Estimation of Building Density with the Integrated Use of GF-1 PMS and Radarsat-2 Data

Building density, as a component of impervious surface fraction, is a significant indicator of population distribution as essentially all humans live and conduct activities in buildings. Because population spatialization usually occurs over large areas, large-scale building density estimation through a proper, time-efficient, and relatively precise way is urgently required. Therefore, this study constructed a decision tree by the Classification and Regression Tree (CART) algorithm combining synthetic aperture radar (SAR) with optical images. The input features included four spectral bands (B1–4) of GF-1 PMS imagery; Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and Ratio Built-up Index (RBI) derived from them; and backscatter intensity (BI) of Radarsat-2 SAR data. In addition, a new index called amended backscatter intensity (ABI), which takes the influence created by different spatial patterns into account, was introduced and calculated through fractal dimension and lacunarity. Result showed that before the integration use of multisource data, a model using B1–4, NDVI, NDWI, and RBI had the highest accuracy, with RMSE of 10.28 and R2 of 0.63 for Jizhou and RMSE of 20.34 and R2 of 0.36 for Beijing. In Comparison, the best model after combining two data sources (i.e., the model employing B1–4, NDVI, NDWI, RBI and ABI) reduced the RMSE to 8.93 and 16.21 raised the R2 to 0.80 and 0.64, respectively. The result indicated that the synergistic use of optical and SAR data has the potential to improve the building density estimation performance and the addition of ABI has a better capacity for improving the model than other input features.

[1]  Jordan Graesser,et al.  Generation of fine-scale population layers using multi-resolution satellite imagery and geospatial data , 2013 .

[2]  Giorgio Franceschetti,et al.  A canonical problem in electromagnetic backscattering from buildings , 2002, IEEE Trans. Geosci. Remote. Sens..

[3]  Hongsheng Zhang,et al.  Improving the impervious surface estimation with combined use of optical and SAR remote sensing images , 2014 .

[4]  Zhang Lei Wu Bing-fang Ma Xin-hui Li Jin-ye.  Study on Extracting Building Density and Floor Area Ratio Based on High Resolution Image , 2011 .

[5]  T. Esch,et al.  Settlement detection and impervious surface estimation in the Mekong Delta using optical and SAR remote sensing data , 2011 .

[6]  Heinz-Otto Peitgen,et al.  The science of fractal images , 2011 .

[7]  N. Lam,et al.  Examining Lacunarity Approaches in Comparison with Fractal and Spatial Autocorrelation Techniques for Urban Mapping , 2005 .

[8]  Pinliang Dong,et al.  Test of a new lacunarity estimation method for image texture analysis , 2000 .

[9]  Martin Schmidtab,et al.  Estimation of building density using Terrasar-X-Data , 2010, IGARSS 2010.

[10]  Junichi Susaki,et al.  Urban density mapping of global megacities from polarimetric SAR images , 2014 .

[11]  Liming Jiang,et al.  Quantifying Sub-pixel Urban Impervious Surface through Fusion of Optical and InSAR Imagery , 2009 .

[12]  Jinghui Yang,et al.  Block-regression based fusion of optical and SAR imagery for feature enhancement , 2010 .

[13]  N. Lam,et al.  An Evaluation of Fractal Methods for Characterizing Image Complexity , 2002 .

[14]  M. Bauer,et al.  Estimating and Mapping Impervious Surface Area by Regression Analysis of Landsat Imagery , 2007 .

[15]  Patrick Leinenkugel,et al.  The Combined Use of Optical and SAR Data for Large Area Impervious Surface Mapping , 2010 .

[16]  Shunlin Liang,et al.  Fractal analysis of remotely sensed images: A review of methods and applications , 2006 .

[17]  R. Engstrom,et al.  Spatial refinement of census population distribution using remotely sensed estimates of impervious surfaces in Haiti , 2010 .

[18]  Leo Breiman,et al.  Classification and Regression Trees , 1984 .

[19]  Alan T. Murray,et al.  Population Estimation Using Landsat Enhanced Thematic Mapper Imagery , 2007 .

