基于空间光谱信息协同的城市不透水层提取方法比较研究

doi:10.12302/j.issn.1000-2006.201911012

国家林草科技领军期刊
中国精品科技期刊
中国高校百佳科技期刊
江苏省新闻出版政府奖期刊奖
RCCSE林学权威期刊（A+）
CSCD核心期刊
Scopus数据库收录期刊
中文核心期刊
SCD核心期刊

作者加群：102861116

微信公众号：南京林业大学学报

高级检索

南京林业大学学报（自然科学版） ›› 2021, Vol. 45 ›› Issue (1): 212-218.doi: 10.12302/j.issn.1000-2006.201911012

基于空间光谱信息协同的城市不透水层提取方法比较研究

范佳辉¹(), 张亚丽¹, 李明诗¹^,²^,^*()

1.南京林业大学林学院,江苏南京 210037
2.南京林业大学,南方现代林业协同创新中心,江苏南京 210037

收稿日期:2019-11-06 接受日期:2020-03-15 出版日期:2021-01-30 发布日期:2021-02-01
通讯作者: 李明诗
基金资助:
国家自然科学基金项目(31971577);国家自然科学基金项目(31670552);江苏省青蓝工程项目(2017)

Comparing four methods for extracting impervious surfaces using spectral information in synergy with spatial heterogeneity of remotely sensed imagery

FAN Jiahui¹(), ZHANG Yali¹, LI Mingshi¹^,²^,^*()

1. College of Forestry, Nanjing Forestry University, Nanjing 210037,China
2. Co-Innovation Center for the Sustainable Forestry in Southern China, Nanjing Forestry University, Nanjing 210037,China

Received:2019-11-06 Accepted:2020-03-15 Online:2021-01-30 Published:2021-02-01
Contact: LI Mingshi

摘要/Abstract

摘要：

【目的】利用不同的端元提取方法及混合像元分解算法计算南京市2018年城市不透水层覆盖度,评估各方法的精度,为城市可持续发展提供可靠的基础数据支撑。【方法】采用Landsat 8 OLI遥感影像,基于像元纯度指数(pixel purity index,PPI)并考虑空间光谱信息协同提出空间像元纯度指数(spatial pixel purity index,SPPI),精炼提纯植被、裸土、高反照度不透水层及低反照度不透水层4种类型端元,利用线性混合光谱模型(linear mixed spectral model,LMM)、混合调制匹配滤波(mixture tuned matched filtering,MTMF)、双线性混合光谱模型(bilinear mixed spectral model,BMM)及BP神经网络(BP neural network,BPNN)算法提取南京城市不透水层,采用同年的Google Earth遥感影像目视解译结果对提取的不透水层丰度进行精度验证。【结果】SPPI能有效结合多光谱波段的光谱信息和全色波段的空间信息,提高端元提取精度并减少计算量;同时,基于SPPI的BP神经网络算法提取精度最高,为90.45%;而基于PPI的线性混合光谱模型精度最低,为80.62%。BP神经网络算法在复杂城市中的解混精度高于线性混合光谱模型、混合调制匹配滤波和双线性混合光谱模型。【结论】采用全色波段像元亮度空间异质性辅助提取端元的方法,用空间信息弥补多光谱波段光谱信息较少的缺点,对于改进或发展适用于中/高分辨率多光谱影像的端元提取方法具有一定的参考价值,将其与神经网络模型结合可以在城市不透水层提取中推广应用。

关键词: 城市不透水层, 空间像元纯度指数, 混合调制匹配滤波, 双线性混合光谱模型, BP神经网络, 线性混合光谱模型

Abstract:

