增强形态学建筑物指数应用于高分辨率影像中建筑物提取

测绘学报 ›› 2014, Vol. 43 ›› Issue (5): 514-520.

增强形态学建筑物指数应用于高分辨率影像中建筑物提取

胡荣明,黄小兵,黄远程

西安科技大学

收稿日期:2013-12-02 修回日期:2014-02-15 出版日期:2014-05-20 发布日期:2014-06-05
通讯作者: 黄远程 E-mail:yuancheng.huang@gmail.com
基金资助:
国家自然科学基金资助项目“高光谱遥感影像混合像元分解的稀疏分析方法研究”;陕西省教育厅专项科研计划“遥感影像亚像元信息提取的关键技术研究”;测绘遥感信息工程国家重点实验室开放基金“稀疏表达理论及其扩展应用于高光谱影像分类的研究”;西安科技大学校级培育基金“高光谱影像分类的稀疏分析理论研究”

An Enhanced Morphological Building Index for Building Extraction from High-Resolution Images

Received:2013-12-02 Revised:2014-02-15 Online:2014-05-20 Published:2014-06-05
Supported by:
Project;Project

摘要/Abstract

摘要：

分辨影像是城市地物覆盖分析的重要数据基础，本文提出了一种增强的形态学建筑物指数（EMBI），利用该指数和地物的几何形状约束来完成高分辨率建筑物的自动提取。本方法首先提取城市的不透水层特征，然后通过建立建筑物属性与形态学运算之间的关系得到了EMBI特征图像以增强对建筑物的描述，随后结合形状特征（长宽比，面积等）采用决策树分析的方法完成对建筑物的最终提取。为了验证本文提出的方法，利用华盛顿商业街的航空高分辨高光谱HYDICE影像和武汉洪山区的两幅QuickBird影像进行实验，实验的精度对比反映本文算法比MBI算法能获得更好的建筑物提取结果，其总体精度分别提高了7.31％，6.48％，7.83％，从而表明EMBI算法更可靠。

关键词: 高分辨率影像, 增强形态学建筑物指数, 城市不透水层, 形状特征, 决策树

Abstract:

High-resolution images are important basic data for urban surface features coverage analysis. This study proposed an enhanced morphological building index (EMBI) for automatic building extraction from high-resolution remotely sensed imagery. Firstly we extracted the urban impervious feature, and then EMBI was built based on a multi-scale white top-hat morphology reconstruction operation on the feature, which taking advantage of the relationship between the physical properties of buildings and morphological operators. Subsequently, the EMBI feature image combined with the shape characteristics (length-width ratio, area, etc.) completed the final building extraction using a decision tree method. In order to verify the proposed method, the Washington Commercial Street high-resolution hyperspectral HYDICE image and Wuhan Hongshan District two QuickBird images were used. In these experiments, the EMBI algorithm achieved satisfactory results and outperformed the MBI algorithm in terms of accuracies, i.e. the overall accuracy respectively increased by 7.31%, 6.48%, 7.83%, which proved that the EMBI algorithm performed more reliability.

Key words: high-resolution images, enhanced morphological building index, urban impervious feature, the shape characteristics, decision tree

中图分类号:

P237

胡荣明黄小兵黄远程. 增强形态学建筑物指数应用于高分辨率影像中建筑物提取[J]. 测绘学报, 2014, 43(5): 514-520.

参考文献

[1] M.Fauvel, Y.Tarabalka, J.A.Bennediktsson, J.Chanussot and J.C.Tilton. Advances in Spectral-Spatial Classification of Hyperspectral Images [J]. Proceedings of IEEE. 2013, 101 (3): 652 - 675.
[2] X Jin, Davis C H. Automated Building Extraction from High-resolution Satellite Imagery in Urban Areas Using Structural, Contextual, and Spectral Information [J]. EURASIP Journal on Applied Signal Processing. 2005, 14: 2196–2206.
[3] Lee D S, Shan J, Bethel J S. Class-guided Building Extraction from Ikonos Imagery [J]. Photogrammetric Engineering &Remote Sensing. 2003, 69(2):143–150.
[4] Huang X, Zhang L. An SVM Ensemble Approach Combining Spectral, Structural, and Semantic Features for the Classi?cation of High-Resolution Remotely Sensed Imagery [J]. IEEE Transactions on Geoscience and Remote Sensing, 2013, 51(1):257–272.
[5] Huang X, Zhang L. An Adaptive Mean-shift Analysis Approach for Object Extraction and Classification from Urban Hyperspectral Imagery [J]. IEEE Transactions on Geoscience and Remote Sensing, 2008, 46(12):4173–4185.
[6] Huang X, Zhang L, Li P. Classi?cation and Extraction of Spatial Features in Urban Areas Using High Resolution Multispectral Imagery [J]. IEEE Geoscience Remote Sensing Letter. 2007, 4(2): 260–264.
[7] Fauvel M, Benediktsson J A, Chanussot J, eta. Spectral and Spatial Classi?cation of Hyperspectral Data Using SVMs and Morphological Pro?les [J]. IEEE Trans Geosci Remote Sens. 2008, 46(11): 3804–3814.
[8] Huang X, Zhang L. A multiscale urban complexity index based on 3D wavelet transform for spectral–spatial feature extraction and classi?cation: an evaluation on the 8-channel WorldView-2 imagery [J]. International Journal of Remote Sensing. 2012, 33(8): 2641–2656.
[9] Lhomme S, He D C, Weber C, et.al. A New Approach to Building Identification from Very-high-spatial Resolution Images [J]. International Journal of Remote Sensing. 2009, 30(5): 1341–1354.
[10] Pesaresi M, Gerhardinger A, Kayitakire F. A Robust Built-up Area Presence Index by Anisotropic Rotation-invariant Textural Measure [J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2008, 1(3): 180–192.
[11] Huang X, Zhang L. A Multidirectional and Multiscale Morphological Index for Automatic Building Extraction from Multispectral GeoEye-1 imagery [J]. Photogramm Eng Remote Sens. 2011, 77(7): 721–732.
[12] Lu D, Hetrick S, Moran E. Impervious Surface Mapping with QuickBird Imagery [J]. International Journal of Remote Sensing. 2011, 32(9): 2519-2533.
[13] Pesaresi M, Benediktsson J A. A New Approach for the Morphological Segmentation of High-resolution Satellite Imagery [J]. IEEE Trans Geosci Remote Sens. 2001, 39(2): 309–320.
[14] Epifanio I, Soille P. Morphological Texture Features for Unsupervised and Supervised Segmentations of Natural Landscapes [J]. IEEE Trans Geosci Remote Sens. 2007, 45(4): 1074–1083.
[15] Benediktsson J A, Pesaresi M, Arnason K. Classi?cation and Feature Extraction for Remote Sensing Images from Urban Areas Based on Morphological Transformations [J]. IEEE Trans Geosci Remote Sens. 2003, 41(9): 1940–1949.
[16] F. Dell' Acqua, P. Gamba, A. Ferrai, J.A, Palmason, J.A, Benediktsson, and K. Amason. Exploiting Spectral and Spatial Information in Hyperspectral Urban Data with High Resolution [J] .IEEE Geoscience and Remote Sensing Letters. 2004, 1:322-326.
[17] Benediktsson J A, Palmason J A, Sveinsson J R. Classification of Hyperspectral Data from Urban Areas Based on Extended Morphological Profiles[J] . IEEE Transactions on Geoscience and Remote Sensing. 2005, 43(3): 480–491.