基于多源遥感影像融合的武汉市土地利用分类方法研究

doi:10.11870/cjlyzyyhj201610014

摘要/Abstract

摘要： 准确高效的获取土地利用信息，对于合理利用和开发土地资源具有十分重要的意义。在快速城镇化地区，土地利用活动频繁且密集，土地利用格局演变十分剧烈，增加了城市土地利用精准分类的不确定性；且受环境气候和云雨天气影响增加了有效光学影像获取的难度。为提高城市土地分类精度，该文选取武汉市中心城区为研究案例，以Sentinel-1A和Landsat8 OLI影像为数据源，采用Gram-Schmidt变换方法进行影像融合，选取最大似然、支持向量机、CART决策树、BP神经网络等4种分类方法对融合的影像进行分类，提取了研究区土地利用信息，并对其进行分析。进一步，通过与光学影像的分类结果对比，探究了Sentinel-1A和Landsat8 OLI融合影像在土地利用信息提取方面是否具有优势。研究结果表明：（1）对比其他3种方法，CART决策树分类方法对于融合后的影像分类精度最高，总体分类精度和Kappa系数分别达到88.55%和0.841 4；（2）与光学影像相比，Sentinel-1A和Landsat8 OLI融合影像可以更有效地获取高精度城市土地利用信息；（3）基于多源遥感影像融合的CART决策树分类方法是获取研究区高精度土地利用信息的一种行之有效的技术手段。研究成果可为快速城镇化区域的土地利用分类提供参考。

关键词: 城市土地利用分类, 影像融合, Sentinel-1A, Landsat8 OLI, 武汉市

Abstract: It is of great significance to acquire accurate and efficient land use information for rational use and development of land resources. In areas undergoing rapid urbanization, land use activity is frequent and intensive, and the land use pattern changes very sharply, which increases the uncertainty of the precise classification of urban land use. At the same time, the impact of environment and weather conditions increases the difficulty of obtaining effective optical images. In order to improve the precision of the urban land classification, in this paper we selected the city center area of Wuhan as a case and took Sentinel-1A and Landsat 8 OLI images as the data source, using the Gram-Schmidt transformation method for image fusion. We selected four classification methods to classify the fusion image, including maximum likelihood, support vector machine, CART decision tree and BP neural network to extract the information of land use in the study area. Further, by comparing with the results of the classification of the optical image, we explored whether the Sentinel-1 A and Landsat8 OLI fusion image had the advantage in terms of land use information extraction. The research results showed that:(1) compared with the other 3 methods, the CART decision tree classification method had the highest classification accuracy for the fused image, the overall classification accuracy and Kappa coefficient reached 88.55% and 0.8414; (2) compared with the optical image, Sentinel-1A and Landsat 8 OLI fusion image can obtain high precision urban land use information more effectively; (3) the CART decision tree classification method based on multi source remote sensing image fusion was an effective technique to obtain the high precision land use information in the research area. The results can provide reference for land use classification in the rapid urbanization region.

Key words: urban land use classification, image fusion, Sentinel-1A, Landsat8 OLI, Wuhan City

中图分类号:

TP79

翟天林, 金贵, 邓祥征, 李兆华, 王润. 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.

ZHAI Tian-lin, JIN Gui, DENG Xiang-zheng, LI Zhao-hua, WANG Run. 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.