【Objective】 In order to provide a reliable foundation for the sustainable development of Nanjing City, this study compared different endmember extraction methods and mixed pixel decomposition algorithms to calculate the coverage of urban impervious surfaces (UISs) in Nanjing in 2018, and evaluated the accuracy of each method. 【Method】 Using Landsat 8 OLI images, an improved spatial pixel purity index (SPPI), based on the pixel purity index (PPI), was first proposed to refine or purify the endmembers for four land cover types including vegetation, bare soil, high albedo UISs and low albedo UISs. Next, based on the two extracted suites of endmembers derived from PPI and SPPI, a linear spectral mixed model, a mixture tuned matched filtering, a bilinear mixed spectral model and a BP neural network were implemented to extract UISs in Nanjing. The extracted UIS abundance was validated using visual interpretation of high spatial resolution Google Earth images for 2018. 【Result】 The results showed that SPPI could improve the identification accuracy of endmembers effectively and reduce the computational load by combining the spectral information from multi-spectral bands with the spatial heterogeneity of the panchromatic band. The UIS extraction accuracy of the SPPI-based BP network algorithm was the highest, at 90.45%, while the PPI-based linear spectral mixed model was the lowest at 80.62%. Overall, the BP network model outperformed the other three models in UIS extraction, regardless of whether PPI-based or SPPI-based endmembers were used. 【Conclusion】 The proposed method of using the panchromatic band to assist with extracting endmembers effectively integrated spatial heterogeneity to compensate for inadequate spectral information in the multispectral bands. The study provides methodological references to improve or develop means for endmember extraction from medium/high-resolution multispectral images. Additionally, integration of the SPPI and BP network model can be popularized in the UIS extraction domain.

Key words: urban impervious surface, spatial pixel purity index(SPPI), mixture tuned matched filtering(MTMF), bilinear mixed spectral model(BMM), BP neural network(BPNN), linear mixing spectral model(LMM)

中图分类号:

P237

范佳辉,张亚丽,李明诗. 基于空间光谱信息协同的城市不透水层提取方法比较研究[J]. 南京林业大学学报（自然科学版）, 2021, 45(1): 212-218.

FAN Jiahui, ZHANG Yali, LI Mingshi. Comparing four methods for extracting impervious surfaces using spectral information in synergy with spatial heterogeneity of remotely sensed imagery[J].Journal of Nanjing Forestry University (Natural Science Edition), 2021, 45(1): 212-218.DOI: 10.12302/j.issn.1000-2006.201911012.

