分类图斑概括的一种自适应方法—以遥感图像土地利用分类为例

doi:10.11873/j.issn.1004-0323.2016.5.0994

遥感技术与应用

2016, Vol. 31

Issue (5): 994-1002 DOI: 10.11873/j.issn.1004-0323.2016.5.0994

遥感应用

分类图斑概括的一种自适应方法—以遥感图像土地利用分类为例

涂媛杰¹,周坚华²

(1.华东师范大学地理科学学院,上海 200241;
2.华东师范大学地理信息科学教育部重点实验室,上海 200241)

Self-adaptive Generalization of Classified Patch—A Case Study on Land Use Classification from Remotely Sensed Imagery

Tu Yuanjie¹,Zhou Jianhua²

(1.Geography,East China Normal University,Shanghai 200241,China;
2.Key Lab of Geographical Information Science,Ministry of Education,
East China Normal University,Shanghai 200241,China)

全文: PDF(14572 KB)

摘要：

从遥感图像监督分类结果到矢量对象的转换是遥感技术领域的一个瓶颈问题。提出了一种“分类图斑自适应概括”(Self-adaptive Generalization of Classified patch,SGCP)的方法,是针对这一问题的新尝试。SGCP能实现从破碎图斑到完整图像对象的自动转换,它由如下运算组成:①以形态学开启和形状系数分离道路与其他不透水表面;②以面积过滤和数学形态学操作去除噪声,以使图斑完整;③以递归凸残差回补简化图斑边界;④以膨胀和面积占优方法消除图斑裂隙;⑤以凸节点减少率评估图斑概括度,并同时以面积保持和分类精度保持评估概括精度;直至形成指定概括度的对象。概括运算的主要参数(如结构元素尺寸、递归次数、邻域窗口尺寸等)均由计算机自适应确定,同时预留部分用户调节参数,在自动概括的同时,允许人工干预概括程度。经Matlab仿真测试,该方法可以在保持分类精度与获取概括对象之间取得较好平衡。当图斑简化度上升22.9%时,面积平均变化仅为2.7%,分类精度仅平均下降0.72%。


关键词： 图斑概括; 二值形态学; 凸残差; 形状系数; 自适应参数化

Abstract:

Pixels and patches allocated by supervised classification are often very scattered and cluttered.To make these classified patches more complete to form image objects and with only tolerable errors,a new algorithm,named Self\|adaptive Generalization of Classified Patch (SGCP),has been proposed.It uses some typical algorithms of both image analysis and map generalization,and has sure progress in the combined applications of the two.By using SGCP,it has been achieved to conduct generalization of classified patches of land use in a self\|adaptive way.Meanwhile,a better balance between degree and precision of the generalization can be promised.
There are six steps to conduct SGCP:①performing a supervised classification in a multi\|descriptor space;②separating road from the rest patches of impervious surface via binary morphology operations and by using shape descriptors;③removing noises and making these patches more complete via binary morphology operations and by filtering out smaller patches;④simplifying the boundary of a patch by recursively backfilling its convex residuals into a convex hill of the patch;⑤eliminating gaps between patches by merging the gaps into surrounding larger patches and ⑥ assessing the generalization degree of a patch by checking the vertex reduction rate of a convex hill of the patch and,in the same time,assessing the generalization accuracy by checking whether the area of each class and the global accuracy of all the classes are maintained as well as possible.Some main parameters,such as size of structure element,recursion times,neighboring size etc.,are self\|adaptively determined.In addition,there are several reserved parameters to allow the degree of generalization adjustable by user as the user is unsatisfied with the results of automatic generalization.Simulation tests with Matlab show that by using the algorithm proposed in this paper,a proper balance between the degree and accuracy of generalization can often be guaranteed.An increase of 22.9% in the generalization degree will lead only a decrease of 0.72% in the global accuracy and a change of 2.72% in the patch area.