参考文献

[1] 史利江, 王圣云, 姚晓军, 等.1994~2006年上海市土地利用时空变化特征及驱动力分析[J].长江流域资源与环境, 2012, 21(12):1468-1479.[SHI L J, WANG S Y, YAO X J, et al. Spatial and temporal variation characteristics of land use and its driving force in Shanghai city from 1994 to 2006[J]. Resources and Environment in the Yangtze Basin, 2012, 21(12):1468-1479.]
[2] 杜国明, 匡文慧, 孟凡浩, 等.巴西土地利用/覆盖变化时空格局及驱动因素[J].地理科学进展, 2015, 34(1):73-82.[DU G M, KUANG W H, MENG F H, et al. Spatiotemporal pattern and driving forces of land use/cover change in Brazil[J]. Progress in Geography, 2015, 34(1):73-82.]
[3] 屈芳青."3S"支持下的成都LUCC研究[D].成都:中国科学院成都山地灾害与环境研究所硕士学位论文, 2007.[QU F Q. Chengdu LUCC research supported by "3S"[D]. Chengdu:Master Dissertation of Institute of Mountain Hazards and Environment, CAS, 2007.]
[4] CHEN Y H, SU W, LI J, et al. Hierarchical object oriented classification using very high resolution imagery and LIDAR data over urban areas[J]. Advances in Space Research, 2009, 43(7):1101-1110.
[5] 邓劲松, 李君, 王珂.基于多时相PCA光谱增强和多源光谱分类器的SPOT影像土地利用变化检测[J].光谱学与光谱分析, 2009, 29(6):1627-1631.[DENG J S, LI J, WANG K. Detecting land use change using PCA-Enhancement and multi-source classifier from SPOT images[J]. Spectroscopy and Spectral Analysis, 2009, 29(6):1627-1631.]
[6] FRANKE J, ROBERTS D A, HALLIGAN K, et al. Hierarchical multiple endmember spectral mixture analysis (MESMA) of hyperspectral imagery for urban environments[J]. Remote Sensing of Environment, 2009, 113(8):1712-1723.
[7] AGUIRRE-GUTIÉRREZ J, SEIJMONSBERGEN A C, DUIVENVOORDEN J F. Optimizing land cover classification accuracy for change detection, a combined pixel-based and object-based approach in a mountainous area in Mexico[J]. Applied Geography, 2012, 34:29-37.
[8] 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):5167-5173.
[9] FUNG T. An assessment of TM imagery for land-cover change detection[J]. IEEE Transactions on Geoscience and Remote Sensing, 1990, 28(4):681-684.
[10] 刘盛和, 吴传钧, 沈洪泉.基于GIS的北京城市土地利用扩展模式[J].地理学报, 2000, 55(4):407-416.[LIU S H, WU C J, SHEN H Q. A GIS based model of urban land use growth in Beijing[J]. Acta Geographica Sinica, 2000, 55(4):407-416.]
[11] 周春山, 叶昌东.中国特大城市空间增长特征及其原因分析[J].地理学报, 2013, 68(6):728-738.[ZHOU C S, YE C D. Features and causes of urban spatial growth in Chinese metropolises[J]. Acta Geographica Sinica, 2013, 68(6):728-738.]
[12] 陈劲松, 韩宇, 陈工, 等.基于多源遥感信息融合的广东省土地利用分类方法——以雷州半岛为例[J].生态学报, 2014, 34(24):7233-7242.[CHEN J S, HAN Y, CHEN G, et al. Land utilization mapping in Guangdong Province based on integration of optical and SAR remote sensing data[J]. Acta Geographica Sinica, 2014, 34(24):7233-7242.]
[13] 于泓峰, 张显峰.光学与微波遥感的新疆积雪覆盖变化分析[J].地球信息科学学报, 2015, 17(2):244-252.[YU H F, ZHANG X F. Retrieval and analysis of snow-covered days in Xinjiang based on optical and microwave remote sensing data[J]. Journal of Geo-Information Science, 2015, 17(2):244-252.]
[14] POHL C, VAN GENDEREN J L. Multisensor image fusion in remote sensing:concepts, methods and applications[J]. International Journal of Remote Sensing, 1998, 19(5):823-854.
[15] 于欢, 孔博, 杨德生.基于规则替换法的多源遥感数据地表覆盖信息提取[J].国土资源遥感, 2011(4):87-91.[YU H, KONG B, YANG D S. Land-cover information extraction using multi-source remote sensing images based on rule-based substitution methods[J]. Remote Sensing for Land & Resources, 2011(4):87-91.]
[16] 黄明祥, 史舟, 李艳.SAR遥感技术在农业土地利用遥感调查的应用[J].农业工程学报, 2004, 20(6):133-137.[HUANG M X, SHI Z, LI Y. Application of SAR remote sensing to agricultural land use investigation[J]. Transactions of The CSAE, 2004, 20(6):133-137.]
[17] WANG Y T, AINSWORTH T L, LEE J S. Estimation of the orientation and shape parameters of canopy scatterers from POLSAR observations[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012, 5(3):835-847.
[18] LI X F. The first Sentinel-1 SAR image of a typhoon[J]. Acta Oceanologica Sinica, 2015, 34(1):1-2.
[19] CLAPHAM JR W B. Continuum-based classification of remotely sensed imagery to describe urban sprawl on a watershed scale[J]. Remote Sensing of Environment, 2003, 86(3):322-340.
