	龚围, 李丽, 柳钦火, 辛晓洲, 彭志晴, 邬明权, 牛铮, 田海峰. “一带一路”区域水电站工程生态环境影响遥感监测[J]. 地球信息科学学报, 2020, 22(7): 1424-1436.
[5]	连丽聪, 万智巍, 鞠民, 贾玉连, 洪祎君, 蒋梅鑫, 曾峰海. 民国中期湖南洞庭湖区耕地空间格局重建[J]. 地球信息科学学报, 2020, 22(5): 989-996.
[6]	刘纪远, 张增祥, 张树文, 颜长珍, 吴世新, 李仁东, 匡文慧, 史文娇, 黄麟, 宁佳, 董金玮. 中国土地利用变化遥感研究的回顾与展望——基于陈述彭学术思想的引领[J]. 地球信息科学学报, 2020, 22(4): 680-687.
[7]	董金玮, 吴文斌, 黄健熙, 尤南山, 何盈利, 闫慧敏. 农业土地利用遥感信息提取的研究进展与展望[J]. 地球信息科学学报, 2020, 22(4): 772-783.
[8]	赵鹏军, 万婕. 城市交通与土地利用一体化模型的核心算法进展及技术创新[J]. 地球信息科学学报, 2020, 22(4): 792-804.
[9]	赵林峰, 刘小平, 刘鹏华, 陈广照, 何家律. 基于地理分区与FLUS模型的城市扩张模拟与预警[J]. 地球信息科学学报, 2020, 22(3): 517-530.
[10]	张经度, 梅志雄, 吕佳慧, 陈进钊. 纳入空间自相关的FLUS模型在土地利用变化多情景模拟中的应用[J]. 地球信息科学学报, 2020, 22(3): 531-542.
[11]	单渌铱, 王海军, 张彬, 潘鹏. 顾及土地生态安全的环鄱阳湖城市群土地利用情景模拟[J]. 地球信息科学学报, 2020, 22(3): 543-556.
[12]	杨露, 颉耀文, 宗乐丽, 邱天, 焦继宗. 基于多目标遗传算法和FLUS模型的西北农牧交错带土地利用优化配置[J]. 地球信息科学学报, 2020, 22(3): 568-579.
[13]	柯新利, 肖邦勇, 郑伟伟, 马艳春, 李红艳. 城镇-农业-生态空间划定的多情景模拟[J]. 地球信息科学学报, 2020, 22(3): 580-591.
[14]	王家丰, 王蓉, 冯永玖, 雷振坤, 高忱, 陈书睿, 金雁敏, 翟淑婷. 顾及轨道交通影响的浙中城市群土地利用多情景模拟与分析[J]. 地球信息科学学报, 2020, 22(3): 605-615.
[15]	聂拼, 梁明, 李玉洁, 游欣妍, 孙晓娟. 基于最邻近时空距离的土地变化过程时空模式分析[J]. 地球信息科学学报, 2020, 22(3): 628-637.