Key words: Patch generalization Binary morphology Convex residuals Shape factor Self-adaptive parameterization

收稿日期: 2015-07-02 出版日期: 2016-11-25

TP 75

基金资助:

国家理科基地科研训练及科研能力提高项目（J1310028）资助。

通讯作者: 周坚华（1956-），女，上海人，副教授，硕士生导师，主要从事图像智能识别和生态遥感研究。Email:jhzhou@geo.ecnu.edu.cn。

作者简介: 涂媛杰（1995-），女，江西南昌人，硕士研究生，主要从事遥感与地理信息系统研究。Email:tuzement@126.com。

	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
	涂媛杰
	周坚华

引用本文:

涂媛杰,周坚华. 分类图斑概括的一种自适应方法—以遥感图像土地利用分类为例[J]. 遥感技术与应用, 2016, 31(5): 994-1002.

Tu Yuanjie,Zhou Jianhua. Self-adaptive Generalization of Classified Patch—A Case Study on Land Use Classification from Remotely Sensed Imagery. Remote Sensing Technology and Application, 2016, 31(5): 994-1002.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2016.5.0994 或 http://www.rsta.ac.cn/CN/Y2016/V31/I5/994

［1］Chen G,Hay G J,Carvalho L M T,et al.Object-based Change Detection［J］.International Journal of Remote Sensing,2012,33(14):4434-4457.

［2］Zhou Jianhua.Remote Sensing Image Analysis and Spatial Data Mining［M］.Shanghai:Shanghai Technology Education Press,2010.［周坚华.遥感图像分析与空间数据挖掘［M］.上海:上海科技教育出版社,2010.］

［3］Gao Fangqin,Wu Jianping.Detecting Linear Object in RS Image Recognition［J］.Chinese Journal of Scientific Instrument,2004,25(Sup.1):653-656.［高芳琴,吴健平.遥感图像识别中线性地物提取方法研究［J］.仪器仪表学报,2004,25(增刊1):653-656.］

［4］Pan Jianping,Li Zhi.Road Extraction based on Remote Sensing Classification and Mathematic Morphology［J］.Computer Engineering and Applications,2010,46(34):213-214.［潘建平,李治.基于遥感分类与数学形态学的道路信息提取［J］.计算机工程与应用,2010,46(34):213-214.］

［5］Huang H,Legarsky J J,Gudimetla S,et al.Post-classification Smoothing of Digital Classification Map of St.Louis,Missouri［C］//2004 IEEE International Geoscience and Remote Sensing Symposium,2004.IGARSS04,2004,(5):3039-3041.

［6］Lü Junbai.An Efficient Thinning Algorithm for Binary Images［J］.Computer Engineering,2003,29(18):147-148.［吕俊白.一种有效的二值图像细化算法［J］.计算机工程,2003,29(18):147-148.］

［7］Sheng Yehua,Tang Hong,Du Peijun,et al.One Fast Shape Preserving Morphological Thinning Algorithm［J］.Journal of Image and Graphics,2000,5(2):89-93.［盛业华,唐宏,杜培军,等.一种保形的快速图像形态细化算法［J］.中国图象图形学报,2000,5(2):89-93.］

［8］Guo L J,Moore J M.Post-classification Processing for Thematic Mapping based on Remotely Sensed Image Data［C］//1991,International Geoscience and Remote Sensing Symposium,1991.IGARSS91,1991:2203-2206.

［9］Lu Zhanwei,Hao Xiangyang.The Recognition and Extraction of Map Information based on Structural Features［J］.Journal of The Pla Institute of Surveying and Mapping,2001,18(2):107-109.［卢战伟,郝向阳.基于结构特征的地图信息识别与提取［J］.测绘学院学报,2001,18(2):107-109.］

［10］Wang Huilian,Wu Fang,Zhang Linlin.The Application of Mathematical Morphology and Pattern Recognition to Building Polygon Simplification［J］.Geodaetica et Cartographic Sinica,2005,34(3):269-276.［王辉连,武芳,张琳琳,等.数学形态学和模式识别在建筑物多边形化简中的应用［J］.测绘学报,2005,34(3):269-276.］ 

［11］Wang Jiayao,Wu Fang.The Principle and Methods of Automated Cartographic Generalization for Digital Maps［M］.Beijing:PLA Publishing House,1997.［王家耀,武芳.数字地图自动制图综合原理与方法［M］.北京:解放军出版社,1997.］

［12］Hicham L,Arnaud M,Driss A,et al.Classifier Fusion for Post-Classification of Textured Images［C］//2008 11th International Conference on Information Fusion,2008.

