高分辨率影像城市植被自动提取算法

doi:10.3724/SP.J.1047.2016.00248

摘要/Abstract

摘要：

近十几年来,随着城市化进程加剧,准确获取城市植被的分布信息,是城市气候和地表能量平衡研究的重要内容。高空间分辨率遥感影像数据,为精确获取和动态监测城市植被提供了重要资料。本研究利用资源三号数据对长江三角洲地区城市植被进行光谱特征分析与提取,提出一种城市植被的自动化信息提取算法—分离面法（Hyperplanes for Plant Extraction Methodology,HPEM）。结果表明：在假彩色反射率空间,植被与NDVI值低的背景有很好的分离性,而在真彩色反射率空间,植被与NDVI值高的背景有很好的分离性;HPEM能很好地避免NDVI最佳阈值法中将建筑物误分为植被的问题,其精度明显优于NDVI最佳阈值法,Kappa系数从0.85提高到0.90,总的错分与漏分误差从21.15%降低到14.18%。可见,本文的HPEM方法能有效提高城市植被信息自动提取的精度。

关键词: 资源三号, 城市植被, 城市遥感, 支持向量机, 自动提取

Abstract:

With the progress of sustained urbanization in the past ten years, information of accurate urban vegetation cover is turning to be essential for the study of both regional climate and urban energy balance. High spatial-resolution remote sensing imagery provides an important tool for automatic mapping and monitoring of urban vegetation cover due to its broad coverage and high-spatial resolution. We propose an automatic urban vegetation extraction methodology, named as hyperplanes for plant extraction methodology (HPEM), based on the vegetation spectral feature analysis with the ZY-3 multi-spectral imagery over different cities in Yangtze River Delta. The results showed that: first, the vegetation pixels and non-vegetation pixels with low NDVI value can be well separated in the false color composite reflectance space, while the vegetation pixels and non-vegetation pixels with high NDVI value can be well separated in the true color composite reflectance space; second, HPEM could effectively suppress the errors of commission that come from built-up pixels which was often misclassified in NDVI method. HPEM’s performance was better than NDVI at the optimal threshold, with kappa coefficients increased from 0.85 to 0.90 and the total errors of omission and commission reduced from 21.15% to 14.18%. Compared to NDVI method, HPEM also avoided the tedious trial-and-error procedures for searching the optimal threshold. Therefore, HPEM can effectively improve the accuracy of automatic urban vegetation mapping. Moreover, the urban vegetation products are more reliable for further urban environment research.

Key words: ZY-3, urban vegetation, urban remote sensing, support vector machine, automatic extraction

姚方方, 骆剑承, 沈占锋, 董迪, 杨珂含. 高分辨率影像城市植被自动提取算法[J]. 地球信息科学学报, 2016, 18(2): 248-254.DOI:10.3724/SP.J.1047.2016.00248

YAO Fangfang,LUO Jiancheng,SHEN Zhanfeng,DONG Di,YANG Kehan. Automatic Urban Vegetation Extraction Method Using High Resolution Imagery[J]. Journal of Geo-information Science, 2016, 18(2): 248-254.DOI:10.3724/SP.J.1047.2016.00248

