Detection of Buildings in Multispectral Very High Spatial Resolution Images Using the Percentage Occupancy Hit-or-Miss Transform

The morphological hit-or-miss transform (HMT) was found to be efficient for the detection of buildings in panchromatic bands of very high spatial resolution images. The use of multispectral information was judged to be necessary to improve the results. The application of morphological operators to multispectral images is problematic, as no universal strategy for ordering the multivalued pixels of these images has been widely adopted. In this paper, we propose a new method to detect building locations based on a recently developed concept for the HMT to handle noise, called percentage occupancy HMT (POHMT). The parameters for the POHMT were defined with the aid of the top-hat by reconstruction transformation. To eliminate irrelevant locations, we applied a vegetation mask and verified locations by their proximity to shadows. The novelty of the method consists in the proposed vector-based strategy that allows for the application of the POHMT to multispectral images in order to detect building locations. Moreover, an original technique to automatically define the parameters for the POHMT was proposed. The method was tested on subsets from a pan-sharpened Ikonos image and from raw GeoEye and WorldView-2 images. The experimental results are promising.

[1]  Chi-Ren Shyu,et al.  Automated object extraction through simplification of the differential morphological profile for high-resolution satellite imagery , 2005, Proceedings. 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005. IGARSS '05..

[2]  Sébastien Lefèvre,et al.  A Multivariate Hit-or-Miss Transform for Conjoint Spatial and Spectral Template Matching , 2008, ICISP.

[3]  Peijun Li,et al.  Urban land cover classification from very high resolution imagery using spectral and invariant moment shape information , 2010 .

[4]  Paul Murray,et al.  A New Design Tool for Feature Extraction in Noisy Images Based on Grayscale Hit-or-Miss Transforms , 2011, IEEE Transactions on Image Processing.

[5]  Jonathan Li,et al.  MULTIVARIATE MATHEMATICAL MORPHOLOGY BASED ON PRINCIPAL COMPONENT ANALYSIS : INITIAL RESULTS IN BUILDING EXTRACTION , 2004 .

[6]  S. D. Mayungaa,et al.  SEMI-AUTOMATIC BUILDING EXTRACTION UTILIZING QUICKBIRD IMAGERY , 2005 .

[7]  Martino Pesaresi,et al.  Systematic Study of the Urban Postconflict Change Classification Performance Using Spectral and Structural Features in a Support Vector Machine , 2008, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[8]  Alexandre Carleer,et al.  Assessment of Very High Spatial Resolution Satellite Image Segmentations , 2005 .

[9]  Jing Peng,et al.  An improved snake model for building detection from urban aerial images , 2005, Pattern Recognit. Lett..

[10]  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..

[11]  Stéphane Lhomme,et al.  Automatisation d’une méthode d’identification de bâtiments grâce à l’ajout du test statistique de Fisher , 2009 .

[12]  Dong-Chen He,et al.  Building Detection in Very High Spatial Resolution Multispectral Images Using the Hit-or-Miss Transform , 2013, IEEE Geoscience and Remote Sensing Letters.

[13]  Huadong Guo,et al.  A Global Human Settlement Layer From Optical HR/VHR RS Data: Concept and First Results , 2013, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[14]  Pierre Soille,et al.  Differential Area Profiles: Decomposition Properties and Efficient Computation , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .

[16]  Christophe Collet,et al.  A robust hit-or-miss transform for template matching applied to very noisy astronomical images , 2009, Pattern Recognit..

[17]  Emmanuel P. Baltsavias,et al.  Object extraction and revision by image analysis using existing geodata and knowledge: current status and steps towards operational systems☆ , 2004 .

[18]  Pierre Soille,et al.  Edge extraction by statistical dependence analysis: application to multi-angular WorldView-2 series , 2012, 2012 IEEE International Geoscience and Remote Sensing Symposium.

[19]  Sébastien Lefèvre,et al.  A comparative study on multivariate mathematical morphology , 2007, Pattern Recognit..

[20]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[21]  Sébastien Lefèvre,et al.  La morphologie mathématique binaire pour l'extraction automatique des bâtiments dans les images THRS , 2007, Rev. Int. Géomatique.

[22]  Arzu Erener,et al.  Unsupervised building detection in complex urban environments from multispectral satellite imagery , 2012 .

[23]  Jesús Angulo,et al.  Hit-or-Miss Transform in Multivariate Images , 2010, ACIVS.

[24]  Dong-Chen He,et al.  Automatic change detection of buildings in urban environment from very high spatial resolution images using existing geodatabase and prior knowledge , 2010 .

[25]  J. Shan,et al.  CLASS-GUIDED BUILDING EXTRACTION FROM IKONOS IMAGERY , 2003 .

[26]  Zhongming Zhao,et al.  Urban building extraction from high-resolution satellite panchromatic image using clustering and edge detection , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[27]  Pierre Soille,et al.  Local Mutual Information for Dissimilarity-Based Image Segmentation , 2014, Journal of Mathematical Imaging and Vision.

[28]  Jon Atli Benediktsson,et al.  A new approach for the morphological segmentation of high-resolution satellite imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[29]  Kim L. Boyer,et al.  A system to detect houses and residential street networks in multispectral satellite images , 2005, Comput. Vis. Image Underst..

[30]  Antonio J. Plaza,et al.  A new approach to mixed pixel classification of hyperspectral imagery based on extended morphological profiles , 2004, Pattern Recognit..

[31]  Pierre Soille,et al.  Constrained connectivity for hierarchical image partitioning and simplification , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  He,et al.  Color Preserving Fusion of Multiresolution Images , 2010 .

[33]  Dong-Chen He,et al.  A new approach to building identification from very‐high‐spatial‐resolution images , 2009 .

[34]  Jean Serra,et al.  Image Analysis and Mathematical Morphology , 1983 .

[35]  Peijun Li,et al.  Multispectral image segmentation by a multichannel watershed‐based approach , 2007 .

[36]  Cem Ünsalan,et al.  Urban-Area and Building Detection Using SIFT Keypoints and Graph Theory , 2009, IEEE Transactions on Geoscience and Remote Sensing.

[37]  Soille Pierre,et al.  Tree Based Representations For Fast Information Mining From VHR Images , 2012 .

[38]  Cem Unsalan,et al.  Building detection using local Gabor features in very high resolution satellite images , 2009, 2009 4th International Conference on Recent Advances in Space Technologies.

[39]  Yun Zhang,et al.  Semi-Automatic Building Extraction Utilizing QuickBird Imagery , 2005 .

[40]  Paolo Gamba,et al.  Improved VHR Urban Area Mapping Exploiting Object Boundaries , 2007, IEEE Transactions on Geoscience and Remote Sensing.

[41]  J. Weber,et al.  Automatic Building Extraction in VHR Images Using Advanced Morphological Operators , 2007, 2007 Urban Remote Sensing Joint Event.

[42]  Liangpei Zhang,et al.  Morphological Building/Shadow Index for Building Extraction From High-Resolution Imagery Over Urban Areas , 2012, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.