图/表 6

图1

图2

图3

图4

表1

图5

参考文献 27

[1]	BRABEC E, SCHULTE S, RICHARDS P L. Impervious surfaces and water quality:a review of current literature and its implications for watershed planning[J]. J Plan Lit, 2002,16(4):499-514.DOI: 10.1177/088541202400903563. doi: 10.1177/088541202400903563
[2]	SHEN W J, WU T, LI M S. Mapping urban impervious surfaces of Nanjing from the dense landsat imagery[C]// 2012 5th International Congress on Image and Signal Processing,16-18 Oct 2012,Chongqing,China.IEEE, 2012:1068-1072.DOI: 10.1109/CISP.2012.6469893.
[3]	仵宏基. 基于长时间序列陆地卫星数据的南京城市不透水层动态制图研究[D]. 南京:南京林业大学, 2017.
	WU H J. Dynamic mapping of urban impervious surfaces in Nanjing based on landsat long-term time series observations[D]. Nanjing:Nanjing Forestry University, 2017.
[4]	CAO S S, HU D Y, ZHAO W J, et al. Monitoring changes in the impervious surfaces of urban functional zones using multisource remote sensing data:a case study of Tianjin,China[J]. Giscience Remote Sens, 2019,56(7):967-987.DOI: 10.1080/15481603.2019.1600110. doi: 10.1080/15481603.2019.1600110
[5]	吴志杰, 赵书河. 基于TM图像的“增强的指数型建筑用地指数”研究[J]. 国土资源遥感, 2012,24(2):50-55. doi: 10.6046/gtzyyg.2012.02.10
	WU Z J, ZHAO S H. A study of enhanced index-based built-up index based on landsat TM imagery[J]. Remote Sens Land Resour, 2012,24(2):50-55.DOI: 10.6046/gtzyyg.2012.02.10.
[6]	YANG J, HE Y H. Automated mapping of impervious surfaces in urban and suburban areas:linear spectral unmixing of high spatial resolution imagery[J]. Int J Appl Earth Obs Geoinformation, 2017,54:53-64.DOI: 10.1016/j.jag.2016.09.006. doi: 10.1016/j.jag.2016.09.006
[7]	甘玉泉. 高光谱遥感图像光谱解混方法研究及其应用[D]. 北京:中国科学院大学, 2018.
	GAN Y Q. Research and application of spectral unmixing method for hyperspectral remote sensing imagry[D]. Beijing:University of Chinese Academy of Sciences, 2018.
[8]	蓝金辉, 邹金霖, 郝彦爽, 等. 高光谱遥感影像混合像元分解研究进展[J]. 遥感学报, 2018,22(1):13-27.
	LAN J H, ZOU J L, HAO Y S, et al. Research progress on unmixing of hyperspectral remote sensing imagery[J]. J Remote Sens, 2018,22(1):13-27.DOI: 10.11834/jrs.20186502.
[9]	RIDD M K. Exploring a V-I-S (vegetation-impervious surface-soil) model for urban ecosystem analysis through remote sensing:comparative anatomy for cities[J]. Int J Remote Sens, 1995,16(12):2165-2185.DOI: 10.1080/01431169508954549. doi: 10.1080/01431169508954549
[10]	WU C S, MURRAY A T. Estimating impervious surface distribution by spectral mixture analysis[J]. Remote Sens Environ, 2003,84(4):493-505.DOI: 10.1016/S0034-4257(02)00136-0. doi: 10.1016/S0034-4257(02)00136-0
[11]	杨斌, 王斌. 高光谱遥感图像非线性解混研究综述[J]. 红外与毫米波学报, 2017,36(2):173-185.
	YANG B, WANG B. Review of nonlinear unmixing for hyperspectral remote sensing imagery[J]. J Infrared Millim Waves, 2017,36(2):173-185.DOI: 10.11972/j.issn.1001-9014.2017.02.009.
[12]	LEE D D, SEUNG H S. Learning the parts of objects by non-negative matrix factorization[J]. Nature, 1999,401(6755):788.DOI: 10.1038/44565. doi: 10.1038/44565 pmid: 10548103
[13]	ZHUO L, SHI Q L, TAO H Y, et al. An improved temporal mixture analysis unmixing method for estimating impervious surface area based on MODIS and DMSP-OLS data[J]. ISPRS J Photogramm Remote Sens, 2018,142:64-77.DOI: 10.1016/j.isprsjprs.2018.05.016. doi: 10.1016/j.isprsjprs.2018.05.016
[14]	ALTMANN Y, HALIMI A, DOBIGEON N, et al. Supervised nonlinear spectral unmixing using a postnonlinear mixing model for hyperspectral imagery[J]. IEEE Trans Image Process, 2012,21(6):3017-3025.DOI: 10.1109/TIP.2012.2187668. doi: 10.1109/TIP.2012.2187668 pmid: 22345533
[15]	FAN W Y, HU B X, MILLER J, et al. Comparative study between a new nonlinear model and common linear model for analysing laboratory simulated-forest hyperspectral data[J]. Int J Remote Sens, 2009,30(11):2951-2962. DOI: 10.1080/01431160802558659. doi: 10.1080/01431160802558659
[16]	夏俊士, 杜培军, 曹文. 基于非线性光谱混合模型的遥感影像提取城市不透水层[J]. 光子学报, 2011,40(1):13-18. doi: 10.3788/gzxb20114001.0013
	XIA J S, DU P J, CAO W. Urban impervious surface extraction from remote sensing image based on nonlinear spectral mixture model[J]. Acta Photonica Sin, 2011,40(1):13-18.DOI: 10.3788/gzxb20114001.0013.
[17]	CHANG C I, PLAZA A. A fast iterative algorithm for implementation of pixel purity index[J]. IEEE Geosci Remote Sensing Lett, 2006,3(1):63-67.DOI: 10.1109/lgrs.2005.856701. doi: 10.1109/LGRS.2005.856701
[18]	CHANG C I, WU C C, LIU W, et al. A new growing method for simplex-based endmember extraction algorithm[J]. IEEE Trans Geosci Remote Sens, 2006,44(10):2804-2819.DOI: 10.1109/TGRS.2006.881803. doi: 10.1109/TGRS.2006.881803
[19]	CRAIG M D. Minimum-volume transforms for remotely sensed data[J]. IEEE Trans Geosci Remote Sensing, 1994,32(3):542-552.DOI: 10.1109/36.297973. doi: 10.1109/36.297973
[20]	FUHRMANN D R. Simplex shrink-wrap algorithm[J]. Proceedings of SPIE-the International Society for Optical Engineering, 1999,3718(5):501-511. DOI: 10.1117/12.359990.
[21]	焦俊男. 基于空间光谱信息协同的多光谱影像端元精确提取方法研究[D]. 南京:南京大学, 2017.
	JIAO J N. Integrating spatial spectral information for multispectral image refined endmember extraction[D]. Nanjing:Nanjing University, 2017.
[22]	南京市规划和自然局. 2018年季度国土资源综合统计报告[R/OL].(2019-04-28)[2019-10-29] http://zrzy.jiangsu.gov.cn/gtapp/nrglIndex.action?type=2&messageID=2c9082b56a2e4062016a62ac17c40a60.html.
[23]	VERMOTE E, JUSTICE C, CLAVERIE M, et al. Preliminary analysis of the performance of the Landsat 8/OLI land surface reflectance product[J]. Remote Sens Environ, 2016,185:46-56.DOI: 10.1016/j.rse.2016.04.008. doi: 10.1016/j.rse.2016.04.008 pmid: 32020955
[24]	徐涵秋. 利用改进的归一化差异水体指数(MNDWI)提取水体信息的研究[J]. 遥感学报, 2005,9(5):589-595. doi: 10.11834/jrs.20050586
	XU H Q. A study on information extraction of water body with the modified normalized difference water index (MNDWI)[J]. J Remote Sens, 2005,9(5):589-595.DOI: 10.3321/j.issn:1007-4619.2005.05.012.
[25]	苏红军, 刘浩. 一种利用空间和光谱信息的高光谱遥感多分类器动态集成算法[J]. 国土资源遥感, 2017,29(2):15-21.
	SU H J, LIU H. a novel dynamic classifier selection algorithm using spatial-spectral information for hyperspectral classification[J]. Remote Sens Land Resour, 2017,29(2):15-21.DOI: 10.6046/gtzyyg.2017.02.03.
[26]	王靖, 吴见. 融入空间信息的湿地信息提取技术[J]. 南京林业大学学报(自然科学版), 2014,38(4):19-22.
	WANG J, WU J. Wetland information extraction technology integrated by spatial information[J]. J Nanjing For Univ (Nat Sci Ed), 2014,57(4):19-22.DOI: 10.3969/j.issn.1000-2006.2014.04.004.
[27]	杨斌, 王斌, 吴宗敏. 基于双线性混合模型的高光谱图像非线性光谱解混[J]. 红外与毫米波学报, 2018,37(5):631-641.
	YANG B, WANG B, WU Z M. Nonlinear spectral unmixing for hyperspectral imagery based on bilinear mixture models[J]. J Infrared Millim Waves, 2018,37(5):631-641.DOI: 10.11972/j.issn.1001-9014.2018.05.017.