［13］Xu Si,Zhou Jianhua.Multi-dimensional Descriptors and Multi-scale Classification of Urban Architecture［J］.Remote Sensing Information,2014,29(2):15-17.［徐偲,周坚华.多描述符和多尺度城镇建筑分类［J］.遥感信息,2014,29(2):15-17.］ 

［14］Ye Q Z.A Fast Algorithm for Convex Hull Extraction in 2D Images［J］.Pattern Recognition Letters,1995,16(5):531-537.

［15］Zimmer Y,Tepper R,Akselrod S.An Improved Method to Compute the Convex Hull of A Shape in a Binary Image［J］.Pattern Recognition,1997,30(3):397-402.

［16］Bo Y,Chew L T.Convex Hull based Skew Estimation［J］.Pattern Recognition,2007,40(2):456-475.

［17］Osterom P V.Research and Development in Geo-information Generalization and Multiple Representation［J］.Computers Environment and Urban Systems,2009,33(5):303-310.

［18］Wu Jie,Li lin,Guo Renzhong,et al.On Automatic Evaluation Model of Digital Cartographic Generalization［J］.Developments in Surveying and Mapping,2002,27(2):34-39.［吴洁,李霖,郭仁忠,等.数字环境下地图综合结果自动评价模型的研究与应用［J］.测绘科学,2002,27(2):34-39.］

［19］Woojin P,Kiyun Y.Hybrid Line Simplification for Cartographic Generalization［J］.Pattern Recognition Letters,2011,32(9):1267-1273.

［20］Liu Pengcheng.Applications of Shape Recognition in Map Gerneralization［J］.Acta Geodaetica et Cartographics Sinica,2012,41(2):316-316.［刘鹏程.形状识别在地图综合中的应用研究［J］.测绘学报,2012,41(2):316-316］.

［21］Deng Min,Xu Zhen,Zhao Binbin,et al.A Transmission Model of Geometrical Information for Individual Spatial Objects in Cartographic Gerneralization［J］.Journal of Geo-information Science,2010,12(5):655-661.［邓敏,徐震,赵彬彬,等.地图概括中空间目标几何信息传递模型研究［J］.地球信息科学学报,2010,12(5):655-661.］

［22］Price J C.Estimating Vegetation Amount from Visible and Near Infrared Reflectances［J］.Remote Sensing of Environment,1992,41(92):29-34.

［23］Zhou Jianhua,Zhou Yifan,Mu Wangshu.Mathematic Descriptors for Identifying Plant Species:A Case Study on Urban Landscape Vegetation［J］.Journal of Remote Sensing,2011,15(3):524-538.［周坚华,周一凡,穆望舒.城镇绿地树种识别的数学描述符［J］.遥感学报,2011,15(3):524-538.］ 

［24］Zhou J H,Yu B L,Qin J.Multi-level Spatial Analysis for Change Detection of Urban Vegetation at Individual Tree Scale［J］.Remote Sensing,2014,6(9):9086-9103.

［25］Gu Xubojun,Yu Siyi,Jin Yemeng,et al.Complex Linear Topographic Features Extraction Using Mathematical Morphology and Hough Transform［J］.Remote Sensing Technology and Application,2014,29(4):689-694.［顾徐博君,虞思逸,金叶蒙,等.基于数学形态学和Hough变换的复杂形态线状地物提取方法［J］.遥感技术与应用,2014,29(4):689-694.］

［26］Zheng L,Wan L,Huo H,et al.A Noise Removal Approach for Object-based Classification of VHR Imagery via Post-classification［C］//2014 IEEE International Conference on Audio,Language and Image Processing (ICALIP),2014:915-920.

[1]	闫鹏飞,明冬萍. 尺度自适应的高分辨率遥感影像分水岭分割方法[J]. 遥感技术与应用, 2018, 33(2): 321-330.

Viewed

Full text

Abstract

Cited

Shared

Discussed