图/表 7

表1

图1

图2

图3

图4

图5

表2

参考文献 22

[14]	[ Wang N N, Yang R J, Li S Q, et al.Application of ZY-3 Satellite data in finding land illegal behavior: taking Beihai Haicheng of Guangxi as an example[J]. Journal of Guangxi Teachers Education University: Natural Science Edition, 2014,31(1):60-66. ] doi: 10.3969/j.issn.1002-8743.2014.01.013
[15]	殷涛,张姝娟,李德江.资源三号影像融合技术在地理国情普查中的应用[J].测绘与空间地理信息,2014,37(6):122-124. doi: 10.3969/j.issn.1672-5867.2014.06.045
	[ Yin T, Zhang S J, Li D J.The Application of ZY-03 image fusion technology in geographical conditions survey[J]. Sichuan College of Architectural Technology, 2014,37(6):122-124. ] doi: 10.3969/j.issn.1672-5867.2014.06.045
[16]	森巴提,贾盛杰,郑江华,等.资源三号卫星在种植型药用植物资源调查中的应用研究[J].新疆农业科学,2014,51(2):384-391. doi: 10.6048/j.issn.1001-4330.2014.02.027
[1]	Sobrino J A, Oltra-Carrió R, Sòria G, et al.Impact of spatial resolution and satellite overpass time on evaluation of the surface urban heat island effects[J]. Remote Sensing of Environment, 2012,117(15):50-56. doi: 10.1016/j.rse.2011.04.042
[2]	Rizwan A M, Dennis L Y C, Liu C. A review on the generation, determination and mitigation of Urban Heat Island[J]. Journal of Environmental Sciences, 2008,20(1):120-128. doi: 10.3321/j.issn:1001-0742.2008.01.019 pmid: 18572534
[16]	[ Sen B T, Jia S J, Zheng J H, et al.Application research into ZY-3 satellite in investigating resources of medicinal plants[J]. Xinjiang Agricultural Sciences, 2014,51(2):384-391. ] doi: 10.6048/j.issn.1001-4330.2014.02.027
[17]	王佳,宋珊芸,刘霞.结合影像光谱与地形因子的森林蓄积量估测模型[J].农业机械学报, 2014,45(5):216-220. doi: 10.6041/j.issn.1000-1298.2014.05.033
[3]	Yuan F, Bauer M E.Comparison of impervious surface area and normalized difference vegetation index as indicators of surface urban heat island effects in Landsat imagery[J]. Remote Sensing of Environment, 2007,106(3):375-386. doi: 10.1016/j.rse.2006.09.003
[4]	Tigges J, Lakes T, Hostert P.Urban vegetation classification: Benefits of multitemporal RapidEye satellite data[J]. Remote Sensing of Environment, 2013,136(1):66-75. doi: 10.1016/j.rse.2013.05.001
[5]	Weng Q, Lu D, Schubring J.Estimation of land surface temperature-vegetation abundance relationship for urban heat island studies[J]. Remote Sensing of Environment, 2004,89(4):467-483. doi: 10.1016/j.rse.2003.11.005
[6]	Al-Abed M,史舟,Yaghi A,等.遥感与地理信息系统技术在叙利亚沿海地区土壤侵蚀评价中的应用研究(英文)[J].浙江大学学报(农业与生命科学版),2000,26(2):76-81. doi: 10.3321/j.issn:1008-9209.2000.02.018
[17]	[ Wang J, Song S Y, Liu X, et al. Forest volume estimation model using spectra and topographic factors of ZY-3 image[J]. Transactions of the Chinese Society of Agricultura, 2014,45(5):216-220. ] doi: 10.6041/j.issn.1000-1298.2014.05.033
[18]	杨磊,潘志强,傅俏燕,等.资源三号卫星多光谱数据的大气校正研究[J].光谱学与光谱分析,2013,33(7):1903-1907. doi: 10.3964/j.issn.1000-0593(2013)07-1903-05
[6]	[ Al-Abed M, Shi Z, Yaghi A, et al.Application of GIS and remote sensing in soil degradation assessments in the Syrian coast[J]. Journal of Zhejiang University: Agric. & Life Sci. Edition, 2000,26(2):76-81. ] doi: 10.3321/j.issn:1008-9209.2000.02.018
[7]	史世莲,章文波,王国燕.北京地区植被盖度提取及其分布变化研究[J].遥感技术与应用, 2014,29(5):866-872. doi: 10.11873/j.issn.1004-0323.2014.5.0866
[18]	[ Yang L, Pan Z Q, Fu Q Y, et al.Research on the atomospheric correction for ZY-3 MUX image[J]. Spectroscopy and Spectral Analysis, 2013,33(7):1903-1907. ] doi: 10.3964/j.issn.1000-0593(2013)07-1903-05
[19]	Mantero P, Moser G, Serpico S B.Partially supervised classification of remote sensing images through SVM-based probability density estimation[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005,43(3):559-570. doi: 10.1109/TGRS.2004.842022
[7]	[ Shi S L, Zhang W B, Wang G Y. The measurement of vegetation coverage and the analysis of seasonal change in Beijing[J]. Remote Sensing Technology and Application, 2014,29(5):866-872. ] doi: 10.11873/j.issn.1004-0323.2014.5.0866
[8]	苗正红,刘志明,王宗明,等.基于MODIS NDVI的吉林省植被覆盖度动态遥感监测[J].遥感技术与应用,2010,25(3):387-393.
	[ Miao Z H, Liu Z M, Wang Z M, et al.Dynamic monitoring of vegetation fraction change in Jilin province based on MODIS NDVI[J]. Remote Sensing Technology and Application, 2010,25(3):387-393. ]
[9]	Small C.Estimation of urban vegetation abundance by spectral mixture analysis[J]. International Journal of Remote Sensing, 2001,22(7):1305-1334.
[10]	刘勇,岳文泽.基于图像融合与混合像元分解的城市植被盖度提取[J].生态学报,2010,30(1):93-99.
	[ Liu Y, Yue W Z.Extimation of urban vegetation fraction by image fusion and spectural unmixing[J]. Acta Ecologica Sinica,2010,30(1):93-99. ]
[11]	Carpenter G A, Gjaja M N, Gopal S, et al.ART neural networks for remote sensing: vegetation classification from Landsat TM and terrain data[J]. IEEE Transactions on Geoscience and Remote Sensing, 1997,35(2):308-325. doi: 10.1109/36.563271
[12]	高闪闪,陈仁喜.适于ALOS图像植被信息提取的新植被指数[J].国土资源遥感,2013,25(4):48-52. doi: 10.6046/gtzyyg.2013.04.08
[20]	Mountrakis G, Im J, Ogole C.Support vector machines in remote sensing: A review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2011,66(3):247-259. doi: 10.1016/j.isprsjprs.2010.11.001
[21]	Van der Linden S, Janz A, Waske B, et al. Classifying segmented hyperspectral data from a heterogeneous urban environment using support vector machines[J]. Journal of Applied Remote Sensing, 2007,1(1):013543-013543-17.
[12]	[ Gao S S, Chen R X.New vegetation index for extracting vegetation information from ALOS image[J]. Remote Sensing For Land & Resources, 2013,25(4):48-52. ] doi: 10.6046/gtzyyg.2013.04.08
[13]	张秀英,冯学智,丁晓东,等.基于面向对象方法的IKONOS影像城市植被信息提取[J].浙江大学学报(农业与生命科学版),2007,33(5):76-81. doi: 10.3321/j.issn:1008-9209.2007.05.017
	[ Zhang X Y, Feng X Z, Ding X D, et al.Detecting urban vegetation categories based on object- oriented method from IKONOS data[J]. Journal of Zhejiang University: Agric. & Life Sci. Edition, 2007,33(5):76-81. ] doi: 10.3321/j.issn:1008-9209.2007.05.017
[14]	王宁娜,杨如军,李双青,等.资源三号卫星影像在土地违法发现中的应用——以广西北海市海城区为例[J].广西师范学院学报(自然科学版),2014,31(1):60-66. doi: 10.3969/j.issn.1002-8743.2014.01.013
[22]	Cao X, Chen J, Imura H, et al.A SVM-based method to extract urban areas from DMSP-OLS and SPOT VGT data[J]. Remote Sensing of Environment, 2009,113(10):2205-2209. doi: 10.1016/j.rse.2009.06.001

