Optimal fusion of optical and SAR high-resolution images for semiautomatic building detection

Building detection from different high-resolution aerial and satellite images has been a notable research topic in recent decades. The primary challenges are occlusions, shadows, different roof types, and similar spectral behavior of urban covers. Integration of different data sources is a solution to supplement the input feature space and improve the existing algorithms. Regarding the different nature and unique characteristics of optical and radar images, there are motivations for their fusion. This paper is aimed to identify an optimal fusion of radar and optical images to overcome their individual shortcomings and weaknesses. For this reason, panchromatic, multispectral, and radar images were first classified individually, and their strengths and weaknesses were evaluated. Different feature-level fusions of these data sets were then assessed followed by a decision-level fusion of their results. In both the feature and decision levels of integration, artificial neural networks were applied as the classifiers. Several post-processing methods using normalized different vegetation index, majority filter, and area filter were finally applied to the results. Overall accuracy of 92.8% and building detection accuracy of 89.1% confirmed the ability of the proposed fusion strategy of optical and radar images for building detection purposes.

[1]  Gangyao Kuang,et al.  Building detection from urban SAR image using building characteristics and contextual information , 2013, EURASIP J. Adv. Signal Process..

[2]  Mustafa Turker,et al.  Building extraction from high-resolution optical spaceborne images using the integration of support vector machine (SVM) classification, Hough transformation and perceptual grouping , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[3]  P. V. Arun,et al.  RETRACTED ARTICLE: An intelligent approach towards automatic shape modelling and object extraction from satellite images using cellular automata based algorithm , 2013, ArXiv.

[4]  Bisheng Yang,et al.  Extracting buildings from airborne laser scanning point clouds using a marked point process , 2014 .

[5]  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.

[6]  Ching Y. Suen,et al.  Application of majority voting to pattern recognition: an analysis of its behavior and performance , 1997, IEEE Trans. Syst. Man Cybern. Part A.

[7]  Yongfeng Cao,et al.  High resolution SAR building detection with scene context priming , 2012, 2012 IEEE 11th International Conference on Signal Processing.

[8]  Yongil Kim,et al.  Improved Classification Accuracy Based on the Output-Level Fusion of High-Resolution Satellite Images and Airborne LiDAR Data in Urban Area , 2014, IEEE Geoscience and Remote Sensing Letters.

[9]  Chongzhao Han,et al.  Building Detection from High Resolution PolSAR Data by combining Region and Edge Information , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[10]  Jean-Yves Tourneret,et al.  High-Resolution Optical and SAR Image Fusion for Building Database Updating , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[11]  D. Lu,et al.  A comparative analysis of approaches for successional vegetation classification in the Brazilian Amazon , 2014 .

[12]  Lorenzo Bruzzone,et al.  Analysis of the reliability of the double bounce scattering mechanism for detecting buildings in VHR SAR images , 2009, 2009 IEEE Radar Conference.

[13]  Qian Du,et al.  A Hybrid Approach for Building Extraction From Spaceborne Multi-Angular Optical Imagery , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[14]  Yong Wang,et al.  Building simplification using backpropagation neural networks: a combination of cartographers' expertise and raster-based local perception , 2013 .

[15]  Uwe Stilla,et al.  Building feature extraction via a deterministic approach: application to real high resolution SAR images , 2007, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[16]  Florence Tupin,et al.  Detection of building outlines based on the fusion of SAR and optical features , 2003 .

[17]  R. Pontius,et al.  Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment , 2011 .

[18]  Yun Zhang,et al.  Optimisation of building detection in satellite images by combining multispectral classification and texture filtering , 1999 .

[19]  Francisco Javier Ariza-López,et al.  Automated Assessment of Road Generalization Results by Means of an Artificial Neural Network , 2012 .

[20]  Paolo Gamba,et al.  Texture-based characterization of urban environments on satellite SAR images , 2003, IEEE Trans. Geosci. Remote. Sens..

[21]  Curt H. Davis,et al.  A combined fuzzy pixel-based and object-based approach for classification of high-resolution multispectral data over urban areas , 2003, IEEE Trans. Geosci. Remote. Sens..

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

[23]  Ram Chellappa.  Advanced Automatic Target Recognition. , 1998 .

[24]  Curt H. Davis,et al.  Automated Building Extraction from High-Resolution Satellite Imagery in Urban Areas Using Structural, Contextual, and Spectral Information , 2005, EURASIP J. Adv. Signal Process..

[25]  Hélène Oriot,et al.  Rectangular building extraction from stereoscopic airborne Radar images , 2005, IEEE Transactions on Geoscience and Remote Sensing.

[26]  Yun Zhang,et al.  A semi‐automated approach for extracting buildings from QuickBird imagery applied to informal settlement mapping , 2007 .

[27]  Florence Tupin,et al.  Extraction and Three-Dimensional Reconstruction of Isolated Buildings in Urban Scenes From High-Resolution Optical and SAR Spaceborne Images , 2011, IEEE Transactions on Geoscience and Remote Sensing.

[28]  Jean-Francois Mangin,et al.  Detection of linear features in SAR images: application to road network extraction , 1998, IEEE Trans. Geosci. Remote. Sens..

[29]  Lênio S. Galvão,et al.  Spectral/textural attributes from ALI/EO-1 for mapping primary and secondary tropical forests and studying the relationships with biophysical parameters , 2014 .

[30]  Qing Zhu,et al.  Mathematical morphology-based generalization of complex 3D building models incorporating semantic relationships , 2012 .

[31]  John A. Richards,et al.  Remote Sensing Digital Image Analysis: An Introduction , 1999 .

[32]  Mandeep Singh,et al.  SAR Image Classification Using PCA and Texture Analysis , 2011 .

[33]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[34]  Saman A. Zonouz,et al.  Identification Using Encrypted Biometrics , 2013, CAIP.

[35]  Uwe Soergel,et al.  Building Detection From One Orthophoto and High-Resolution InSAR Data Using Conditional Random Fields , 2011, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[36]  Jon Atli Benediktsson,et al.  Neural Network Approaches Versus Statistical Methods in Classification of Multisource Remote Sensing Data , 1989, 12th Canadian Symposium on Remote Sensing Geoscience and Remote Sensing Symposium,.