[20]  Jianping Wu,et al.  Automated derivation of urban building density information using airborne LiDAR data and object-based method , 2010 .

[21]  Tat Soon Yeo,et al.  A novel lacunarity estimation method applied to SAR image segmentation , 2002, IEEE Trans. Geosci. Remote. Sens..

[22]  André Ricardo Backes,et al.  A new approach to estimate lacunarity of texture images , 2013, Pattern Recognit. Lett..

[23]  Pinliang Dong,et al.  Lacunarity for Spatial Heterogeneity Measurement in GIS , 2000, Ann. GIS.

[24]  Soe Win Myint,et al.  A study of lacunarity-based texture analysis approaches to improve urban image classification , 2005, Comput. Environ. Urban Syst..

[25]  Junichi Susaki,et al.  Urban-Area Extraction From Polarimetric SAR Images Using Polarization Orientation Angle , 2013, IEEE Geoscience and Remote Sensing Letters.

[26]  Wanxiao Sun.  Three New Implementations of the Triangular Prism Method for Computing the Fractal Dimension of Remote Sensing Images , 2006 .

[27]  Zheng Hu,et al.  Urban Building Density Estimation Based on the VIIRS Night-time Satellite Data——a Case of Nanjing , 2014 .

[28]  Nina S. N. Lam,et al.  Fractal Characterization of Hyperspectral Imagery , 1999 .

[29]  T. Schueler.  The importance of imperviousness , 1995 .

[30]  Qihao Weng,et al.  Improving Urban Impervious Surface Mapping by Linear Spectral Mixture Analysis and Using Spectral Indices , 2015 .

[31]  Shuqing Zhao,et al.  A comparative study of urban expansion in Beijing, Tianjin and Shijiazhuang over the past three decades , 2015 .

[32]  Limin Yang,et al.  An approach for mapping large-area impervious surfaces: synergistic use of Landsat-7 ETM+ and high spatial resolution imagery , 2003 .

[33]  Hui Lin,et al.  A comparison study of impervious surfaces estimation using optical and SAR remote sensing images , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[34]  Thomas Esch,et al.  Estimation of building density using Terrasar-X-Data , 2010, 2010 IEEE International Geoscience and Remote Sensing Symposium.

[35]  David J. Spiegelhalter,et al.  Machine Learning, Neural and Statistical Classification , 2009 .

[36]  Zhang Wei,et al.  Construction of ratio build-up index for GF-1 image , 2015 .

[37]  Nathan J. Heinert,et al.  Extending satellite remote sensing to local scales: land and water resource monitoring using high-resolution imagery , 2003 .

[38]  J. Townshend,et al.  A stepwise regression tree for nonlinear approximation: Applications to estimating subpixel land cover , 2003 .

[39]  Yongfeng Cao,et al.  Building unit density detection from high resolution TerraSAR-X image based on mathematical morphological operators , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[40]  Qihao Weng,et al.  Remote sensing of impervious surfaces in the urban areas: Requirements, methods, and trends , 2012 .

[41]  Jingshui Zhang,et al.  Building extraction from high resolution SAR imagery in urban areas , 2011, Geo spatial Inf. Sci..

[42]  Hong Sun,et al.  Urban building density detection using high resolution SAR imagery , 2011, 2011 Joint Urban Remote Sensing Event.

[43]  I. Good,et al.  Fractals: Form, Chance and Dimension , 1978 .

[44]  P. Burrough,et al.  A fractal approach to the classification of Mediterranean vegetation types in remotely sensed images , 1995 .

[45]  E. Terrence Slonecker,et al.  Remote sensing of impervious surfaces: A review , 2001 .

[46]  Paolo Gamba,et al.  Spatial Indexes for the Extraction of Formal and Informal Human Settlements From High-Resolution SAR Images , 2008, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[47]  Dengsheng Lu,et al.  Land‐cover classification in the Brazilian Amazon with the integration of Landsat ETM+ and Radarsat data , 2007 .