点号 No.	Google Earth	PPI_LSMM	PPI_MTMF	PPI_BMM	PPI_BPNN	SPPI_LSMM	SPPI_MTMF	SPPI_BMM	SPPI_BPNN
1	0.126 5	0.141 0	0.331 7	0.237 1	0.225 0	0.297 1	0.303 2	0.213 8	0.224 6
2	0.365 5	0.287 1	0.262 7	0.389 8	0.316 0	0.297 8	0.257 3	0.396 7	0.329 6
3	0.475 7	0.309 1	0.421 6	0.546 8	0.449 6	0.587 4	0.402 3	0.587 1	0.445 7
…	…	…	…	…	…	…	…	…	…
49	0.216 1	0.106 8	0.176 3	0.149 5	0.186 2	0.116 4	0.177 1	0.156 4	0.186 4
50	0.225 8	0.321 2	0.322 4	0.331 7	0.281 4	0.329 8	0.285 2	0.321 7	0.291 8
窗口平均精度/% average accuracy		80.62	83.17	87.56	88.37	81.37	86.42	89.50	90.45

基于空间光谱信息协同的城市不透水层提取方法比较研究

Comparing four methods for extracting impervious surfaces using spectral information in synergy with spatial heterogeneity of remotely sensed imagery

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 27

相关文章 4

编辑推荐

Metrics

本文评价

作者

读者

审稿

[1]	孙铭辰, 姜立春. 基于机器学习算法的樟子松立木材积预测[J]. 南京林业大学学报（自然科学版）, 2023, 47(1): 31-37.
[2]	沈剑波,雷相东,李玉堂,兰莹. 基于BP神经网络的长白落叶松人工林林分平均高预测[J]. 南京林业大学学报（自然科学版）, 2018, 42(02): 147-154.
[3]	佟达,张燕,宋魁彦. 人工林胡桃楸幼龄期与成熟期界定方法的比较[J]. 南京林业大学学报（自然科学版）, 2013, 37(03): 103-109.
[4]	赵茂程1,郑加强1,凌小静2. 基于神经网络的树形识别系统研究[J]. 南京林业大学学报（自然科学版）, 2005, 29(04): 11-14.