		资源三号多光谱	资源三号全色(正视)	资源三号全色(前、后视)
空间分辨率/m		5.8	2.1	3.6
重访周期/d		5	5	5
光谱分辨率/μm	Band1	(450~520)	(450~800)	(450~800)
	Band2	(520~590)
	Band3	(630~690)
	Band4	(770~890)
幅宽/km		52	50	52

分类方法	阈值(opt)	类型	Kappa系数	OA / (%)	PA / (%)	OE / (%)	UA / (%)	CE / (%)	TE / (%)
NDVI阈值法	0.35	Vegetation	0.85	93.94	91.59	8.41	87.26	12.74	21.15
	0.35	Non-Veg	0.85	93.94	94.85	5.15	96.69	3.31	8.46
	0.30	Vegetation	0.83	92.82	97.92	2.08	80.5	19.50	21.58
		Non-Veg	0.83	92.82	90.86	9.14	99.12	0.88	10.02
	0.40	Vegetation	0.83	93.50	82.39	17.61	93.47	6.53	24.14
		Non-Veg	0.83	93.50	97.78	2.22	93.51	6.49	8.71
HPEM		Vegetation	0.90	96.12	88.43	11.57	97.39	2.61	14.18
		Non-Veg	0.90	96.12	99.09	0.91	95.69	4.31	5.22