[20] 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.
[21] 张海龙, 蒋建军, 吴宏安, 等.SAR与TM影像融合及在BP神经网络分类中的应用[J].测绘学报, 2006, 35(3):229-233, 239.[ZHANG H L, JIANG J J, WU H A, et al. The BP neural network classification based on the fusion of SAR and TM images[J]. Acta Geodaetica et Cartographica Sinica, 2006, 35(3):229-233, 239.]
[22] 吴后建, 王学雷, 宁龙梅, 等.土地利用变化对生态系统服务价值的影响——以武汉市为例[J].长江流域资源与环境, 2006, 15(2):185-190.[WU H J, WANG X L, NING L M, et al. Effects of land use change on ecosystem services value——a case study in Wuhan city[J]. Resources and Environment in the Yangtze Basin, 2006, 15(2):185-190.]
[23] 金贵, 王占岐, 姚小薇, 等.国土空间分区的概念与方法探讨[J].中国土地科学, 2013, 27(5):48-53.[JIN G, WANG Z Q, YAO X W, et al. Concept and methods for spatial zoning[J]. China Land Sciences, 2013, 27(5):48-53.]
[24] CLAYTON D G. Algorithm AS 46:Gram-schmidt orthogonalization[J]. Journal of the Royal Statistical Society Series C (Applied Statistics), 1971, 20(3):335-338.
[25] 李存军, 刘良云, 王纪华, 等.两种高保真遥感影像融合方法比较[J].中国图象图形学报, 2004, 9(11):1376-1385.[LI C J, LIU L Y, WANG J H, et al. Comparison of two methods of fusing remote sensing images with fidelity of spectral information[J]. Journal of Image and Graphics, 2004, 9(11):1376-1385.]
[26] STEIN A, BASTIAANSSEN W G M, DE BRUIN S, et al. Integrating spatial statistics and remote sensing[J]. International Journal of Remote Sensing, 1998, 19(9):1793-1814.
[27] 骆剑承, 王钦敏, 马江洪, 等.遥感图像最大似然分类方法的EM改进算法[J].测绘学报, 2002, 31(3):234-239.[LUO J C, WANG Q M, MA J H, et al. The EM-based maximum likelihood classifier for remotely sensed data[J]. Acta Geodaetica et Cartographica Sinica, 2002, 31(3):234-239.]
[28] 魏长寿, 唐秋华, 丁继胜, 等.最大似然分类法在多波束底质分类中的应用[J].海洋测绘, 2005, 25(4):5-7.[WEI C S, TANG Q H, DING J S, et al. Seafloor classification from multibeam backscatter data using maximum likelihood analysis[J]. Hydrographic Surveying and Charting, 2005, 25(4):5-7.]
[29] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297.
[30] 田源, 塔西甫拉提·特依拜, 丁建丽, 等.基于支持向量机的土地覆被遥感分类[J].资源科学, 2008, 30(8):1268-1274.[TIAN Y, TASHPOLAT T, DING J L, et al. Land cover classification using remote sensing image based on support vector machines[J]. Resources Science, 2008, 30(8):1268-1274.]
[31] 梁亮, 杨敏华, 李英芳.基于ICA与SVM算法的高光谱遥感影像分类[J].光谱学与光谱分析, 2010, 30(10):2724-2728.[LIANG L, YANG M H, LI Y F. Hyperspectral remote sensing image classification based on ICA and SVM algorithm[J]. Spectroscopy and Spectral Analysis, 2010, 30(10):2724-2728.]
[32] 王新明, 梁维泰, 周方, 等.基于支持向量机和Getis因子的高分辨率遥感图像分类[J].地理与地理信息科学, 2008, 24(4):16-19, 24.[WANG X M, LIANG W T, ZHOU F, et al. Study on classification of high spatial resolution remotely sensed imagery with SVM and local spatial statistics Getis-Ord Gi[J]. Geography and Geo-Information Science, 2008, 24(4):16-19, 24.]
[33] BREIMAN L, FRIEDMAN J H, OLSHEN R, et al. Classification and regression trees[J]. Journal of the American Statistical Association, 1984, 81(1):17-23.
[34] 董连英, 邢立新, 潘军, 等.高光谱图像植被类型的CART决策树分类[J].吉林大学学报(信息科学版), 2013, 31(1):83-89.[DONG L Y, XING L X, PAN J, et al. Vegetation classification in hyperspectral image with CART decision tree[J]. Journal of Jilin University (Information Science Edition), 2013, 31(1):83-89.]
[35] RUMELHART D E, HINTON G E, WILLIAMS R J. Learning representations by back-propagating errors[J]. Nature, 1986, 323(6088):533-536.
[36] 李明诗, 彭世揆, 周林, 等.基于ASTER数据的决策树自动构建及分类研究[J].国土资源遥感, 2006(3):33-36.[LI M S, PENG S K, ZHOU L, et al. A study of automated construction and classification of decision tree classifiers based on ASTER remotely sensed datasets[J]. Remote Sensing for Land & Resources, 2006(3):33-36.]
[37] 吴健生, 潘况一, 彭建, 等.基于QUEST决策树的遥感影像土地利用分类——以云南省丽江市为例[J].地理研究, 2012, 31(11):1973-1980.[WU J S, PAN K Y, PENG J, et al. Research on the accuracy of TM images land-use classification based on QUEST decision tree:a case study of Lijiang in Yunnan[J]. Geographical Research, 2012, 31(11):1973-1980.]

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed